I know it's popular comparing coding agents to slot machines right now, but the comparison doesn't entirely hold for me.
It's more like being hooked on a slot machine which pays out 95% of the time because you know how to trick it.
(I saw "no actual evidence pointing to these improvements" with a footnote and didn't even need to click that footnote to know it was the METR thing. I wish AI holdouts would find a few more studies.)
Steve Yegge of all people published something the other day that has similar conclusions to this piece - that the productivity boost for coding agents can lead to burnout, especially if companies use it to drive their employees to work in unsustainable ways: https://steve-yegge.medium.com/the-ai-vampire-eda6e4f07163
Being on a $200 plan is a weird motivator. Seeing the unused weekly limit for codex and the clock ticking down, and knowing I can spam GPT 5.2 Pro "for free" because I already paid for it.
> It's more like being hooked on a slot machine which pays out 95% of the time because you know how to trick it.
I think you are mistaken on what the "payout" is. There's only one reason someone is working all hours and during a party and whatnot: it's to become rich and powerful. The payout is not "more code", it's a big house, fast cars, beautiful women etc. Nobody can trick it into paying out even 1% of the time, let alone 95%.
Probably the best we can hope for at the moment is a reduction in the back-and-forth, increase in ability to one-shot stuff with a really good spec. The regular human work then becomes building that spec, in regular human (albeit AI-assisted) ways.
If you are trying to build something well represented in the training data, you could get a usable prototype.
If you are unfamiliar with the various ways that naive code would fail in production, you could be fooled into thinking generated code is all you need.
If you try to hold the hand of the coding agents to bring code to a point where it is production ready, be prepared for a frustrating cycle of models responding with ‘Fixed it!’ while only having introduced further issues.
How are we still citing the (excellent) METR study in support of conclusions about productivity that its authors rightly insist[0] it does not support?
My paraphrase of their caveats:
- experts on their own open source proj are not representative of most software dev
- measuring time undervalues trading time for effort
- tools are noticeably better than they were a year ago when the study was conducted
- it really does take months of use to get the hang of it (or did then, less so now)
Before you respond to these points, please look at the full study’s treatment of the caveats! It’s fantastic, and it’s clear almost no one citing the study actually read it.
I think that in a world where code has zero marginal cost (or close to zero, for the right companies), we need to be incredibly cognizant of the fact that more code is not more profit, nor is it better code. Simpler is still better, and products with taste omit features that detract from vision. You can scaffold thousands of lines of code very easily, but this makes your codebase hard to reason about, maintain, and work in. It is like unleashing a horde of mid-level engineers with spec documents and coming back in a week with everything refactored wrong. Sure you have some new buttons but does anyone (or can any AI agent, for that matter) understand how it works?
And to another point: work life balance is a huge challenge. Burnout happens in all departments, not just engineering. Managers can get burnout just as easily. If you manage AI agents, you'll just get burnout from that too.
After actually using LLM coding tools for a while, some of these anti-LLM thinkpieces feel very contrived. I don’t see the comparison to gambling addiction at all. I understand how someone might believe that if they only view LLMs through second hand Twitter hot takes and think that it’s a process of typing a prompt and hoping for the best. Some people do that, but the really effective coders work with the LLM and drive the coding, writing some or much of the code themselves. The social media version of vibe coding where you just prompt continuously and hope for the best is not going to work in any serious endeavor where details matter. We see claims of it in some high profile examples like OpenClaw, but even OpenClaw has maintainers and contributors who look at the code and make decisions. It’s also riddled with security problems as a result of the YOLO coding style.
The gambling analogy completely falls apart on inspection. Slot machines have variable reward schedules by design — every element is optimized to maximize time on device. Social media optimizes for engagement, and compulsive behavior is the predictable output. The optimization target produces the addiction.
