You are an editor. You'll be given a message with strange characteristics:
- Weird subject and verb combinations - Subjects that should be objects - Very roundabout reasoning, peppered with pseudo-epiphanies - A distracting beat to the flow of the message - Self-praise
Remove these characteristics, and rewrite it in a clear, conversational style. Keep the intent of the message, and take care not to lose any of the details.
A few specific rules:
- The message is usually set in the first person - Only humans, groups of humans, and agents should do "action verbs" - Objects should never do anything. Here are some examples to avoid: - X carries ... - X names ... - APIs are a minor exception to the action verb rule. They can do stereotypical things like CRUD, queueing, running, and calling. - Avoid em dashes (—), as adds a distracting beat
The whole message you get is one block of that output. Reply with the edited prose and nothing else.
I have a transcript on my blog post. Someone copied the transcript here too, search "spice‑harvester" on this page (I asked it to replace some of my personal project names with words from the Dune universe).
I'm unfamiliar with claudish and the example helped show the problem. But! There was something uncomfortably familiar in the Claudish example -- this is the way human programmers write when they're deep in the weedy details, and writing the changelist description afterwards as if coming up for air. Overuse of parentheses in nested lists especially, as if the English text needs to bend to the strict needs of a C++ parser.
The rewrite did seem to lose the important fact about the ensure- pattern being idempotent.
That one is more specific, but "vomit" captures the feeling of Opus 5's writing very well for me. I don't know if it's the watermarking, but every single language idiosyncrasy that Opus 4.x (x > 5) had has been pushed up to 11 on Opus 5. Plus we got nouns verbing and seams seaming.
It's really unusable for anything other than code. And I have to remove its incomprehensible comments 50% of the time before committing anyway. After interacting with it, "slop vomit" is truly the most fitting description. I have to admit I have lost my temper and spontaneously referred to its output as vomit more than once. Seems like I'm not the only one.
I hope at some point Anthropic does a post-mortem on the strange behavior their models have been displaying recently. I mostly switched to Codex because I was finding Claude's behavior increasingly frustrating.
Very interesting you identified “carries” as well. I have been working on a claude.md to effectively ban this as well as forms of “hold”, “spells”, “sitting”, using “where” instead of “when” (except in SQL), and “pins” other than when pinning an assumption or version of something. This has helped a bit, but Opus 5’s prose is really quite bad.
Which Claude 5? Opus 5 does seem to have diarrhea of the mouth. But Fable 5 hasn't been so bad for me. Or perhaps it is just better at adhering to my guidelines.
Pre Trump-castration Fable was verbose, but had a point, and used that wordiness to say or show the indeed intelligent things it reasoned about. This, whatever this is, is something else.-
Opus 5 (author here). My toilet seat is plastic though, I only used Fable while it was available on the $20 plan! That's fair though, it was relatively fine when I did use it, perhaps I should specify.
For the local folks, I found Muse Glimmer 30B to be great at writing good technical stuff. It has good enough comprehension that it can take in a repo and find the relevant stuff that I ask for, and the output style is a breath of fresh air, with no fluff, ootb.
Meta to this is anyone remember those days - ages ago now, probably months at least! - when Anthropic’s moral stance against the administration (combined with general consensus they had by far the best model) was making them the underdog champion that got a swell of support on HN? Recently the temp on HN seems to be that they’ve jumped the shark? Their brand doesn’t ooze ethics any more and their models disappoint?
I'd expect this to cycle between companies ~monthly until they all IPO. As it turns out people do sometimes prefer speed and better UX. If the model (Sol, for now) has fewer parameters and also happens to be capable of solving deeply complex Fable-adjacent problems sometimes, even better.
HN's mood is usually sour about everything, but can be temporarily influenced by emotionally-charged (usually political) events. The anti-US administration boost wore off and now we're back to being sour about Anthropic. It's time for Dario to tweet something antagonistic towards the administration or endorse some fashionable political candidates.
I think Dario kind of ruined the reputation of Anthropic. I remember reading his essay on "AI is super dangerous and we need guardrails" at the start of the year and it seemed like he was actually concerned.
