I surprisingly had good results when I told the LLM to only communicate in ASCII memes. It did a fantastic job of summarizing the situation using relevant memes, and the humor was enough to keep things fresh. As silly as it sounds, it's worth trying when you're in that LLM burnout corner.
This is legitimately the reason I'm looking to leave programming.
I got into programming because the problems of programming were interesting to me. But if the problems go from "figure out why this calculator is off by one in France" to "Get this LLM to stop spamming cutsey emojis", then maybe it's time for a career change.
Giving my "otherside", because the pressure to output more at work is real, but at the same time, out side of work, I love this. I'm able to do way more projects than ever before because a barrier to entry was always the amount of research+time required to start up a pet project.
My latest is, I'm really into fizzy/soda water and wanted my own continuous carbonator. My entire build from water source to tap with an ESP32 controlled pump, pressure, water level, cooling fans.
There were so many areas I made mistakes in my shopping cart and it found it - like Home Brewer likes 8mm lines but water filter systems like 9.5mm. Really optimized the versions from a simple on/off pump w/ float switch to effectively a full on PLC system. So many iterations gained by chatting with "someone more experienced". Once I get the parts I can build and have the software side running in less than an hour.
Did you make the move yourself from software development? I'm considering a move into economics lately but I wouldn't want to leave IT completely i.e. saying bye to a 15y career in software and all the stuff I learnt along the way. Ideally I'd find something in between but I don't know how feasible that is.
I'm no longer in corporate America, so maybe I'm out of touch a bit, but could you just...not...use an LLM? You can still solve interesting problems on your own if you choose to do so?
Yeah at many places you still can. It’s just so easy to turn your brain off and let the robot do a maybe good enough job that even people who know better are merging slop.
We’ve had 3 production incidents this week that slipped past CI because there’s a whole team that is just shoving out PRs without understanding what’s going out.
A lot is said about context you can feed into the LLM but I do think there is still superior power in human context awareness. That kind of ambient collation and organisation of the whole business and its purpose, all the different work going on and how it all relates to eachother. It happens when you isolate business units a bit too much also.
It's not surprising that if you have a hundred separate, isolated contexts working on the same business, that don't cross-talk and have no ability to subconsciously receive and collate the thousands of signals we get from our work environment, that you end up shipping lots of incomplete or incompatible work.
It’s not there yet but we’re clearly heading towards a world where the answer is “no, you have no choice”. AI is weaved into business processes. If Ai leaves a comment on your pr, you must resolve it before merging, you’re expected to “get things done” at a particular pace consistent with using ai, regardless of whether what you did is any good.
LLM skew the time estimate tho. Now everybody expect stuff based on LLM work instead of normal human work. I/we can choose to solve problem normally, but the expectations have changed.
There are plenty of shops where they are requiring people to use LLMs. Not "we require you to produce work at X rate" such that one can't hit the target without an LLM, but actually mandating use of LLMs based on the (unproven) assumption that it will boost productivity.
Part of the annoying thing is that if you're working on a product which uses LLMs, at some level you run out of levers to pull in terms of being able to fix things. At best you're stacking hacks on top of hacks to prevent unwanted output, but at the end of the day if the LLM really decides it simply doesn't want to follow your instructions, you can't do much other than resign to adding *IMPORTANT* and hoping the next model fixes it.
The experience is much closer to working with an external API that you don't have control over, and where the internal implementation details of the API randomly change every day so you can't even work around bugs. And those have always been the most frustrating parts of programming.
I got into programming to just build stuff, the coding is just a means to an end, try not to think too hard about the how and think more about the why and what
We get it, you don't have a passion for the act or the craft, just the end result, but I'm absolutely sick of hearing it all over this site as if it's a universal truth that some of us just don't recognize yet.
Sorry, some of us have a joy for programming where the how is just as important, if not more so, than the what and the why. No matter how much people proclaim that the how doesn't matter to them, it isn't going to suddenly make it true for others.
This isn't a response I expect from people who are here for a productive discussion. I'm sorry that you are sick of hearing this, but I'm not responsible for making sure you only read what you find worthy of your own personal brand of respect. Instead of attacking someone for simply offering their point of view, in what appears to be a quasi-gatekeeping effort, maybe you should look inward and discover what is making you this upset toward a complete stranger.
__I cannot take away the joy you have for programming simply by stating what drives me.__
I'm totally fine, just annoyed by how much this "try not to think too hard about the how and think more about the why and what"[0] is getting brought up every single time someone mentions why they prefer hand coding to vibe coding. At this point, it's being overstated, thus gives off less "this is why I use it" and more "come on, get onboard the hypetrain to dystopia or you're going to get left behind". It's hardly conducive to a "productive discussion" when it's the millionth time as a drive-by comment. What kind of response did you expect?
Look, I don't have a problem with your personal motivation. I just hate seeing it suggested that people should abandon their passion because someone else doesn't share it. There's absolutely nothing wrong with "I enjoy making something useful" just as there's nothing wrong with "I enjoy making something with my hands or figuring out how to make it". My problem is with "your enjoyment of that is invalid because I don't enjoy that, so learn to enjoy this".
0: Not really a statement of your drive, is it? More of a directive or suggestion.
But ultimately you got into this craft to solve a problem. That is how the craft developed. And when you build a very complex elaborate system, it can still have interesting technical challenges, even for a developer with AI. You should shift your technical insight to a higher abstraction level, where the AI cannot help anymore.
What’s interesting to me is reasoning about the problem and its implementation. And that doesn’t stop at any abstraction level. Reasoning in the small is just as important as reasoning in the large. And the issue with LLMs is that their capacity for sound reasoning is limited. They are sloppy on any level. You can’t get them to be thorough and dependable in reasoning, regardless of the abstraction level.
Well I think the reasoning of coding agents on lower levels is good enough for me that I don't have to constantly be involved with it, only occasionally have to dive in and help out.
I don’t think that the logical reasoning ability of LLMs depends on the abstraction level. Their heuristic knowledge differs between levels, but that’s a different thing. My concern is the reasoning capabilities.
Ok, so you're basically saying that the AI-generated code does it's job, but when you actually review it you think the way it does it's job is not as it should, and if you get into that flow, your agentic productivity goes down?
Yes you're right. It's that most programmers are so identified with the code, that now with AI they feel their whole identity is stolen, while indeed, being a developer is more than just coding, people!
+1. I’m in the exact opposite camp, I enjoy programming more than “shipping a product”. But the programming itself, coming up with solutions to tough problems, is the fun part. Shipping a product is a side-effect.
Those who like having a finished thing. Product people. These love LLMs.
Those who love building a thing, working through a problem, learning something new. Finishing a project is generally not required. For them LLMs are soul sucking hell.
This is just a purity test disguised in high minded rhetoric. Defining "quality" in practice is both impractical and a matter of opinion. Building something first, and making it better later, is it's own form of quality.
> do you mean my enjoyment from building things? I'm genuinely confused by this response.
I'm not surprised - your GGP comment indicated that you are more interested in the destination than the journey (you enjoy the output more than the process of crafting that output).
Nothing wrong with that - lots of programmers are interested in the final deliverable and don't really care about how the sausage is made, but you're reading a comment from someone who makes the sausage.
I never said I don't care about the coding itself, or the underlying quality of my systems. I can care about more than one thing, while still identifying goals that I have for how I spend my time.
It's not tantamount to that outside of your imagination. I've spend 30 years coding, I'm well aware the the underlying quality of the systems I build. Please try not to impart upon me these beliefs I do not hold. I stand by my initial statement, which in no way should be regarded as "I don't care about the coding itself". That's just your way of disregarding information you don't like to hear. It's an odious habit from people that disregard clarification in favor of their own preconceived views.
It's tantamount using the accepted definitions of the words in the language we're speaking.
Your comment is incredibly aggressive, hostile, and rude, of out nowhere. You should review the guidelines [1]. It's deeply disingenuous to either communicate really poorly or to backtrack from your position unannounced and then get aggressive about it when people engage with you.
> That's tantamount to "I don't care about the coding itself, or the underlying quality of my systems".
This is "incredibly aggressive, hostile, and rude, of out nowhere". Please leave me alone, I have nothing else to say to people like you.
For anyone else, imagine a winemaker that cares about their end product more than they care about growing grapes.. does that mean this winemaker doesn't care about the quality of their grapes? Probably not, but apparently to this individual the english language requires that we believe the winemaker to be disingenuous if they clarify their position on grape quality.
As I said downthread, that is exactly the opposite of why I got into this field, and I fully admit that I'm upset that people with your attitude were the ones vindicated by technological progress.
I don't think a career switch is really as simple as go do anything you want.you need a skill, and need to go through the entry level pipeline again. You also need too find it interesting like the other commenter mentioned. Otherwise you do just end up as a cashier or something unskilled.