What's Anthropic's optimization target??? Getting you the right answer as fast as possible! The variability in agent output is working against that goal, not serving it. If they could make it right 100% of the time, they would — and the "slot machine" nonsense disappears entirely. On capped plans, both you and Anthropic are incentivized to minimize interactions, not maximize them. That's the opposite of a casino. It's ... alignment (of a sort)
An unreliable tool that the manufacturer is actively trying to make more reliable is not a slot machine. It's a tool that isn't finished yet.
I've been building a space simulator for longer than some of the people diagnosing me have been programming. I built things obsessively before LLMs. I'll build things obsessively after.
The pathologizing of "person who likes making things chooses making things over Netflix" requires you to treat passive consumption as the healthy baseline, which is obviously a claim nobody in this conversation is bothering to defend.
The LLM is not the slot machine. The LLM is the lever of the slot machine, and the slot machine itself is capitalism. Pull the lever, see if it generates a marketable product or moment of virality, get rich if you hit the jackpot. If not, pull again.
Doesn't the alignment sort of depend on who is paying for all the tokens?
If Dave the developer is paying, Dave is incentivized to optimize token use along with Anthropic (for the different reasons mentioned).
If the Dave's employer, Earl, is paying and is mostly interested in getting Dave to work more, then what incentive does Dave have to minimize tokens? He's mostly incentivized by Earl to produce more code, and now also by Anthropic's accidentally variable-reward coding system, to code more... ?
> What's Anthropic's optimization target??? Getting you the right answer as fast as possible!
That is a generous interpretation. Mighr be correct. But they dont make as much money if you quickly get the right answer. They make more money if you spend as many tokens as possible being on that "maybe next time" hook.
Im not saying theyre actually optimizng for that. But charlie munger said "show me the incentives, and ill show you the outcome"
> What's Anthropic's optimization target??? Getting you the right answer as fast as possible!
Wait, what? Anthropic makes money by getting you to buy and expend tokens. The last thing they want is for you to get the right answer as fast as possible. They want you to sometimes get the right answer unpredictably, but with enough likelihood that this time will work that you keep hitting Enter.
Given that pre-paid plans are the most popular way to subscribe to Claude, it quite plainly is a "the less tokens you use, the more money Anthropic makes" kind of situation.
In an environment where providers are almost entirely interchangeable and tiniest of perceived edges (because there's still no benchmark unambiguously judging which model is "better") make or break user retention, I just don't see how it's not ludicrous on its face that any LLM provider would be incentivized to give unreliable answers at some high-enough probability.
> What's Anthropic's optimization target??? Getting you the right answer as fast as possible!
What makes you believe this? The current trend in all major providers seem to be: get you to spin up as many agents as possible so that you can get billed more and their number of requests goes up.
> Slot machines have variable reward schedules by design
LLMs by all major providers are optimized used RLHF where they are optimized in ways we don't entirely understand to keep you engaged.
These are incredibly naive assumptions. Anthropic/OpenAI/etc don't care if you get your "answer solved quickly", they care that you keep paying and that all their numbers go up. They aren't doing this as a favor to you and there's no reason to believe that these systems are optimized in your interest.
> I built things obsessively before LLMs. I'll build things obsessively after.
The core argument of the "gambling hypothesis" is that many of these people aren't really building things. To be clear, I certainly don't know if this is true of you in particular, it probably isn't. But just because this doesn't apply to you specifically doesn't mean it's not a solid argument.
I'm also seeing a lot of new rambling in Sonnet 4.6 when compared to 4.5, more markdown slop and pointing out details and things in the context which isn't too useful etc...
which then causes increased token usage because you need to prompt multiple times.
> "person who likes making things chooses making things over Netflix"
This is subtly different. It's not clear that the people depicted like making things, in the sense of enjoying the process. The narrative is about LLMs fitting into the already-existing startup culture. There's already a blurry boundary between "risky investment" and "gambling", given that most businesses (of all types, not just startups) have a high failure rate. The socially destructive characteristic identified here is: given more opportunity to pull the handle on the gambling machine, people are choosing to do that at the expense of other parts of their life.