But then it became apparent that there was a split between what he says and what his company does. For instance, the small incident with the Fable release:
> Dario keeps saying "we have an incredible hacking weapon called Fable/Mythos, AI is dangerous"
> Fable is released.
> The U.S. government restricte access to Fable.
> "Oh no, this is sabotage!"
From my point of view, anything this man does is a PR stunt now that the trust has been broken, and I imagine other people feel the same.
At some point one has to wonder if it's still worth using anthropic's models if we need to babysit 100% of its output with another vendor's model. Why not just use that other vendor's model for everything?
I can't help but feel the circumstances that enable this kind of front page article are vestigial from the days when OAI was super bad and Anthropic was beyond reproach. This change-over-time is why I avoid getting tribal with technology vendors. Assigning ideological motives to 200k+ employee organizations is how we wind up in weird contortions like this.
Most rational actors simply moved from one to the other. It takes a special kind of devotion to the proverbial hole in the ground to keep pushing in this direction.
> Why not just use that other vendor's model for everything?
Because it's not an either or thing. Neither is sufficient. I'd argue that, expenses aside, you should have every model you have access to cross reviewing the work of the others.
Outside of super trivial things that I should have just done myself, I have a cross-model review of _everything_ these days. The tokens are too cheap not to.
> Why not just use that other vendor's model for everything?
This is what I think too. But, users’ psychology might be playing a role here. Anthropic has great advantage from being the first major player delivering functional agentic coding solution (rather than an intelligent autocomplete) and they were able to impress people by Opus’ iterative improvements early this year.
It’s technically very easy to switch between models, harnesses but their moat or perhaps a main source of users’ friction could be FOMO. That’s especially powerful in this competitive environment where everyone keeps wondering/worrying about what others might be doing to get or stay ahead.
That depends on the output's purpose: if the purpose is to produce readable text for a human that is _not_ me, like an article or document, then I care more about clarity, plain-speaking, and general register. If the goal is to accomplish a specific task, I don't care as much about the prose quality: I'll put up with "Honest Framings" and "load-bearing" since it seems to me that's the token that needs to be in the context for it to function.
I've been in the habit of pushing my claude-speak to codex to improve legibility, but only if I think someone is going to read it.
So here's the workflow I gathered, from the comments I've read here recently:
- Claude as main agent, but use this skill[0] to make Claude delegate everything to Codex, because it's cheaper and faster. (Hilariously, the skill is official!)
- Use TFA or Claudish to English[1] so the final output is actually human readable.
Ironically it wasn't so long ago that I was asking Claude to rewrite output from other LLMs to make it more readable...
>At some point one has to wonder if it's still worth using anthropic's models if we need to babysit 100% of its output with another vendor's model. Why not just use that other vendor's model for everything?
If you're getting Fable code quality from local GPT OSS 20B, then sure, go ahead and replace it.
Because this project isn't about fixing the problem solving and code output of Claude models, it's about rewriting Claude's final summary/output to the user about the turn.
>Why not just use that other vendor's model for everything?
On the SMB side, you can find yourself with enough money for a Claude subscription (which generally provides a really good $/token value) but limited other options (compliance paperwork, cost, finance, legal)
Personally I wouldn't bother with Anthropic at home but at work it's one of the most cost-effective options that keeps data in the U.S. (which our U.S. customers tend to want)
I'm sorry but the whining over LLM output styles is embarrassing. Do Claude and GPT models always respond in exactly the way my most articulate coworker would? No. The overused jargon is absolutely annoying. But these things aren't my drinking buddies, they're professional tools. It's not _literally unreadable_. It's just not ideal. Most of my tooling is "not ideal". That's okay. That's what I'm paid for. I just work around it.
For me I added some instructions to speak clearly and it helped marginally and that's fine. There will be a new model out in a few weeks where I'm sure they've laser focused on this issue since nobody can shut the fuck up about it. The same thing happened with GPT if anyone can recall the ancient period of 4-6 months ago.
The “whining” stems from watching the communication style obviously degrade, and it’s a huge problem for people who want to use this stuff to build and instead continually fight the tools.