I do not have the burnout but I certainly operate similarly to the author. I continue to be unable to establish a workflow where allowing the LLM to generate code that I review is faster than writing the code myself. Literally the only two ways out of this dilemma is to blindly trust what was generated or to generate an uncharacteristically exhaustive suite of unit tests to validate every possible scenario. I just write the business logic myself and have the LLM do a lot of the rest. Boilerplate falls into the latter as well.
I don’t understand what could possibly need to be made so fast that isn’t totally made up billable hours. Running at top speed long enough to be burned out is either ineffective, or valuable enough that someone else can take over while you sleep.
Even with Fabel and all that I constantly keep having to babysit it and correct it like it’s an adolescent and it gets really old and the amount of code. It produces not all of its great at all. I’m burnt out looking at. It’s poor coating that somehow magically works.
It sounds kind of like being stuck working with coworkers who--while not overtly hostile--need constant hand-holding and repeat the same mistakes over and over...
I've taken a bit longer than I wanted but it will be open sourced soon.
It's a durable orchestration engine that takes in specs/requirements and coordinates agents externally (meaning the engine drives the loop, not an agent) until the work is fully implemented/verified and reviewed.
It's meant to be used with any harness as basically the last step. You plan your work with whatever LLM you use and then hand off implementation to the engine (through an MCP server or other surfaces)
It can use your OpenAI/Anthropic subscriptions or any other provider and you can mix and match models across implementation and review in any way you want with fan out for parallel reviewers and more.
The goal is to produce high quality unsupervised code that matches your requirements and is reviewed throughout the implementation rather than at the end only, so that mistakes don't compound.
I think having style guidance in your context is valuable for avoiding this kind of thing. Having to read awful, cliched text all day is even worse than having to read reams of useless code. I have some simple humanizing content in there that specifically calls out the rhetorical devices that AI loves, and it drastically improves the diffs and comments. It also makes the coding performance generally slightly worse, but ergonomics uber alles.
I don't think I have a "burnout", but LLMs are really exhausting due to amount of pressure they generate. No one is really pushing me to increase my workload, but at every moment there is always something ready, done by my clankers or clankers of other people that I could be unblocking. In the past (before LLMs) it was already hard to keep up, but now it feels like there's 10x more things waiting at any given time, and there could be 10x more if everyone just "optimized" and streamlined processes fed the AI even more tasks in parallel faster. It just being a bottleneck of everything, all the time is tiring...
A I am happy about all the little side-projects, and ideas it help my realize, and I enjoy exploring this new world, but I've noticed LLMs feed my unhealthy "don't want to take a break and waste time being idle" mindset, and I need to correct it.
> No one is really pushing me to increase my workload, but at every moment there is always something ready, done by wankers
I confess that the above variant on the quotation is how I originally read it. And that's just about how I feel now with trying to sort through vibe-coded slop projects that are put forth by (well-meaning, probably good intentioned, not evil) people who represent them as if they're the handcrafted result of one dedicated developer.
Individual gains from llm seem much larger than net productivity increases. I think a major source of this discrepency is people creating more work for their coworkers at the speed of slop. Especially the people with no idea.
"I did a Chat output, please fix and review it " is the kind of thing that empowers the people who used to have a minimal productivity, and now lets them to wreck things on an industrial scale.
This is valid in the other direction as well. Principle engineers, CTOs, with legitimately earned authority end up using that authority to 100x their output onto the team as if it was a Godsend unlock.
It's not. There is no one person that has universally good taste. Also, we're not in your head, no matter how much better of a coder or whatever. We're not in your head and it's all terribly painful to navigate.
>"I did a Chat output, please fix and review it " is the kind of thing that empowers the people who used to have a minimal productivity, and now lets them to wreck things on an industrial scale.
AI is not a productivity multiplier. There are diminishing results.
The ones that notice the highest increases of productivity are usually the ones that were unproductive at best and dangerously incompetent at worst.
> Individual gains from llm seem much larger than net productivity increases. I think a major source of this discrepency is people creating more work for their coworkers at the speed of slop. Especially the people with no idea.
Lots of companies (nearly all, I’d wager) of any size were leaving bare-minimum a 2x software development speed increase on the table before LLMs, having nothing whatsoever to do with how fast anyone was typing or thinking up code, and everything to do with how they organized and supported development work, and with your basic ordinary corporate dysfunction.
My company, I’d say it was more like 4x or 5x they could have achieved before LLMs, by fixing processes and reducing how often management steps on their own dicks.
All the people I’m seeing with crazy-high LLM productivity at my company? They’ve been given enormous autonomy to basically go do WTF ever they want, and people are jumping to get them anything they need (and most of what they’re doing is prototyping, for that matter). So right off the bat, if they’re competent, they should see a notable multiplier on productivity even if they weren’t using LLMs. Not that those aren’t helping, too, but if you don’t change processes they’re not all that effective, because the problem wasn’t speed of code-writing (and if you can change processes, you already could have sped up development a lot before LLMs…)
In my place I see currently a governance panel effort around LLM agent skills, it is so much shit show that I expect productivity is back to 0.5x pre-agents. But not pre-LLM as autocompletion was really helpful in the trenches. The tool in wrong governing hands and you see sand in cogs thrown in.
> LLM took away the more creative and variable part of the work, and left the repetitive QA rubber-stamping.
This 1000 times. The number of times I now have to use my brain to do something engineer-y is now something like 5 times per week, usually eyeballing some architectural decision from (as you mentioned above) someone else's LLM.
I really loved writing code, and I loved that I could do it for a living. Obviously, nothing is stopping me from continuing to write code and solve problems with my own brain, but that's absolutely not the efficient way to work anymore.
The most high-leverage activity I've done in the last 6 months is a build-out of internal AI orchestration platforms and data access layers so every employee in the company can built with AI against our own data (particularly non-engineers). It has unlocked so much for everyone. Yet, my only real claim is a) coming up with the idea and general architecture and b) ensuring smooth roll-outs and hosting "office hours" for months to help new employees onboard to these new AI tools I built.
High-level design and architecture decisions, quality assurance, and balancing decision-making through subjective areas like UI/UX. That's mostly all I do. Now that I'm leading engineering, I just think even higher-level while the engineers use orchestrated AI do built vast swaths of code. Then I frantically bounce around approving sensitive PRs and architecture decisions -- most of which were written by Claude, described by Claude, and usually don't need a lot of correction.
I don't have an employer. But most of the excuses I used to tell myself are simply not believable anymore and that causes pressure leading to overworking myself.
LLMs drive the unit cost of cognition to zero. Therefore, you will exhaust yourself near-instantly trying to drive differentiated value out of cognitive work.
Non-arbitrable labor is one safe haven: bending steel, drilling wells, running cables, flying drones, etc. Physical agency gets you a premium the clankers can’t (yet?) trespass upon. That’s why guys building data centers are making bank & job-hopping while the SAs administering the computational guts of them are struggling.
A second vector is reputational: either by authority (you’re a regulator) or by taste (you’re a rare/reknown specialist) you make quality attestations about cheaply-produced cognitive artifacts.
The first vector is a big community; the second is not.
Get out of being in a knife fight with the clankers on their own turf, they’ll gut you.
Flying drones is an interesting one, I guess you do have to drive the car out to site and set up the drone. But a lot of drone ops are waypointed, automatic flight. I can see a future in which the only thing the operator does is drive the drone van to site, hit the deploy button as the drone pops out the roof, and wait for it to return. Mission set up already by an LLM prompt back at the office.
Then why are so many others in the thread reporting being swamped with requests to review coworkers' slop? If it's genuinely "cognition" at trivial cost, surely this review would be completely unnecessary?
One of the reasons they exhaust me, is that it's always "one more prompt" to get a UI correct. It's often just slightly off, but it can take 5-10 mins sometimes to rework something. It has led to me working much longer hours.
I think this is in part because I am one of the software engineers that always liked building products more than writing complex software. So, I am driven by the feeling of creating something. And I want to get the feature perfect and complete. But getting from 95%->100% done can take a long time with UI work for me.
Main blocker is I am using apps like Conductor and have lots of plates spinning at once. But that's on, me and I should try and start completing the last part myself.
Maybe when they get better at making SVGs of pelicans riding bicycles, they'll also get better at making UIs that can be reworked into sensible form without too much effort.
I'm getting so many requests to review LLM-generated documents - planning docs, docs intended for end-users, project docs, business plan docs. A team member sent me a zip file with about 30 LLM generated documents in it the other day and asked if I could review them right away. And a lot of it was just repetition and/or stuff that was just out of left field, made-up, hallucinated stuff. They're able to generate this stuff way faster than we can review. It's just really tiring.