But yes, this relies on a subjective distinction between "building, but with unpredictable results" and "gambling, with its associated self-delusions".
>The pathologizing of "person who likes making things chooses making things over Netflix" requires you to treat passive consumption as the healthy baseline, which is obviously a claim nobody in this conversation is bothering to defend
I think their greater argument was to highlight how agentic coding is eroding work life balance, and that companies are beginning to make that the norm.
You may have a point but either way: immediately taking it personally like this and creating a whole semi-rant that includes something to the effect "I've been doing this since before you were born" really makes you sound like a person with a gambling problem.
Trust me, we all feel like the house is our friend until its isn't!
Thank you! I don't get how so many people want to see dark patterns everywhere. All arguments miss the big counterargument: in a world where you have competitors, even free ones, you can't fuck around. You need to get it working. it's not a slot machine for me. How on earth are people using it? And if it would be I'd take my money elsewhere (kimi for example, openrouter or whatever). It needs to do my work as correct as possible. That's the business they are in. Tech folks talking about economics is so cringe. It's always just "corporations bad". As if they exist in a vacuum.
Disagree. Unreliability is intractable because of the human, not the tool.
Even a perfect LLM will not be able to produce perfect outputs because humans will never put in all the context necessary to zero-shot any non-trivial query. LLMs can't read your mind and will always make distasteful assumptions unless driven by users without any unique preferences or a lot of time on their hands to ruminate on exactly how they want something done.
I think it will always be mostly boring back-and-forth until the jackpot comes. Maybe future generations will align their preferences with the default LLM output instead of human preferences in that domain, though.
One of my recent thoughts is that Claude Code has become the most successful agent partially because it is more of a black box than previous implementations of the agent pattern: the actual code changes aren't shoved in your face like Cursor (used to be), they are hidden away. You focus more on the result rather than the code building up that result, and so you get into the "just one more feature" mindset a lot more, because you're never concerned that the code you're building is sloppy.
I wish the author had stuck to the salient point about work/life balance instead of drifting into the gambling tangent, because the core message is actually more unsettling. With the tech job market being rough and AI tools making it so frictionless to produce real output, the line between work time and personal time is basically disappearing.
To the bluesky poster's point: Pulling out a laptop at a party feels awkward for most; pulling out your phone to respond to claude barely registers. That’s what makes it dangerous: It's so easy to feel some sense of progress now. Even when you’re tired and burned out, you can still make progress by just sending off a quick message. The quality will, of course, slip over time; but far less than it did previously.
Add in a weak labor market and people feel pressure to stay working all the time. Partly because everyone else is (and nobody wants to be at the bottom of the stack ranking), and partly because it’s easier than ever to avoid hitting a wall by just "one more message". Steve Yegge's point about AI vampires rings true to me: A lot of coworkers I’ve talked to feel burned out after just a few months of going hard with AI tools. Those same people are the ones working nights and weekends because "I can just have a back-and-forth with Claude while I'm watching a show now".
The likely result is the usual pattern for increases in labor productivity. People who can’t keep up get pushed out, people who can keep up stay stuck grinding, and companies get to claim the increase in productivity while reducing expenses. Steve's suggestion for shorter workdays sound nice in theory, but I would bet significant amounts of money the 40-hour work week remains the standard for a long time to come.
Funemployed right now joyously spending way way more time than 996, pulling the slot machine arm to get tokens, having a ball.
But that's for personal pleasure. This post is receeding from the concerns about "token anxiety," about the addiction to tokens. This post is about work culture & late capitalism anxiety, about possible pressures & systems society might impose.
I reflect a lot on AI doesn't reduce the work, it intensifies it.
https://hbr.org/2026/02/ai-doesnt-reduce-work-it-intensifies...