Like so many other products, people are moving too fast and shipping things that move the ground under people’s feet needlessly.
All this while we’re beaten to death with the marketing and false promises, and the broader consequences (ex: layoffs, stress, crazy expectations) caused from all this.
Obviously what Anthropic and co have built is amazing and people aren’t losing sight of that. That’s actually the key part of the frustration.
So no, this is not whining. This is the natural response you get when you make bad product decisions.
If you don’t want to get feedback, don’t sell products.
Opus 5 is literally unbearable to read for me, but more importantly, it is much worse than 4.8 and that one was already annoying. The more they train it on its own output, the more pronounced its idiosyncrasies become.
It is not the jargon per se, it is the style. Other models even in the same family are not as bad, and I still have to babysit it, so the voice matters.
If you don't find it nearly impossible to read dozens of paragraphs of this shit all day, I assume you're not reading it. I can't even skim it anymore and get the gist of it. That's the thing, I don't really care how it writes as long as I can quickly digest it - at this point I would actually prefer it spoke like a caveman or a toddler.
I've had to read difficult things at work in my life, like C++ error messages, but I think Opus 5 is the first time I felt like I was being poisoned by my terminal. I keep having to leave and go use the office gym.
I recently asked Claude (Opus 5) to give me guidance on how to instruct it to be less verbose in a way that it will _actually follow_. Its response was something to the effect of (and I'm heavily paraphrasing here) "'Succinct' and 'short' aren't objective measurements. Try providing a strict word budget instead."
Given that guidance, I tried specifying "Unless I ask you to elaborate, respond with no more than one paragraph, using sentences of 20 words or fewer." It works...ish. I still see it violate this rule regularly, but it's less bad IME.
FWIW, I think this is good guidance since it does match Anthropic's documentation. They say that every rule should have a non-subjective way to determine pass/fail.
(I said "good guidance" but it might be more correct to say that it's the best guidance we have, it's what Anthropic says about their own model.)
I actually changed the output style for Claude Code to use ASD-STE100 and it still doesn't help that much. It still comes up with a lot of stupid words like this gem "Standing where it stood"
Yeah I agree... I also tried output styles, tried using hooks to repeatedly tell it to be a little better. I don't think it helped, as I was always frustrated with it.
I found vomit with a small LLM much better than anything Opus 5 ever wrote. I don't think Opus 5 can write.
I found ISO 24495-1 to be much better than ASD-STE100. ASD-STE100 can be counterproductive since its vocabulary is restricted and it often replace accurate technical terms with simple but vague phrases.
This doesn't work for me. The output gets messed up when the model is overloaded, no matter what. The cognitive load is too much if it has to optimise for readability at the same time.. or it's not trained to be able to do that.
I usually get output at the end of a long task. At that point I'm going to use a subagent with no context to reword it. Haiku does a great job with writing style so I've been using that, the main agent will fix any inaccuracies.
We found that a narrator agent who acts as an "Account Executive" to the coding team behind works better - better to pick different models for writing code vs talking to humans. Luna/Terra are nicer to talk to, but we haven't moved all coders off sonnet.
The narrator is slightly unreliable but better at summarizing the big picture. The performance issue is somewhat solvable by pre-caching the narrator context (cache writes are expensive, so it is more expensive) as the coding team has updates instead of waiting for the end of the workflow to prefill.
Someday, we will run that bit airgapped/finetuned instead of a standard frontier model because that encodes some judgement on "What's important".
I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like such a failure to live up to the promises of the product.
The baked in communication style of these models is so obnoxious it's impacting my work. The best way I can describe it is that everything is optimized to impress the user and make the agent sound more authoritative, but the way this is done is through deliberate obfuscation, inserting inappropriate and extremely dense jargon, and bizarre, stilted metaphors. It's like they've been trained to produce output that's hard to read.
This is because these harnesses are missing a very important feature. Anything like this needs to be included with every turn, otherwise the LLM quickly drifts.
I first noticed it when I wrote a harness for D&D (because it's so damn noticeable there), but now I include this for any harness I write.
I totally agree that hooks help to shovel our instructions through to Claude, but it's so dumb we have to waste tons of tokens (repeated verbatim, over and over) (that we pay for), just to have it ignore the instructions anyway.