Wait, what? I thought everyone agrees that modern models post September 2025 (or whenever Opus or whatever 5.6789 was released) do not hallucinate, make things up, contradict themselves and can review their own output into perfection regardless of task, goal or context????
In general I think from the coding side they're more robust now. However, people generating docs are maybe not as experienced with how to prompt in ways that avoid having the LLM tell you what you want to hear. I think this is still a pitfall that can easily be fallen into. Those of us who are doing LLM-assisted coding for the last couple of years are more aware of this now. Those who are planning/management folks are still kind of susceptible depending on how much experience they've had dealing with LLMs.
They do, just less. To the degree of being usable, as long as there are guardrails and they're used responsibly. This also implies you need SOTA models on max reasoning.
> make things up
Same as above. Ideally you'd give them some way to verify their claims, like web search or browsing and referencing docs, Jira tickets etc., basically improve the signal to noise ratio.
> contradict themselves
They do so way less than before, as long as the above is true.
> can review their own output into perfection
They are pretty good at reviewing things, especially if you make them do adversarial review! It will never be perfect, but can be close in quality to human output (e.g. the code they produce, when used properly and with intent, is better than the code I've seen many developers write and ship before LLMs were a thing).
This also more or less scales with how much compute you give them - three parallel review agents will turn one output artifact into something good with higher confidence than two, and definitely better than with no review.
> regardless of task, goal or context????
Garbage in, garbage out. I won't be an asshole and say that you're holding it wrong, nor will I say that anyone should listen to the claims marketing AI (absolutely delusional takes, meant to attract investors), but we're slowly getting to a better position in regards to LLMs, year by year.
It's just a shame that the peak of inflated expectations hit while the technology still hasn't fully plateaued and reached whatever its ceiling is.
Yeah, my bad, though I’ve also heard those arguments more or less said genuinely - on one hand people hold LLMs to some unreasonably high standard, expecting to one shot apps before being deemed good, and on the other just outputting slop with no regard for the quality.
I always laugh because I've been practicing prompting every single day for the last few years, if they want to start a prompt fight, brother let me at 'em.
Don't know if you are serious, but why become part of the problem?
Why not just review a single document quickly, find an error which invalidates the document, and send it back saying "Policy paper 1 mentions X as being on the business plan for Y, it's not on the plan, please can you fix."
Unless you can write a good-sounding reason why it's on them to review a LLM output before sending it to you, they will outsources this reviewing to you, and it's a lot of reviewing.
Original comment stated that it was 10 documents, all LLM-generated.
In my experience, it does take a lot time and effort to find contradictions between 10 documents. Even with good documentation, it's hard to build a mental map for that amount of information.
Seems like for such requests it's necessary to get some proof of work: require a meeting where for every artifact they sent you to review, they briefly explain the gist and point out the motivation for creating the artifact.
The only way to even start to counter that is to make it a firm company policy that if you use an LLM to hallucinate any documents you absolutely must thoroughly review them yourself before you send them to anybody else, and that you are still responsible for the quality of LLM-generated content.
Getting an LLM to vomit out a bunch of documents and sending them straight to another colleague is absolutely unacceptable behaviour.
This is going to just run up against the insanity that is tokenmaxxing every moment of the day. When people are incentivized (upon pain of firing) to get the LLM to vomit out as much as possible, they're hardly going to stop and ponder if schlepping the slop over the wall is acceptable if the alternative is a pink slip.
We employees need to remember that most software projects fail. So the work we produce should have lower value than we give it.
We also need to be motivated to stay in our jobs.
Most developers like their projects and value their work. But the chances are that it's for nothing.
Many developers know they work on bad products (gambling industry, military, surveillance, whatever) and so it's here that they focus on their technologies, tools and frameworks rather than the work they produce.
"Agentic engineering" for example.
Id be curious to see what and how Googlers are doing with their 20% time.
If tokenmaxxing wins in your company, your company is going to lose. There's an external reality out there, outside your company, and your company has to produce things that actually work out there. Hallucinated AI slop does not help you do that. It leads you to unworkable plans, and if the plans produce, they produce unsellable products.
If you're an employee in that situation, push back if you can. If you can't, put your resume on the street. (But that may not work, these days. If it doesn't, all I can say is ride it out as best you can, and try to maintain both your job and your sanity. How? I don't know.)
> I'm getting so many requests to review LLM-generated documents
That's the other nightmare of AI slop. So easy to generate endless content. Who will review?
Just today the boss request I review slides for a presentation. But it's all AI slop, generated from querying tickets and docs and who knows what. It's mostly sort of correct but also plenty misleading and incorrect. So now I have to fact check all this slop which will take hours (even with my AI assistance) and rewrite most of it.
If AI didn't exist, he would've had to do the research to generate the content and it would be 99% correct and I could just give a few notes of feedback in 5 minutes. But with the asymmetric AI workload, he can generate it in 5 minutes and I get to spend 3 hours correcting.
> If AI didn't exist, he would've had to do the research to generate the content and it would be 99% correct and I could just give a few notes of feedback in 5 minutes. But with the asymmetric AI workload, he can generate it in 5 minutes and I get to spend 3 hours correcting.
Maybe, depending on the boss. Some would have spent five minutes describing what they wanted, and someone else would have spent three hours creating the deck.
I'm fine with that. The company doesn't have infinite people so as long as someone spends 3 hours generating and I spend 5-15 minutes reviewing, that's fine.
Problem with AI is that generation is so many orders of magnitude faster than reviewing so it's basically infinite monkeys on infinite typewriters.
I got this problem with my own employees, LLM are fine, but lazy slop is not permitted. Current idea is to have a clear "best practice" template for most of the research/specs/problem definition they submit and it reduced the slop to a manageable level.
But this might work in a smaller company where the management is reading and is strict about these things.
> A team member sent me a zip file with about 30 LLM generated documents in it the other day and asked if I could review them right away. And a lot of it was just repetition and/or stuff that was just out of left field, made-up, hallucinated stuff
You just discovered the unlock to massive AI-driven productivity increases: outsource the hard stuff to others, or just don't do it at all. Keep the easy tasks that generate a big volume of output for yourself.
> I don't think I have a "burnout", but LLMs are really exhausting due to amount of pressure they generate. No one is really pushing me to increase my workload, but at every moment there is always something ready, done by my clankers or clankers of other people that I could be unblocking.
I see a different type of pressure: I'm at a company that still is requiring everyone use LLMs with token leaderboards, time-spent measurements, and impacts to performance reviews, and all that. So I find myself having to carve out some percent of my time to stop doing productive work, and "go do AI to show token use." So my workload hasn't changed (or it's gone up), but I have N% less time to work on it because I have to spend time appeasing the AI gods...
Just have an agent chug on a side-project for you, or set up a CI script to review every pull request or some similarly “helpful” task. That should eat a lot of tokens!
Man. If I had this kind of mandate I could really burn some tokens. Review each new PR and extract 100 topics to debate related to it. Spin up 1000 sub agents, each with a different personality profile system prompt, to debate each point until consensus has been reached. Synthesize the learnings into a limerick. Build a Spotify playlist that pairs with the tone of the debates. Post the limerick and link to playlist on the PR and tag me to notify me that I have a PR to review.
Oh man, when MCP was still new and shiny I made an MCP that let the AI choose appropriate theme music for what it was doing and it was an absolute blast, I need to make a more modern one.
Peer Gynt Suite's "In the Hall of the Mountain King" made a prominent appearance, but so did Aqua's "Barbie Girl"
Depends on how much you're asked to burn I guess. Until one point, it's actually helpful. Then there's a point where you can do stuff that's semi helpful but doesn't get in the way. But then I would imagine you reach a point where you have to come up with a token burn strategy and some kind of narrative for your manager that's in line with it. I bet at that last point, it gets taxing.
Probably like eating. Having to eat less to loose weight isn't great. Eating anything you want without worries is great. Having to eat more than you want to gain weight, not great.
I wonder how long this will still be a thing. More and more companies seem to come to the conclusion that tokenmaxxing is just too expensive for the value it delivers. Will there be others that continue doing it? Will there be companies that advertise "unlimited tokens" as part of job listings? How will they react when employees test the limits of "unlimited" (whether by accident or not)?
I am happy about all the little side-projects, and ideas it help my realize..
Same, but I really have to fight the urge to just add fun new features to things I work on any time inspiration strikes. I am an appalling 'feature factory' if I don't actively keep myself in check. The cost of just building everything is so low, but the value of those things is also incredibly low, so I'm often just bloating what I build.
There's been a lot of articles and posts about the increasing importance of 'taste' in software built with AI, and I'm finding I know need to look for strategies to find some.