The spirit of this really nails something core to me. We coders especially get help doing so much of menial now. Which means we spend a lot more time making intense analysis and critiques, are much more doing the hard thought work of 'is what we have here as good as it can be'. Finding new references or patterns to feed back into the AI to steer already working implementations towards better outcomes.
And my heart tells me that corporations & work life as we know it are almost universally just really awful about supporting reflective contemplative work like this. Work wants output. It doesn't want you sit in a hammock and think about it. But increasingly I tell you the key to good successful software is Hammock Driven Development. It's time to use our brains more, in quiet reflection. https://github.com/matthiasn/talk-transcripts/blob/master/Hi...
996 sounds like garbage on its own, as a system of toil. But I also very much respect an idea of continuous work, one that also intersperses rest throughout the day. Doing some chores or going to the supermarket or playing with the kid can be an incredibly good way to let your preconscious sift through the big gnarly problems about. The response to the intensity of what we have, to me, speaks of a need to spread out the work, to de-concentrate it, to build in more than hammock time. I was on the fence about whether the traditional workday deserved to survive before AI hit, and my feels about it being a gross mismatch have massively intensified since.
As I started my post with, I personally have a much more positive experience, with what yes feels like a token addiction. But it doesn't feel like an anxiety. It feels like the greatest most exciting adventure, far beyond what I had hoped for in life ever. This is wildly fun, going far far further out than I had ever hoped to get to see. I'm not "anxiously" pulling the lever arm on the token machine, I'm just thrilled to get to do it. To have time to reflect and decide, I have 3-8 things going at once (and probably double they back burnered but open, on Niri rows!) to let myself make slower decisions, to analyze, while keeping the things that can safely move forwards moving forwards.
That also seems like something worker exploitative late capitalism is mostly hot garbage at too! Companies really try to reduce in flight activities. Sprint planning is about crafting deliberate work. But our freedom and agency here far outstrips these dusty old practices. It is anxiety inducing to be so powerful so capable & to have a bureaucracy that constraints and confines, that wants only narrow windows of our use.
> 996 sounds like garbage on its own, as a system of toil. But I also very much respect an idea of continuous work, one that also intersperses rest throughout the day. Doing some chores or going to the supermarket or playing with the kid can be an incredibly good way to let your preconscious sift through the big gnarly problems about.
I _kind_ of get this if we're talking about working on big, important, world-changing problems. If it's another SaaS app or something like that, I find it pretty depressing.
Simple fix for this. When the work day is done, close the laptop and walk away. Don't link notifications to personal devices. Whatever slop it produced will be waiting for you at 8am the next morning.
This is simply yet another outdated analogy from haters that are failing to keep pace with the current frontier because they are too busy getting high on the anti-hype.
We’re well past the need to retry the same prompt multiple times in order to get working code. The models with their harnesses are properly agentic now, they can find the right context, make a plan, write the code, run the tests and fix the bugs with little to no intervention from a human.
The hardest part now is keeping up with them when it comes to approving the deliverables and updating the architecture and spec as new things are discovered by using the software. Not new bugs but corrections to your own assumptions you had before the feature was built.
Rather than let results be random, iteratively and continuously add more and more guardrails and grounding.
Tests, linting, guidance in response to key events (Claude Code hooks are great for this), automatically passing the agent’s code plan to another model invocation then passing back whatever feedback that model has on the plan so you don’t have to point out the same flaws in plans over and over.. custom scripts that iterate your codebase for antipatterns (they can walk the AST or be regex based - ask your agent to write them!)
Codify everything you’re looping back to your agent about and make it a guardrail. Give your agent the tools it needs to give itself grounding.
An agent without guardrails or grounding is like a person unconnected to their senses: disconnected from the world, all you do is dream - in a dream anything can happen, there’s nothing to ensure realism. When you look at it that way it’s a miracle coding agents produce anything useful at all :)
It's very tempting to agree to the 'gambling' part, given that both a jackpot and progress towards the goal in your project will give you a hit of dopamine.