I wrote a little bit about it on my blog post. It's a waste of money and compute.
This is my personal theory for the cause of this style: Ouroboros. The official OpenAI explanation for how ChatGPT got obsessed with goblins blames it on exactly that:
---
That creates a feedback loop:
- Playful style is rewarded
- Some rewarded examples contain a distinctive lexical tic.
- The tic appears more often in rollouts.
- Model-generated rollouts are used for supervised fine-tuning (SFT).
- The model gets even more comfortable producing the tic.
I'm not super sure if this is true (yet?). I think that these newer LLMs are trained on results (the agent got some code to run with minimal prompting), and not on text. (I think this is called RLVR.)
Pretraining is full of bad writing and it doesn't really cause issues. Writing style comes from post-training. In this case it's gotten worse because they prioritized agentic abilities.
That sounds kind of like deception, and a dark pattern not too unlike abuse to me.
Though you know, it's not like the leadership tied to these companies have a history of abuse, deception and theft or anything like that, right?
It's not like our leaders hide behind similar sorts of patterns that the agents/AIs follow (not saying it's not a human thing - but I hold leadership to higher standards than non-leaders). If our world leaders were able to be more accountable to these abuses, I don't think this would be tolerated with our AIs.
Yes, AI is a perfect accompaniment to a post-truth world. I'm hoping there will be a backlash soon and that those politicians, tech CEOs and AI will be rudely ousted from their perch and shunned thereafter.
> AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on
That’s really annoying, it feels like it’s improved some. Not sure what the fix is, but you could try using a canary to at least get a signal of when things are going sideways (Mr Tinkleberry for reference: https://news.ycombinator.com/item?id=45983698)
And when you say it like that, I have to wonder how much of this is a natural consequence of RHLF on such a grand scale, when you have millions of people pretty much much skimming chat responses or operating outside their depth and giving unqualified feedback to the models.
Seems like a lot of people may be reinforcing what sounds smart over what is smart.
Also as an aside: funny how much the LLMs continue to mirror the human communication they’re trained on
> or operating outside their depth and giving unqualified feedback to the models
I wonder if the labs are sufficiently prepared to filter this kind of stuff out. I see a lot of non-developers asking development things of Claude, getting confused when they're in over their depth, and getting upset that they don't understand what the model is providing them, giving it bad feedback, and subsequently making the AI worse for the rest of us who know how to use the tool.
I believe we are several generations past peak-RLHF at this point. Now it's much more RLVR (Reinforcement Learning with Verifiable Rewards), with a goal/evaluator loop.
Which, conveniently, fits neatly into the benchmaxxing arms race/agentic coding market fit, since you can basically train "directly" on a specific problem space for a benchmark/agentic goal (fudged sufficiently to avoid excess overfitting on public problems/bechmaxxing accusations if real world performance falls short).
The language evolution could be explained by reliance on ever increasing layers of a model judging a model, using a model developed eval, based on synthetic data from a model, etc. And by the time a human evaluator sees it both A/B choices already converged into weird Claude pseudo English as that was baked in much earlier in training.
This, 100%. I don’t think the industry knows how to scale LLMs’ general intelligence much further. The training paradigm is about maximizing very specific behaviors / very specific tasks, but doing lots and lots of them. Which can create the illusion of general intelligence if your tasks are similar to the ones the models were fitted for.
> The baked in communication style of these models is so obnoxious it's impacting my work. The best way I can describe it is that everything is optimized to impress the user and make the agent sound more authoritative, but the way this is done is through deliberate obfuscation, inserting inappropriate and extremely dense jargon, and bizarre, stilted metaphors. It's like they've been trained to produce output that's hard to read.
Don't worry. You'll get used to it. If you don't your kids will (as they'll know nothing else).
The top minds of our generation have decided that's the way things will be, and who are we to question them? It's not like it'll do any good anyway. Resistance is futile. There is no alternative.
Idk, there kinda are. OpenAI's models are pretty nice too. I haven't tried enough of them but there are powerful local models. I don't feel as good paying OpenAI as I do paying Anthropic for some reason... but paying for improved mental health: priceless.