I echo this entirely, brother. I think a lot of us developers have a lot of ideas that were unrealized, and now we have this opportunity to do it. And any time an LLM is sitting idle, it feels like we're wasting our time. Why aren't we having it built something for us? Currently, I work on about three projects at work at the same time and about four personal projects at the same time. My day just zips by. I'll burn four hours without even thinking about it. It's exhausting but exhilarating. I do wonder if burnouts in the future though.
> I think the similar thing happened due to factory manufacturing automation. What used to be a varied skillful craft in a shop became standing in a single place of an assembly line doing the exact same thing whole day.
I had to think of Charlie Chaplin's Modern Times. The author's observation is basically the main idea of the sketches, i.e. humans having to follow the pace of the machines instead of the other way around.
> LLM took away the more creative and variable part of the work, and left the repetitive QA rubber-stamping
“I wanted a machine to do the dishes so I could concentrate on my creative work, and all I got was a machine to do my work so I’m left to wash the dishes.”
I wonder if anybody has an implicit fear that with LLM you're expected to be a 20x engineering all the time, otherwise you're out. Can also lead to people producing shiny apps that impress others (sometimes for legit reasons) even though they have no idea how anything work. A "ship value" culture will not bother with the inner workings or actual skills.
> I've noticed LLMs feed my unhealthy "don't want to take a break and waste time being idle" mindset, and I need to correct it.
Embrace it if you’re like me and feel uncomfortable having an idle mind, embrace it! You’ll get more done and being 120% go go go is impossible over the long run so eventually your body will just say I need a break then once you recover full steam head again on the treadmill
> but at every moment there is always something ready
Yes, this is to me the primary driver of the extreme AI burnout. In ~30 years in Silicon Valley and many, many startups, the pressure has never been as intense.
Before AI I'd mostly work on one thing at a time (at least within a given hour) and in the evening I wouldn't start a new 6 hour task because it's too long, so tomorrow is another day.
Now, that 6 hour task is more like 30 minutes, so there is intense pressure to just knock it off tonight. And then the next one. And one more. And while the bot is thinking, to have 4 other work streams in parallel so there is never, ever, a break in the day. The human mind is not built for 100% utilization 15 hours a day.
> In the past (before LLMs) it was already hard to keep up, but now it feels like there's 10x more things waiting at any given time, and there could be 10x more if everyone just "optimized" and streamlined processes fed the AI even more tasks in parallel faster.
I find LLMs to help me manage the unrealistic workload I have, because at least now it's feasible instead of just getting more work piled on top of me with a never ending backlog (that people actually expect me to thin, not let grow). Add on top of that colleagues that would have death by commitee'd many ideas and now just have to argue against actual MVPs that work instead of ideas (or can be proven to not work and discarded without wasting time on them in some cases), and I don't even hate my job as much!
It's just that to ensure that the technology is not a net negative, I need millions upon millions of tokens every single day (tool runs, adversarial reviews, testing), but once you get that inflection point, alongside needing a good enough model, the floor for which currently I'd say GLM 5.2 on Max reasoning reaches, or use something like SOTA Anthropic/OpenAI models, it becomes a pretty good way of working.
Hmm. When you put it that way, it sounds like LLMs and social media trigger the same "I have to see what's going on now" pattern (and therefore can wind up at the same kind of addiction, with the same problems).
I don't have much success with using the LLM to make changes to a big legacy codebase. Instead, I use the LLM to gripe about things I don't like in the code. Usually, it is a brilliant commiserator.
I've started feeling slightly physically ill when I read Opus output for hours straight. This article rings very true for me. I've started complaining about it with my team; at least have a personal style guide in your agent rules that eliminates emdashes, the "it's not X, it's Y"s, the long lists of modifiers before the noun, using the word "land" to mean finish, etc. I hope this is just a phase of adolescent LLMs.
`arc land` is burnt into my brain by Phabricator, so I'm aware that the term predates LLMs, but it still drives me nuts.
It's impossible to undo some of these linguistic wobbles. Even if you could filter out 100% of LLM input, the humans themselves are learning to say "land" at a higher frequency now.
I had Claude make a world cloud from its responses because I was curious to see how big "honest" would be. It barely showed up, so I asked it to just give me the counts and it responded telling me it was trained not to use the word "honest" much because it makes people distrust responses (in addition to showing me the counts).
I just did this on one .claude directory and >20% of the answers there included some variation of "real", "actual", "exact", "honest", "genuine", "valid", "true".
This is one of those things I barely noticed because I tend to read fast and skim. Someone pointed the over use of these terms and now its like hitting a set of spike strips every time I'm reading the output from any given model.
Its like when someone points something out a in picture you never saw and now you cannot "unsee" it ever again.
I was describing this exact feeling today. I haven't quite been able to put it into words but I do get slightly physically ill. Almost similar to mild trypophobia?
Me too. It feels like I’m taking psychic damage from reading so much of this stuff. Contrary to the theory that it’s “just the contract workers’ Nigerian English,” I think the models are developing an ultra-terse hyper-stylized dialect of their own under RL pressure. They seem to be writing increasingly in _code_, and I don’t mean computer code. The words don’t mean quite what they mean to humans.
Over the last few days with fable I've found it at times incomprehensible, terse word salad. It also invents phrases assuming I'll understand (but that could be because it's reusing terms in the codebase I no longer remember).
I've often had to paste its output back in to ask it what it actually means. Weird.
I think the main thing is just fatigue. There's so little variety. Each model has its preferred idiolect which everyone becomes tired of due to ubiquity. That's the worst part. It's like always eating fast food.
My non-English-native-speaker head of development, to whom I report, does 100% of his work using LLMs and doesn't even check if the code compiles, but somehow this isn't my biggest problem with it – it's the botspeak in the PR comments (or answers to my PR comments) that are so clearly not written by him, and the documentation that makes absolutely 0 sense sometimes even if I break it down. Just a word salad of "robust", "maintainable", "smoke test" that amount to absolutely nothing. And the "You're absolutely right, I fixed it" responses (narrator: he didn't fix it).
I used to have a lot of fatigue due to it until I stopped caring.
I'm starting to wonder if I can adapt, or how much longer I'll be able to take it. It's painful to read the botspeak all day, but it's more than that. The incentives to crank out loads of "results" are immense, but I no longer trust anything "I" "produce," and I'm not building on my knowledge of the system. They just want more and more slop. It's slop on slop at this point. I can't raise concerns or I would get fired. But I'm still responsible for the slop. It's starting to make me anxious.
"That's such a clever way to see things! Let's delve into that!"
The bots (all of them) seem to show patterns of overuse of specific phrases, words, and punctuation.
Some of those are the ones you mentioned. Another that I've been seeing lately is overuse of the term "gate", wherein: As a human, I know what a gate is. A gate is a thing that can be open, or that can be closed. It might be locked or unlocked. The path beyond the gate may be passable or impassable or nonexistent. The gate is just a gate, and the presence of the gate doesn't imply whether it is open or closed.
But in bot-speak, a gate only refers to a hard block -- an impassable construct. Like a fence or a wall, or even a lava-filled moat.
But while a lava-filled moat is intended to be impassable, the bot uses "gate" -- a thing that is designed to be passed -- to describe that same kind of obstacle.
That's misuse of the term, I think, based on decades of dealing with gates in reality: Usually when I encounter a gate that is closed, I just open it and walk through.
I do have instructions that tell the bot to avoid that usage of the word and it ignores them sometimes anyway.
But "gate" is just today's problem-word that comes to mind as I write this. Yesterday, it was something different. Tomorrow, it will be something else entirely.
The overall pattern here is that of gratingly-repetitive bullshit-grade jargon that doesn't fit to begin with.
I like that term, botspeak. I'll keep it around and use it.
One thing I did recently with the bot definitely involved actual smoke tests, though: I was working with real hardware that can blow up in real ways, with the bot doing all of the circuit design work and coding based on my goals while I just distantly commanded the show from On-High and plugged shit into a breadboard.
(The project works well and I consider it to be Good Enough; I might go back and polish it more later. There was no smoke, but there could have been.)
My expectation is that you'd hear a lot more about "gated communities", "gatekeeping" etc. than any of the uses of gates that give warm fuzzies. (As a suffix, it's also associated with scandals; but that probably isn't relevant here.)
I found Codex to use "gate" in a different sense: As the condition of an if statement. I have a local style rule not to use that. Another really grating thing is to use "X-shaped" for "something vaguely related to X". And using temporal words like "still" and "already" in contexts with no temporal connotation.
This has been my experience as well. It's incredibly grating to repeatedly read "genuinely load-bearing", "honestly?", etc. I've tried to get Opus to stop using these phrases via an entry in its memory, with mediocre results.