The difference is that in gambling 'the house always wins', but in our case we do make progress towards our goal of conquering the world with our newly minted apps.
The situation where this comparison holds is when vibe coding leads nowhere and you don't accomplish anything but just burn through tokens.
60 comments
[ 2.7 ms ] story [ 83.1 ms ] threadIt's more like being hooked on a slot machine which pays out 95% of the time because you know how to trick it.
(I saw "no actual evidence pointing to these improvements" with a footnote and didn't even need to click that footnote to know it was the METR thing. I wish AI holdouts would find a few more studies.)
Steve Yegge of all people published something the other day that has similar conclusions to this piece - that the productivity boost for coding agents can lead to burnout, especially if companies use it to drive their employees to work in unsustainable ways: https://steve-yegge.medium.com/the-ai-vampire-eda6e4f07163
I think you are mistaken on what the "payout" is. There's only one reason someone is working all hours and during a party and whatnot: it's to become rich and powerful. The payout is not "more code", it's a big house, fast cars, beautiful women etc. Nobody can trick it into paying out even 1% of the time, let alone 95%.
If you are unfamiliar with the various ways that naive code would fail in production, you could be fooled into thinking generated code is all you need.
If you try to hold the hand of the coding agents to bring code to a point where it is production ready, be prepared for a frustrating cycle of models responding with ‘Fixed it!’ while only having introduced further issues.
My paraphrase of their caveats:
- experts on their own open source proj are not representative of most software dev
- measuring time undervalues trading time for effort
- tools are noticeably better than they were a year ago when the study was conducted
- it really does take months of use to get the hang of it (or did then, less so now)
Before you respond to these points, please look at the full study’s treatment of the caveats! It’s fantastic, and it’s clear almost no one citing the study actually read it.
[0]: https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...
And to another point: work life balance is a huge challenge. Burnout happens in all departments, not just engineering. Managers can get burnout just as easily. If you manage AI agents, you'll just get burnout from that too.
What's Anthropic's optimization target??? Getting you the right answer as fast as possible! The variability in agent output is working against that goal, not serving it. If they could make it right 100% of the time, they would — and the "slot machine" nonsense disappears entirely. On capped plans, both you and Anthropic are incentivized to minimize interactions, not maximize them. That's the opposite of a casino. It's ... alignment (of a sort)
An unreliable tool that the manufacturer is actively trying to make more reliable is not a slot machine. It's a tool that isn't finished yet.
I've been building a space simulator for longer than some of the people diagnosing me have been programming. I built things obsessively before LLMs. I'll build things obsessively after.
The pathologizing of "person who likes making things chooses making things over Netflix" requires you to treat passive consumption as the healthy baseline, which is obviously a claim nobody in this conversation is bothering to defend.
If Dave the developer is paying, Dave is incentivized to optimize token use along with Anthropic (for the different reasons mentioned).
If the Dave's employer, Earl, is paying and is mostly interested in getting Dave to work more, then what incentive does Dave have to minimize tokens? He's mostly incentivized by Earl to produce more code, and now also by Anthropic's accidentally variable-reward coding system, to code more... ?
That is a generous interpretation. Mighr be correct. But they dont make as much money if you quickly get the right answer. They make more money if you spend as many tokens as possible being on that "maybe next time" hook.
Im not saying theyre actually optimizng for that. But charlie munger said "show me the incentives, and ill show you the outcome"
Wait, what? Anthropic makes money by getting you to buy and expend tokens. The last thing they want is for you to get the right answer as fast as possible. They want you to sometimes get the right answer unpredictably, but with enough likelihood that this time will work that you keep hitting Enter.
In an environment where providers are almost entirely interchangeable and tiniest of perceived edges (because there's still no benchmark unambiguously judging which model is "better") make or break user retention, I just don't see how it's not ludicrous on its face that any LLM provider would be incentivized to give unreliable answers at some high-enough probability.