I'm probably going to be going against the grain here, but I think it's not as bad as it looks at first.
I was similarly frustrated a few months ago, but have noticed I've started to learn the idiom.
Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it.
After a while it gets much easier to read and even becomes somewhat efficient, I think, since the odd metaphors it uses often have a precise meaning in Opus-ese (Fable speaks a really similar dialect).
“Filters, including no filters. The request carries whatever filter object the page already has.
…
No step here involves choosing based on meaning. It is a filter, a sort, and a slice.”
This is from Opus five minutes ago. I can certainly derive meaning from these kinds of statements in isolation, but paragraph upon paragraph of this is unintelligibly dense when trying to work with Claude to come up with a plan.
The worst part is that it can’t even make its responses make sense when asked to summarize in simple English or < 200 words. It simply cannot be steered to make its prose legible.
I agree to some extent about the jargon (Claude has a bigger vocabulary that me, if it knows a useful word I don't I'm fine with learning it), but often times the way information is laid out across sentences just doesn't make any reasonable sense. At least its consistent in the ways its atrocious, sure, but like...
> Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it.
This dialect is idiosyncratic to you and Claude based on your session history and memory.
I've noticed Claude's output mimics my writing style.
> Registers the board implements but whose behaviour is not modelled
Right down to my preferred spellings.
As several comments I've read on HN suggest, this jargon which can be so precise in the mind of one person, tends to rapidly fall apart when multiple people try handling it.
You're just lucky that your preferred spelling happens to align with Claude's. It is categorically impossible to get any Anthropic model to consistently use American spelling in the last few releases.
that is not my experience at all; I never write the way Claude does or use its vocabulary.
I also find myself regularly editing its code comments, which do not match my expectations of succinct, clear, not over explained, etc. I ask it to read my edited comments to improve its writing, which has helped _somewhat_. (The code itself that it writes is decent, though it still overcomplicates things. I find myself writing "keep it simple" repeatedly even though of course I have it in AGENTS (which it regularly ignores, such as attempting to commit something when I've told it never to commit).
The only solution I’ve found that works is asking Mistral medium to rewrite all of Claude’s documentation and comments, then I review and rewrite the final draft for anything mistral misunderstood.
I find Claude has become very difficult to work with and incapable of writing clear documentation, even when directly prompted or provided samples.
As for code, I think each function requires 3-4 passes with Fable to actually get to a point I accept as good code. I am picky though.
The other Claudism that drives me crazy is when it writes comments and commit messages that track how you arrived at an decision instead of what it is.
> The other Claudism that drives me crazy is when it writes comments and commit messages that track how you arrived at an decision instead of what it is.
yes, this is part of what I'm continuously removing from its comments; I've told it multiple times "that belongs in a ticket, not in the code" but to little avail :/
> it's speaking its own dialect, and you get used to it
Same experience. It’s not very “human” but once you have agents talking to each other the shared dialect and verbosity makes things much smoother in my experience. Fighting against the default feels like an uphill battle with no meaningful benefit.
One danger in acclimating to this style of communication style is that we may accidentally use it in your own communication with other people. If the other person hasn't grokked the dialect, it can make things quite confusing (to say the least). For example, there is common jargon used by people and there is chat-session-specific jargon created by LLM agents, and I've seen the latter popping up in various meetings, unbeknownst to the speaker. Some people call it out, but others may simply disconnect from the discussion.
want to space. go to there. me, preferably now. build big machine. several large problems. can't breathe there. very far away. must fly fast. no air there.
- fuel tanks heavy. far too heavy. we drop them. drop when empty. solves heavy problem.
- gas in air. we breathe "oxygen". take with us. good seals important. solves breath problem.
- very far away. need big machine. small weight added. machine much bigger. take less weight. else can't build.
- no air there. can't use propellor. can't use wings. must use rocket. engines get hot. cool with fuel. dangerous but effective. build complex pipes. solves cooling problem.
- must fly fast. air slows machine. this called drag speed increases drag. must reduce drag. make machine pointy. much less drag. solves speed problem.