I don't mind interacting with LLMs myself and find they increase my productivity a decent amount. I just can't stand dealing with other people's slop.
Getting sent IM responses that are copy pasted LLM nonsense. Getting a massive PR to review that was generated overnight and the author didn't read it first.
So annoying, I'm dealing with a client that just constantly feeds my responses to their question into AI. Which of course just asks more questions and tells me how clever I am. I also know the client isn't reading because in many spots I put "[Client Name] you need to answer this directly as we need to know the actual real business detail" and its ignored or the AI provides a detail I know is made up.
Ask random questions until you get enough sense of things to ask "the right" questions. Never stop asking questions. Use everything you can to get the answers and never settle for any answer no matter how good it sounds, doubt it and go back to step 1.
It's burnt me out too. I'm generating 10x more features and multitasking across 4 disparate projects. My greatest concern is I don't really have a strong connection to the underlying fundamentals anymore. I need to see how the things works to internalize it. Now I just trust that the agent wrote this piece correctly.
The productivity drive and the sheer feature set you can generate in record time makes it easy to forget proper sdlc hygiene.
Knowing how things work, knowing what should be possible and where “there be dragons”, and having a pretty well-developed “sixth sense” for all kinds of things is proving just as valuable with LLM-heavy programming as it did before.
… but I am almost certain I’d never have developed those in the first place if I hadn’t spent 25ish years programming on a bunch of different platforms and setting up servers and networks and all that, without LLMs.
I dunno how you make another “me”, now, while before lots and lots of programmers naturally ended up as someone with skills and knowledge like mine, and those skills seem super useful when writing code with LLMs.
I don't really understand how this isn't a self-inflicted problem? Perhaps it's because I'm not really mandated to use LLMs in a particular way, but I've had great success doing a combination of writing code myself and using smaller but faster models as a sort of "flood fill". The larger models can also be useful when you're implementing something which already exists in similar form in the codebase, because you can just put that code in the context and you'll get something very similar outputted. So the more code you write, the better the LLM can be later on. Codebases should get easier to add to the bigger they get, not harder.
Of course if you're supposed to achieve so much output that it's not possible to do anything but vibe it, fair enough.
is there any evidence that Alec Scollon, the first time blog author responsible for this post, even exists? look up the name. boo this post and the premise behind it.
Define "exists". Are you questioning whether a human typed those characters with human fingers on a keyboard? Or are you questioning whether Alec Scollon is the name on that human's government-issued ID? It's not exactly new or unusual for people to use pseudonyms.
From my experience, there are mainly 3 burnout reasons.
1. Multi-tasking is the top one. I usually have to frequently switch between 3 to 5 agent windows which are on different things. It's extremely exhausting when each round takes a few minutes. Before coding agent era, I believe most developers had chance to spend 2+ hours focusing on one thing. Now coding agents have increased my spectrum on the tech stack, but the bandwidth to do deep work isn't increased.
2. Agents are good at getting things running without crash, but do not guarantee to produce correct code. This is quite different from human experts with fundamental knowledge.
3. I also get frustrated when reviewing piles of AI generated low quality PRs. My attention is a limited resource. I don't waste too much energy on other people's work, but if I don't spend more effort, the entire project is corrupted quickly by reckless AI generated code without human author's careful thoughts and designs. Working with people who have less due diligence in mind is painful, working with them in coding agent era is 10x painful because they produce 10x shit. It's a team culture challenge that cannot be easily enforced.
Agreed. I am working hard to restrict myself to only 1-2 agent workflows at a time. More is untenable, though it’s so easy to fall into the trap of deploying an agent “just for this minor fix.”
The worst is that every agent session is generating so many "btw fix this" side-quests that it is really hard to stay in the task focus. I throw some into todo list manually but still it is exploding by the day. Perfect is evil of good.
The reason I'm getting LLM burnout is from dealing with the obvious neutering and opaque downgrading of all the top models.
Prior to the last 12mos AI companies were hell bent on squeezing out the best results from mediocre models.
But... now that the top models have progressed, those same AI companies have switched their efforts into reducing the computation (cost of a producing a result) as much as possible without being too obvious.
What was an exponential slope in the quality of results over the last 36 months has now nearly flat lined.
Smart people have been falling into this trap as long as LLMs have hit production. Supposedly early internal versions of GPT-4 had "sparks of AGI" but the public version was "dumbed down for safety"
I feel the same way about consumer AI tools now. Gemini and ChatGPT have been abysmal lately. They can no longer be relied on to do multi-turn searching and thinking.
Before, they could stay in thinking mode for more than 7 minutes. For example, "find a source for this claim" would search, analyze, and self-adjust the query. Nowadays, even if I push for it, I cannot make these tools work for more than 30 seconds before they give generic answers, even in "Pro" mode.
At one point we considered adding artifical delay to responses because irrational users dont trust something that finishes fast, even if its the same quality.
How empirical are your comparisons of new and old outputs?
Hell, the Opus 4.5 moment was only last November, and that was when agentic coding and most coding CLI tools became truly first class options. That's a wild paradigm shift. Hell, GPT-5 wasn't even out (that's August of last year). Most people were using 4o. Their current offerings are wildly better for coding than 4o was.
I generally don't agree with the original commenter here. I think many of the complaints about model regressions are the result of increased usage and increased scrutiny revealing gaps there were there all the time. I've been more critical than most of the output quality since my initial "wow" moment was pretty early - GPT 3.5 API - and the results then were extremely obviously not production ready. But, keeping that level of scrutiny through my usage, I haven't seen the falloff that people who don't look at the output every time claim to see.
But that's also let me use "agent" stuff longer, I guess? The better you were at knowing what you wanted and how to ask for it, the less of an inflection point that you got from Opus 4.5 or GPT 5.
Some of the highest-time-saved-for-max-ROI agentic problems I've solved to date were in September and October of last year with Claude or Cursor.
What helped was a sleep and work system, oriented around being offline that was inspired by nature and from my earlier days in working in tech while car camping across the national parks.
Basically: the sun wins in terms of how all energy on the earth is structured, and expressed. All manners of cycles of organisms and living systems are in relation to its rise and fall, and even its particular color spectrum phases (whether thats night oriented or day). I call this our real circadian rhythm; it's used to being signaled by the light of the sun and maybe fire for millions of years and it isn't until recent centuries when we started tricking our biology with LEDs and lights. So the solution is simple. Orient yourself around the light of the sun and make sure it's the first and last major light source you see; blue limiting is the most important part BEFORE sunrise and AFTER CUT OFF ALL BLUE LIGHT. On my Mac I use a red light filter (using it now, it's 11:07pm ET and the sun went down about 2.5 hours ago). It's really hard to stay alert and chatting with an LLM when the only light sources are red and you keep them dim at that. Our ancestors would rest when the sun's at its peak (~1:05 pm today) and that's a good time to divide my own day productively as well. With intentional breaks diving the middle of the day with sunlight anchoring it, my nervous system is more relaxed, and by the evening time, it's also ready to transition out of anything blue-light assisted and most intellectual work and problem solving falls into this bucket. It's really hard to explain but it really works so simply. To enjoy the process a little more I made this fun sun clock, check it out at https://sunsignal.app
I once experimented with beeswax candles as my only after-dark light source. This meant no hyper-stimulating screen activities whatsoever, too. TV, phone, video games, browsing the web? Nope, nope, nope, and nope. Just dim, warm light from actual flames.
Cured my lifelong “night owl” “trait” in a couple days. Shockingly effective.
Turned out to be hard to keep up and still, like, exist with other people, and you’d probably need to relax it a little in Winter unless your job lets you work reduced hours to kinda “hibernate” (otherwise when would you do anything that’s not work but requires light or electronics?) but it sure worked.
That's so cool. And +1 to Beeswax candles. I have a dream we will orient ourselves with greater agency and autonomy and after traditional careers die if we get a UBI and still choose to work we would orient ourselves around the sun naturally and have time in the day for social lives.
I picked beeswax because the petroleum-based ones smell terrible, and I found some that weren't much more expensive than unscented soy. They have a nice smell!
But burning non-petroleum candles a couple hours each evening (and I found it took two tapers to have enough to comfortably read by) is pretty expensive. Plus burning anything isn't great for air quality, even if it smells OK. One person doing it in a full-sized house, alight, maybe. Three or more people in a house carrying around pairs of candles every night? You might start to notice the air quality and your shelves or walls getting a bit sooty.
If I wanted to do it longer term I'd probably build a few shaded (it actually hurts to look directly at even something as dim as a single candle flame, let alone a slightly-brighter bulb, when your eyes are adjusted to low light; I didn't come up with a solution for this with my candles, in the ~3 weeks I was using them) nightlight-level-output battery powered lamps. Most of the lamps or lanterns you can buy have built-in LEDs these days (so, limited ability to modify them) and their dimmest setting is way brighter than two actual candles, plus you'd want a candle-warmth color temp and lots of them are cool sunlight-temp. So I think building a few would be the best option.