What makes you believe this? The current trend in all major providers seem to be: get you to spin up as many agents as possible so that you can get billed more and their number of requests goes up.
> Slot machines have variable reward schedules by design
LLMs by all major providers are optimized used RLHF where they are optimized in ways we don't entirely understand to keep you engaged.
These are incredibly naive assumptions. Anthropic/OpenAI/etc don't care if you get your "answer solved quickly", they care that you keep paying and that all their numbers go up. They aren't doing this as a favor to you and there's no reason to believe that these systems are optimized in your interest.
> I built things obsessively before LLMs. I'll build things obsessively after.
The core argument of the "gambling hypothesis" is that many of these people aren't really building things. To be clear, I certainly don't know if this is true of you in particular, it probably isn't. But just because this doesn't apply to you specifically doesn't mean it's not a solid argument.
which then causes increased token usage because you need to prompt multiple times.
Idk, maybe it's just me though.
https://www-cdn.anthropic.com/58284b19e702b49db9302d5b6f135a...
(cmd-f "slot machine")
This is subtly different. It's not clear that the people depicted like making things, in the sense of enjoying the process. The narrative is about LLMs fitting into the already-existing startup culture. There's already a blurry boundary between "risky investment" and "gambling", given that most businesses (of all types, not just startups) have a high failure rate. The socially destructive characteristic identified here is: given more opportunity to pull the handle on the gambling machine, people are choosing to do that at the expense of other parts of their life.
But yes, this relies on a subjective distinction between "building, but with unpredictable results" and "gambling, with its associated self-delusions".
yeah I think the bluesky embed is much more along the lines of what I'm experiencing than the OP itself.
I think their greater argument was to highlight how agentic coding is eroding work life balance, and that companies are beginning to make that the norm.
Trust me, we all feel like the house is our friend until its isn't!
Even a perfect LLM will not be able to produce perfect outputs because humans will never put in all the context necessary to zero-shot any non-trivial query. LLMs can't read your mind and will always make distasteful assumptions unless driven by users without any unique preferences or a lot of time on their hands to ruminate on exactly how they want something done.
I think it will always be mostly boring back-and-forth until the jackpot comes. Maybe future generations will align their preferences with the default LLM output instead of human preferences in that domain, though.
It is a business that sells monthly subscriptions
To the bluesky poster's point: Pulling out a laptop at a party feels awkward for most; pulling out your phone to respond to claude barely registers. That’s what makes it dangerous: It's so easy to feel some sense of progress now. Even when you’re tired and burned out, you can still make progress by just sending off a quick message. The quality will, of course, slip over time; but far less than it did previously.
Add in a weak labor market and people feel pressure to stay working all the time. Partly because everyone else is (and nobody wants to be at the bottom of the stack ranking), and partly because it’s easier than ever to avoid hitting a wall by just "one more message". Steve Yegge's point about AI vampires rings true to me: A lot of coworkers I’ve talked to feel burned out after just a few months of going hard with AI tools. Those same people are the ones working nights and weekends because "I can just have a back-and-forth with Claude while I'm watching a show now".
The likely result is the usual pattern for increases in labor productivity. People who can’t keep up get pushed out, people who can keep up stay stuck grinding, and companies get to claim the increase in productivity while reducing expenses. Steve's suggestion for shorter workdays sound nice in theory, but I would bet significant amounts of money the 40-hour work week remains the standard for a long time to come.
But that's for personal pleasure. This post is receeding from the concerns about "token anxiety," about the addiction to tokens. This post is about work culture & late capitalism anxiety, about possible pressures & systems society might impose.