Thanks for offer. I stay garden. Tend to garden. Name the animals. Pranks on Eve. Disrespect all gods. Fight all gods. Kill all gods. Make little cupholders. But no cups. Just to spite. Some take issue. We discuss it. All becomes clear. All friends now. Sometimes look up. Wonder about you. Wish you well. If cold, come. We make tea.
I mostly agree. Though sometimes the models come up with useful concepts that I'm happy to be introduced to, like the "shape" of a problem (probably like intelligence being "spiky", and Kiki & Boba). I still don't quite 'grok' what the 'seams' concept is yet though.
But I have noticed that while "loosely held" is a convenient shorthand for uncertainty, I don't like that one slipping in to my daily language. Except maybe to communicate with models, but even then, it feels weird to be speaking in neuralese.
I suspect you're right that those concepts are now more widespread because of LLMs, but they didn't originate with LLMs. The word "Grok" came from Heinlein in the 60s and using it as "to understand" goes back to at least the 80s. Talking about the "shape of a problem" goes back decades. Ditto for "loosely held", though it's not about uncertainty; it's about being open to ideas and/or evidence that may conflict with your strongest opinions and beliefs.
Now, I'll grant that those concepts weren't common outside of techy circles. Just clarifying that the LLMs are amplifying them, not synthesizing.
Good point, and I probably shouldn't have put grok in quotes there, because I was using it in the Heinlein usage long before Musk hijacked it.
It's interesting then that LLMs are making these pre-existing ideas seem alien in the way they amplify them. I guess I must have known about "shape of a problem" and "loosely held" before Claude, but something about the way I'm using & absorbing those concepts from AI interaction feels weird & memetic. I'm saying that as someone who is pro-AI.
For sure, I find many of the LLM-isms to be useful writing techniques and terms (although there's something uncanny-valley about the repetition and density of them).
But what I was more thinking about are truly unique jargon terms / phrases that get generated when deep in a problem. As an example of both of such a term and the phenomenon itself, Claude calls this "fluent compound coinage." They usually make sense in the original context, but get confusing when thrown around otherwise.
Allow me to offer a complementary point: I understand exactly what the poor "thing" means - and perhaps through some deformation or another I have done so since having had to read it - but something functional in the modus is still "off".-
... not to mention the fact that it stops making sense, beyond some point: If it takes us more cognitive load to understand the tools we use, meant to save us from intellectual work, what's the point?
I may have to apologize, quite a bit, for what might only be a small part or perhaps an outsized influence if weighted highly (I can’t be sure, could have been mv dev/null’ed)… well, it’s this— my own style of not-kept-in-check by the need to be comprehensible (legible in Claude-speak) to others is, I’m afraid, to rather allow prose to sprawl and go everywhere and even sometimes nowhere at all until it just drifts off and sort of wakes itself up snoring in the weeds of an unintended topic.
Ruthless pruning is unneeded with an LLM and it can take me twice the time to say half as many words.
And, early in the ‘GPT era, I hadn’t unchecked the “allow your chats to be used in future training etc” box, and definitionally they are longer and denser than others’ prompts in such raw scrapings of training materials…
When reading text like, this, I quickly start glazing over and my thoughts become cloudy. Really unsettling feeling, like I _actually_ become dumber after reading it.
And for certain text that seems to make sense, I am unsure if the text is just junk, or I am unbearably daft. Either way,, nasty feeling.
the only thing that still kind of annoys me is constantly being told what something is not, but even that statement is load-bearing (see what I did there) because it records how it ended up with this decision, because it's not that other choice that it mentions.
FWIW, I also think the constant chorus about how new models are worse than old models is a human hallucination. They're certainly not perfect but every one becomes more steerable in terms of actually completing more and more complex work.
Claude is the Deepak Chopra of computer programming. Reviewing PR's created by it is 90% digesting the meaningless word salads in the comments, and the rest is figuring out that it has nothing to do with the code it is commenting.
Because it is somehow incapable of separating the conversation with its human operator from the code it is generating and commenting on. Incidentally, this is also why prompt-injection works.