Standard modern nighttime lighting started seeming insanely bright after a few days of doing the candle thing. It really takes very little light to navigate your house and do many tasks safely and comfortably, if you let your eyes adjust and don't have some kind of serious vision problems, and if you've got a few people awake in your house doing things after dark it's easy to have hundreds of times as much illumination active as anyone really needs. I also kinda liked carrying my light with me, rather than flipping switches from room to room.
I use the candles for a meditative gazing practice called trataka. Gazing at fire has never hurt me (edit: even at low light conditions), but usually feels calming, giving me more creativity as well. Also to optimize cost, I discovered beeswax tea light candles which are reasonably priced, between $0.30-$0.50/candle and I'd put them in these tiny single lanterns that you can carry around that make it more practical to use these for indoor light. I also found that having a incense burner device (theres ones where you use the beeswax candle under a metal mesh, as the source of heat (And now light too!) with my favorite resins like myrrh for scents also really helped set a great mood & regulate the nervous system for transition. I also would use these digital yellow candles that operate off of AA batteries and you can set on a schedule with a remote, they were so good and before I moved they would jsut automatically set the mood and light core areas with just enough light and brightness for night time. I suggest them! The brand I got was Aignis Flameless LED Candles (on Amazon). Get the orange and not white/blue.
>Standard modern nighttime lighting started seeming insanely bright after a few days of doing the candle thing. It really takes very little light to navigate your house and do many tasks safely and comfortably
Yes agreed. It's so nice once you get used to this, and I think this is how our ancestors lived for millions of years followed by candles, incandescent and then horrifyingly today's blue lights.
Did you notice blue in specific feel incredibly unnerving and painful to look at at night even in low light output after adjusting to night time settings?
302 comments
[ 3.3 ms ] story [ 69.6 ms ] threadhttps://github.com/JuliusBrussee/caveman
It's for getting it to output shorter answers, but also could help with your burnout.
It's ok if you don't get it, but other people do, so can't generalize with your lack of comprehension.
I got into programming because the problems of programming were interesting to me. But if the problems go from "figure out why this calculator is off by one in France" to "Get this LLM to stop spamming cutsey emojis", then maybe it's time for a career change.
My latest is, I'm really into fizzy/soda water and wanted my own continuous carbonator. My entire build from water source to tap with an ESP32 controlled pump, pressure, water level, cooling fans.
There were so many areas I made mistakes in my shopping cart and it found it - like Home Brewer likes 8mm lines but water filter systems like 9.5mm. Really optimized the versions from a simple on/off pump w/ float switch to effectively a full on PLC system. So many iterations gained by chatting with "someone more experienced". Once I get the parts I can build and have the software side running in less than an hour.
It doesn't make money, but man I really enjoy it.
We’ve had 3 production incidents this week that slipped past CI because there’s a whole team that is just shoving out PRs without understanding what’s going out.
It's not surprising that if you have a hundred separate, isolated contexts working on the same business, that don't cross-talk and have no ability to subconsciously receive and collate the thousands of signals we get from our work environment, that you end up shipping lots of incomplete or incompatible work.
The experience is much closer to working with an external API that you don't have control over, and where the internal implementation details of the API randomly change every day so you can't even work around bugs. And those have always been the most frustrating parts of programming.
Sorry, some of us have a joy for programming where the how is just as important, if not more so, than the what and the why. No matter how much people proclaim that the how doesn't matter to them, it isn't going to suddenly make it true for others.
This isn't a response I expect from people who are here for a productive discussion. I'm sorry that you are sick of hearing this, but I'm not responsible for making sure you only read what you find worthy of your own personal brand of respect. Instead of attacking someone for simply offering their point of view, in what appears to be a quasi-gatekeeping effort, maybe you should look inward and discover what is making you this upset toward a complete stranger.
__I cannot take away the joy you have for programming simply by stating what drives me.__
Look, I don't have a problem with your personal motivation. I just hate seeing it suggested that people should abandon their passion because someone else doesn't share it. There's absolutely nothing wrong with "I enjoy making something useful" just as there's nothing wrong with "I enjoy making something with my hands or figuring out how to make it". My problem is with "your enjoyment of that is invalid because I don't enjoy that, so learn to enjoy this".
0: Not really a statement of your drive, is it? More of a directive or suggestion.
then so is your opinion on the matter. this goes both ways. I can just as easily dismiss your commentary as "drive-by".
> Not really a statement of your drive, is it? More of a directive or suggestion.
Yeah, so was my initial comment. Merely a suggestion concerning view points, and how a shift in that can bring back some amount of joy.
You don't have the moral high ground here.
As a programmer, you also had to work at that higher abstraction level anyway.
It's a myth that you are "moving" up a level; you were always at that level, just not exclusively.
do you mean my enjoyment from building things? I'm genuinely confused by this response.
Those who like having a finished thing. Product people. These love LLMs.
Those who love building a thing, working through a problem, learning something new. Finishing a project is generally not required. For them LLMs are soul sucking hell.
I'm not surprised - your GGP comment indicated that you are more interested in the destination than the journey (you enjoy the output more than the process of crafting that output).
Nothing wrong with that - lots of programmers are interested in the final deliverable and don't really care about how the sausage is made, but you're reading a comment from someone who makes the sausage.
That's tantamount to "I don't care about the coding itself, or the underlying quality of my systems".
Your comment is incredibly aggressive, hostile, and rude, of out nowhere. You should review the guidelines [1]. It's deeply disingenuous to either communicate really poorly or to backtrack from your position unannounced and then get aggressive about it when people engage with you.
[1] https://news.ycombinator.com/newsguidelines.html
This is "incredibly aggressive, hostile, and rude, of out nowhere". Please leave me alone, I have nothing else to say to people like you.
For anyone else, imagine a winemaker that cares about their end product more than they care about growing grapes.. does that mean this winemaker doesn't care about the quality of their grapes? Probably not, but apparently to this individual the english language requires that we believe the winemaker to be disingenuous if they clarify their position on grape quality.
this AI bubble will pop. when it does you'll be hot stuff all over again.
You'll frustrate yourself by not using this tool without above. You'll definintely frustrate yourself expecting the tool to be "genuinely sorry"!
Anyone else working on something like this or know of any projects attempting it?
I've taken a bit longer than I wanted but it will be open sourced soon.
It's a durable orchestration engine that takes in specs/requirements and coordinates agents externally (meaning the engine drives the loop, not an agent) until the work is fully implemented/verified and reviewed.
It's meant to be used with any harness as basically the last step. You plan your work with whatever LLM you use and then hand off implementation to the engine (through an MCP server or other surfaces)
It can use your OpenAI/Anthropic subscriptions or any other provider and you can mix and match models across implementation and review in any way you want with fan out for parallel reviewers and more.
The goal is to produce high quality unsupervised code that matches your requirements and is reviewed throughout the implementation rather than at the end only, so that mistakes don't compound.
https://engine.build if you want to get notified when it releases.
A I am happy about all the little side-projects, and ideas it help my realize, and I enjoy exploring this new world, but I've noticed LLMs feed my unhealthy "don't want to take a break and waste time being idle" mindset, and I need to correct it.
I confess that the above variant on the quotation is how I originally read it. And that's just about how I feel now with trying to sort through vibe-coded slop projects that are put forth by (well-meaning, probably good intentioned, not evil) people who represent them as if they're the handcrafted result of one dedicated developer.
"I did a Chat output, please fix and review it " is the kind of thing that empowers the people who used to have a minimal productivity, and now lets them to wreck things on an industrial scale.
It's not. There is no one person that has universally good taste. Also, we're not in your head, no matter how much better of a coder or whatever. We're not in your head and it's all terribly painful to navigate.
AI is not a productivity multiplier. There are diminishing results.
The ones that notice the highest increases of productivity are usually the ones that were unproductive at best and dangerously incompetent at worst.
Sure it is. Just that some of the values being multiplied are negative.
Lots of companies (nearly all, I’d wager) of any size were leaving bare-minimum a 2x software development speed increase on the table before LLMs, having nothing whatsoever to do with how fast anyone was typing or thinking up code, and everything to do with how they organized and supported development work, and with your basic ordinary corporate dysfunction.
My company, I’d say it was more like 4x or 5x they could have achieved before LLMs, by fixing processes and reducing how often management steps on their own dicks.