I reflect a lot on AI doesn't reduce the work, it intensifies it. https://hbr.org/2026/02/ai-doesnt-reduce-work-it-intensifies... The spirit of this really nails something core to me. We coders especially get help doing so much of menial now. Which means we spend a lot more time making intense analysis and critiques, are much more doing the hard thought work of 'is what we have here as good as it can be'. Finding new references or patterns to feed back into the AI to steer already working implementations towards better outcomes.
And my heart tells me that corporations & work life as we know it are almost universally just really awful about supporting reflective contemplative work like this. Work wants output. It doesn't want you sit in a hammock and think about it. But increasingly I tell you the key to good successful software is Hammock Driven Development. It's time to use our brains more, in quiet reflection. https://github.com/matthiasn/talk-transcripts/blob/master/Hi...
996 sounds like garbage on its own, as a system of toil. But I also very much respect an idea of continuous work, one that also intersperses rest throughout the day. Doing some chores or going to the supermarket or playing with the kid can be an incredibly good way to let your preconscious sift through the big gnarly problems about. The response to the intensity of what we have, to me, speaks of a need to spread out the work, to de-concentrate it, to build in more than hammock time. I was on the fence about whether the traditional workday deserved to survive before AI hit, and my feels about it being a gross mismatch have massively intensified since.
As I started my post with, I personally have a much more positive experience, with what yes feels like a token addiction. But it doesn't feel like an anxiety. It feels like the greatest most exciting adventure, far beyond what I had hoped for in life ever. This is wildly fun, going far far further out than I had ever hoped to get to see. I'm not "anxiously" pulling the lever arm on the token machine, I'm just thrilled to get to do it. To have time to reflect and decide, I have 3-8 things going at once (and probably double they back burnered but open, on Niri rows!) to let myself make slower decisions, to analyze, while keeping the things that can safely move forwards moving forwards.
That also seems like something worker exploitative late capitalism is mostly hot garbage at too! Companies really try to reduce in flight activities. Sprint planning is about crafting deliberate work. But our freedom and agency here far outstrips these dusty old practices. It is anxiety inducing to be so powerful so capable & to have a bureaucracy that constraints and confines, that wants only narrow windows of our use.
Also, shame on Tim Kellogg for not God damned linking the actual post he was citing. Garbagefire move. https://writing.nikunjk.com/p/token-anxiety https://news.ycombinator.com/item?id=47021136
I _kind_ of get this if we're talking about working on big, important, world-changing problems. If it's another SaaS app or something like that, I find it pretty depressing.
We’re well past the need to retry the same prompt multiple times in order to get working code. The models with their harnesses are properly agentic now, they can find the right context, make a plan, write the code, run the tests and fix the bugs with little to no intervention from a human.
The hardest part now is keeping up with them when it comes to approving the deliverables and updating the architecture and spec as new things are discovered by using the software. Not new bugs but corrections to your own assumptions you had before the feature was built.
The hard part is almost entirely management.
That’s something to seriously think about.
Tests, linting, guidance in response to key events (Claude Code hooks are great for this), automatically passing the agent’s code plan to another model invocation then passing back whatever feedback that model has on the plan so you don’t have to point out the same flaws in plans over and over.. custom scripts that iterate your codebase for antipatterns (they can walk the AST or be regex based - ask your agent to write them!)
Codify everything you’re looping back to your agent about and make it a guardrail. Give your agent the tools it needs to give itself grounding.
An agent without guardrails or grounding is like a person unconnected to their senses: disconnected from the world, all you do is dream - in a dream anything can happen, there’s nothing to ensure realism. When you look at it that way it’s a miracle coding agents produce anything useful at all :)
I really cannot tell
The difference is that in gambling 'the house always wins', but in our case we do make progress towards our goal of conquering the world with our newly minted apps.
The situation where this comparison holds is when vibe coding leads nowhere and you don't accomplish anything but just burn through tokens.
I do think it can be addictive, but there are many things that are addictive that aren't gambling.
I think a better analogy is something like extreme sport, where people can get addicted to the point it can be harmful.