All the people I’m seeing with crazy-high LLM productivity at my company? They’ve been given enormous autonomy to basically go do WTF ever they want, and people are jumping to get them anything they need (and most of what they’re doing is prototyping, for that matter). So right off the bat, if they’re competent, they should see a notable multiplier on productivity even if they weren’t using LLMs. Not that those aren’t helping, too, but if you don’t change processes they’re not all that effective, because the problem wasn’t speed of code-writing (and if you can change processes, you already could have sped up development a lot before LLMs…)
This 1000 times. The number of times I now have to use my brain to do something engineer-y is now something like 5 times per week, usually eyeballing some architectural decision from (as you mentioned above) someone else's LLM.
I really loved writing code, and I loved that I could do it for a living. Obviously, nothing is stopping me from continuing to write code and solve problems with my own brain, but that's absolutely not the efficient way to work anymore.
The most high-leverage activity I've done in the last 6 months is a build-out of internal AI orchestration platforms and data access layers so every employee in the company can built with AI against our own data (particularly non-engineers). It has unlocked so much for everyone. Yet, my only real claim is a) coming up with the idea and general architecture and b) ensuring smooth roll-outs and hosting "office hours" for months to help new employees onboard to these new AI tools I built.
High-level design and architecture decisions, quality assurance, and balancing decision-making through subjective areas like UI/UX. That's mostly all I do. Now that I'm leading engineering, I just think even higher-level while the engineers use orchestrated AI do built vast swaths of code. Then I frantically bounce around approving sensitive PRs and architecture decisions -- most of which were written by Claude, described by Claude, and usually don't need a lot of correction.
Spoken like someone who is not at an org/team that has undergone layoffs and reduced hiring in the last 3 years.
You might be in the minority there - especially when it comes to those who are facing burnout.
Cost of generation has been reduced, and is highly subsidized currently.
Cost of verification has effectively not changed. I’d say as a rule of thumb: verification is the tough part.
Our brains don’t fare well under constant review pressure. https://en.wikipedia.org/wiki/Ironies_of_Automation
Then why are so many others in the thread reporting being swamped with requests to review coworkers' slop? If it's genuinely "cognition" at trivial cost, surely this review would be completely unnecessary?
This isn't the problem; the problem is that people incorrectly believe it to be true.
I think this is in part because I am one of the software engineers that always liked building products more than writing complex software. So, I am driven by the feeling of creating something. And I want to get the feature perfect and complete. But getting from 95%->100% done can take a long time with UI work for me.
So I work much longer hours now, unfortunately.
Main blocker is I am using apps like Conductor and have lots of plates spinning at once. But that's on, me and I should try and start completing the last part myself.
But it's probably a common feeling. I wonder if we'll see an increased number of people burn out in the serious, medical sense.
I'm getting so many requests to review LLM-generated documents - planning docs, docs intended for end-users, project docs, business plan docs. A team member sent me a zip file with about 30 LLM generated documents in it the other day and asked if I could review them right away. And a lot of it was just repetition and/or stuff that was just out of left field, made-up, hallucinated stuff. They're able to generate this stuff way faster than we can review. It's just really tiring.
> do not hallucinate
They do, just less. To the degree of being usable, as long as there are guardrails and they're used responsibly. This also implies you need SOTA models on max reasoning.
> make things up
Same as above. Ideally you'd give them some way to verify their claims, like web search or browsing and referencing docs, Jira tickets etc., basically improve the signal to noise ratio.
> contradict themselves
They do so way less than before, as long as the above is true.
> can review their own output into perfection
They are pretty good at reviewing things, especially if you make them do adversarial review! It will never be perfect, but can be close in quality to human output (e.g. the code they produce, when used properly and with intent, is better than the code I've seen many developers write and ship before LLMs were a thing).
This also more or less scales with how much compute you give them - three parallel review agents will turn one output artifact into something good with higher confidence than two, and definitely better than with no review.
> regardless of task, goal or context????
Garbage in, garbage out. I won't be an asshole and say that you're holding it wrong, nor will I say that anyone should listen to the claims marketing AI (absolutely delusional takes, meant to attract investors), but we're slowly getting to a better position in regards to LLMs, year by year.
It's just a shame that the peak of inflated expectations hit while the technology still hasn't fully plateaued and reached whatever its ceiling is.
I think we will very soon move to a prove to me you've read it protocol and/or introduce speed bumps to slow things down.
Why not just review a single document quickly, find an error which invalidates the document, and send it back saying "Policy paper 1 mentions X as being on the business plan for Y, it's not on the plan, please can you fix."
Unless you can write a good-sounding reason why it's on them to review a LLM output before sending it to you, they will outsources this reviewing to you, and it's a lot of reviewing.
If it's genuinely hard to find that single bug .. perhaps the document has reached the quality required for corporate communication?
In my experience, it does take a lot time and effort to find contradictions between 10 documents. Even with good documentation, it's hard to build a mental map for that amount of information.
Hopefully you mean Rate of verification/Rate of generation.
Verification/generation
He who brings the slop cannon shall be drowned by slop rain.
If this approach gets widely adopted, then I think you should probably start building an ARK.
Make it big enough to hold two of every animal species. /s
Getting an LLM to vomit out a bunch of documents and sending them straight to another colleague is absolutely unacceptable behaviour.
Which is going to win?
We also need to be motivated to stay in our jobs.
Most developers like their projects and value their work. But the chances are that it's for nothing.
Many developers know they work on bad products (gambling industry, military, surveillance, whatever) and so it's here that they focus on their technologies, tools and frameworks rather than the work they produce.
"Agentic engineering" for example.
Id be curious to see what and how Googlers are doing with their 20% time.
If you're an employee in that situation, push back if you can. If you can't, put your resume on the street. (But that may not work, these days. If it doesn't, all I can say is ride it out as best you can, and try to maintain both your job and your sanity. How? I don't know.)
That's the other nightmare of AI slop. So easy to generate endless content. Who will review?
Just today the boss request I review slides for a presentation. But it's all AI slop, generated from querying tickets and docs and who knows what. It's mostly sort of correct but also plenty misleading and incorrect. So now I have to fact check all this slop which will take hours (even with my AI assistance) and rewrite most of it.
If AI didn't exist, he would've had to do the research to generate the content and it would be 99% correct and I could just give a few notes of feedback in 5 minutes. But with the asymmetric AI workload, he can generate it in 5 minutes and I get to spend 3 hours correcting.
Maybe, depending on the boss. Some would have spent five minutes describing what they wanted, and someone else would have spent three hours creating the deck.
Problem with AI is that generation is so many orders of magnitude faster than reviewing so it's basically infinite monkeys on infinite typewriters.
You just discovered the unlock to massive AI-driven productivity increases: outsource the hard stuff to others, or just don't do it at all. Keep the easy tasks that generate a big volume of output for yourself.
Or use LLM's to generate 12+ pages of detailed reviews of those documents and return to sender.
I see a different type of pressure: I'm at a company that still is requiring everyone use LLMs with token leaderboards, time-spent measurements, and impacts to performance reviews, and all that. So I find myself having to carve out some percent of my time to stop doing productive work, and "go do AI to show token use." So my workload hasn't changed (or it's gone up), but I have N% less time to work on it because I have to spend time appeasing the AI gods...
Peer Gynt Suite's "In the Hall of the Mountain King" made a prominent appearance, but so did Aqua's "Barbie Girl"
Probably like eating. Having to eat less to loose weight isn't great. Eating anything you want without worries is great. Having to eat more than you want to gain weight, not great.
Just be careful about any legal implication of doing side-projects during work with work-resources.
Same, but I really have to fight the urge to just add fun new features to things I work on any time inspiration strikes. I am an appalling 'feature factory' if I don't actively keep myself in check. The cost of just building everything is so low, but the value of those things is also incredibly low, so I'm often just bloating what I build.
There's been a lot of articles and posts about the increasing importance of 'taste' in software built with AI, and I'm finding I know need to look for strategies to find some.
I had to think of Charlie Chaplin's Modern Times. The author's observation is basically the main idea of the sketches, i.e. humans having to follow the pace of the machines instead of the other way around.
Reverse centaurs are nothing new.
“I wanted a machine to do the dishes so I could concentrate on my creative work, and all I got was a machine to do my work so I’m left to wash the dishes.”
Embrace it if you’re like me and feel uncomfortable having an idle mind, embrace it! You’ll get more done and being 120% go go go is impossible over the long run so eventually your body will just say I need a break then once you recover full steam head again on the treadmill
Yes, this is to me the primary driver of the extreme AI burnout. In ~30 years in Silicon Valley and many, many startups, the pressure has never been as intense.
Before AI I'd mostly work on one thing at a time (at least within a given hour) and in the evening I wouldn't start a new 6 hour task because it's too long, so tomorrow is another day.
Now, that 6 hour task is more like 30 minutes, so there is intense pressure to just knock it off tonight. And then the next one. And one more. And while the bot is thinking, to have 4 other work streams in parallel so there is never, ever, a break in the day. The human mind is not built for 100% utilization 15 hours a day.
I find LLMs to help me manage the unrealistic workload I have, because at least now it's feasible instead of just getting more work piled on top of me with a never ending backlog (that people actually expect me to thin, not let grow). Add on top of that colleagues that would have death by commitee'd many ideas and now just have to argue against actual MVPs that work instead of ideas (or can be proven to not work and discarded without wasting time on them in some cases), and I don't even hate my job as much!
It's just that to ensure that the technology is not a net negative, I need millions upon millions of tokens every single day (tool runs, adversarial reviews, testing), but once you get that inflection point, alongside needing a good enough model, the floor for which currently I'd say GLM 5.2 on Max reasoning reaches, or use something like SOTA Anthropic/OpenAI models, it becomes a pretty good way of working.
AI coding is addictive. Engineers are paying the price https://leaddev.com/ai/ai-coding-is-addictive-engineers-are-...
It's impossible to undo some of these linguistic wobbles. Even if you could filter out 100% of LLM input, the humans themselves are learning to say "land" at a higher frequency now.
Its like when someone points something out a in picture you never saw and now you cannot "unsee" it ever again.
I've often had to paste its output back in to ask it what it actually means. Weird.
I think the main thing is just fatigue. There's so little variety. Each model has its preferred idiolect which everyone becomes tired of due to ubiquity. That's the worst part. It's like always eating fast food.
I used to have a lot of fatigue due to it until I stopped caring.
＊onanizing…
The bots (all of them) seem to show patterns of overuse of specific phrases, words, and punctuation.
Some of those are the ones you mentioned. Another that I've been seeing lately is overuse of the term "gate", wherein: As a human, I know what a gate is. A gate is a thing that can be open, or that can be closed. It might be locked or unlocked. The path beyond the gate may be passable or impassable or nonexistent. The gate is just a gate, and the presence of the gate doesn't imply whether it is open or closed.
But in bot-speak, a gate only refers to a hard block -- an impassable construct. Like a fence or a wall, or even a lava-filled moat.
But while a lava-filled moat is intended to be impassable, the bot uses "gate" -- a thing that is designed to be passed -- to describe that same kind of obstacle.
That's misuse of the term, I think, based on decades of dealing with gates in reality: Usually when I encounter a gate that is closed, I just open it and walk through.
I do have instructions that tell the bot to avoid that usage of the word and it ignores them sometimes anyway.
But "gate" is just today's problem-word that comes to mind as I write this. Yesterday, it was something different. Tomorrow, it will be something else entirely.
The overall pattern here is that of gratingly-repetitive bullshit-grade jargon that doesn't fit to begin with.
"And that's the real, no-nonsense truth!"
Another example of typical botspeak is "smoke test". Why not just say "test"? It feels like a way of downplaying the ability to detect problems.
One thing I did recently with the bot definitely involved actual smoke tests, though: I was working with real hardware that can blow up in real ways, with the bot doing all of the circuit design work and coding based on my goals while I just distantly commanded the show from On-High and plugged shit into a breadboard.
(The project works well and I consider it to be Good Enough; I might go back and polish it more later. There was no smoke, but there could have been.)
I've been on the Internet for ~35 years. What did I miss?
Anything written for humans should be written by humans.
Getting sent IM responses that are copy pasted LLM nonsense. Getting a massive PR to review that was generated overnight and the author didn't read it first.
My mind still can't function well without having knowledge about everything.
The productivity drive and the sheer feature set you can generate in record time makes it easy to forget proper sdlc hygiene.
… but I am almost certain I’d never have developed those in the first place if I hadn’t spent 25ish years programming on a bunch of different platforms and setting up servers and networks and all that, without LLMs.
I dunno how you make another “me”, now, while before lots and lots of programmers naturally ended up as someone with skills and knowledge like mine, and those skills seem super useful when writing code with LLMs.
Of course if you're supposed to achieve so much output that it's not possible to do anything but vibe it, fair enough.
Prior to the last 12mos AI companies were hell bent on squeezing out the best results from mediocre models.
But... now that the top models have progressed, those same AI companies have switched their efforts into reducing the computation (cost of a producing a result) as much as possible without being too obvious.
What was an exponential slope in the quality of results over the last 36 months has now nearly flat lined.
https://www.youtube.com/watch?v=qbIk7-JPB2c
Before, they could stay in thinking mode for more than 7 minutes. For example, "find a source for this claim" would search, analyze, and self-adjust the query. Nowadays, even if I push for it, I cannot make these tools work for more than 30 seconds before they give generic answers, even in "Pro" mode.
How empirical are your comparisons of new and old outputs?
Hell, the Opus 4.5 moment was only last November, and that was when agentic coding and most coding CLI tools became truly first class options. That's a wild paradigm shift. Hell, GPT-5 wasn't even out (that's August of last year). Most people were using 4o. Their current offerings are wildly better for coding than 4o was.
But that's also let me use "agent" stuff longer, I guess? The better you were at knowing what you wanted and how to ask for it, the less of an inflection point that you got from Opus 4.5 or GPT 5.
Some of the highest-time-saved-for-max-ROI agentic problems I've solved to date were in September and October of last year with Claude or Cursor.
What helped was a sleep and work system, oriented around being offline that was inspired by nature and from my earlier days in working in tech while car camping across the national parks.
Basically: the sun wins in terms of how all energy on the earth is structured, and expressed. All manners of cycles of organisms and living systems are in relation to its rise and fall, and even its particular color spectrum phases (whether thats night oriented or day). I call this our real circadian rhythm; it's used to being signaled by the light of the sun and maybe fire for millions of years and it isn't until recent centuries when we started tricking our biology with LEDs and lights. So the solution is simple. Orient yourself around the light of the sun and make sure it's the first and last major light source you see; blue limiting is the most important part BEFORE sunrise and AFTER CUT OFF ALL BLUE LIGHT. On my Mac I use a red light filter (using it now, it's 11:07pm ET and the sun went down about 2.5 hours ago). It's really hard to stay alert and chatting with an LLM when the only light sources are red and you keep them dim at that. Our ancestors would rest when the sun's at its peak (~1:05 pm today) and that's a good time to divide my own day productively as well. With intentional breaks diving the middle of the day with sunlight anchoring it, my nervous system is more relaxed, and by the evening time, it's also ready to transition out of anything blue-light assisted and most intellectual work and problem solving falls into this bucket. It's really hard to explain but it really works so simply. To enjoy the process a little more I made this fun sun clock, check it out at https://sunsignal.app
Cured my lifelong “night owl” “trait” in a couple days. Shockingly effective.
Turned out to be hard to keep up and still, like, exist with other people, and you’d probably need to relax it a little in Winter unless your job lets you work reduced hours to kinda “hibernate” (otherwise when would you do anything that’s not work but requires light or electronics?) but it sure worked.
But burning non-petroleum candles a couple hours each evening (and I found it took two tapers to have enough to comfortably read by) is pretty expensive. Plus burning anything isn't great for air quality, even if it smells OK. One person doing it in a full-sized house, alight, maybe. Three or more people in a house carrying around pairs of candles every night? You might start to notice the air quality and your shelves or walls getting a bit sooty.
If I wanted to do it longer term I'd probably build a few shaded (it actually hurts to look directly at even something as dim as a single candle flame, let alone a slightly-brighter bulb, when your eyes are adjusted to low light; I didn't come up with a solution for this with my candles, in the ~3 weeks I was using them) nightlight-level-output battery powered lamps. Most of the lamps or lanterns you can buy have built-in LEDs these days (so, limited ability to modify them) and their dimmest setting is way brighter than two actual candles, plus you'd want a candle-warmth color temp and lots of them are cool sunlight-temp. So I think building a few would be the best option.
Standard modern nighttime lighting started seeming insanely bright after a few days of doing the candle thing. It really takes very little light to navigate your house and do many tasks safely and comfortably, if you let your eyes adjust and don't have some kind of serious vision problems, and if you've got a few people awake in your house doing things after dark it's easy to have hundreds of times as much illumination active as anyone really needs. I also kinda liked carrying my light with me, rather than flipping switches from room to room.
>Standard modern nighttime lighting started seeming insanely bright after a few days of doing the candle thing. It really takes very little light to navigate your house and do many tasks safely and comfortably
Yes agreed. It's so nice once you get used to this, and I think this is how our ancestors lived for millions of years followed by candles, incandescent and then horrifyingly today's blue lights.
Did you notice blue in specific feel incredibly unnerving and painful to look at at night even in low light output after adjusting to night time settings?