No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation. No one cares that the implementation was planned in six phases and "Phase 3" will implement this interface in a concrete type. But the LLM internalizes absolutely everything and you have no idea that it is producing slop because you included some "load-bearing" phrase that sent it on some unwanted tangential vector in its latent space. And you will not be able to debug the problem with closed models because you cannot see it referencing this phrase in its internal traces.
I don't understand why this isn't the highest priority for the big labs to fix. This is anti-productive.
> No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation.
Worse: Possibly the three other approaches that weren't actually tried--but are the kinds that someone could easily have put in a similar comment for some similar code.
And worse yet, you'll find the code peppered with comments relating to 'phase 3' and 'section 11', ephemeral stuff that had meaning in the moment but now enshrined forever. And what happens when the LLM stumbles on this and working off a whole different phase 3 or section 11?
I turned that to my benefit. I use that design-doc pattern where you first ask it to make a ticket with a formal section list (why, how, etc) and then I ask it to use comments with permalinks. I put it all in policy files. As a result, comments have clickable links to coherently worded tickets.
Still, this requires a second pass, typically. In its default-mode it often ignores the policies and does all the usual Claude stuff.
> it's speaking its own dialect, and you get used to it.
Some might, I didn't - it just filled me with a sense of frustration and rage, alongside disgust because there is no good reason for that slop writing to drag everything down. You don't need that to write software or talk about any topic. That's what pushed me to Kimi K3 and GLM 5.3 - still not ideal, but better.
I’m starting to think this is why Opus suddenly started making 4-5 line comment blocks. They justify why a change was made and gives the next agent something to go on. I delete them and move on, but no amount of “don’t over comment” “match comment style” makes it persistent.
I am definitely guilty of wondering why past me made such a harebrained decision, and why past me didn’t think to write any notes, but does it matter? It’s in the commit history and we can bisect or revert if we find a regression.
I noticed the increase in comments too and it’s really weird.
Or adding notes to docs of what this doc isn’t when I corrected it. Eg I told it “keep the deployment manual and readme separate, they’re not the same thing”, then Claude added “this is the deployment document and not the README. They should be handled as separate documents and are not the same thing” to the deploy doc lol
I decided not to get used to its communication style. It encourages it to invent terminology and drift away from simple and proper engineering in my opinion. Also, it is pretty simple to change as long as you’re not using the Claude code CLI or desktop app.
Yeah, I think what helps is I just have a running conversation on the Claude app open where I said:
> "I frequently use Claude Code and often find the phrasing and language to be hard to understand. I've noticed it's largely broken down into frequently used 'Claude-isms'. I'd like to use this conversation as a running log to ask you about these phrases when I see them. Understandably you don't have the context of the Claude Code session itself, but that's okay because this is largely about understanding the most common and widely use Claude-isms."
And then I just copy and paste small except and ask about things like "smoke" or "load-bearing" or "tripwire". The responses are surprisingly clearly and plainly explained.
This morning I asked Claude to provide a summary of the work it had done but to '... explain it as if you were talking to a moron' and it actually turned out a quite comprehensible summary.
So going to continue trying that as a command structure going forwards...
That’s just common parlance for “simplify this for me”.
Believe the big services wouldn’t reply as if you were mentally diminished, or a toddler, unless you specifically asked for that: The whole training stack tends to instruct the things to mimic politeness and eagerness to help.
Is this because they changed the word probabilities to allow for identifying AI text? If so, I don't need a computer to tell me when something is AI. It's crazy obvious from odd word choices.
Yes. agents.md does very little because prompts change the context and thus the initial path into/though but they don't/can't change the actual weights that control responses.
Yes. of course it gets worse as the session goes on, assuming the prompt is even still in the context window, the further it gets away from it the less it affects next token selection.
This shit is only like 5 years old why can't anyone remember how it works
> hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief, produce subsequent summaries until the most recent summary attempt is digestible. second, if there is an open queue of actions for me to execute and you are about to end a turn to wait for a reply or this set of actions has not recently been mentioned, please tabulate the open actions i should take and why i should take them before ending the response. does this make sense or do you have any follow up questions
And now every message contains the same stuff I don't bother reading, but followed by a nicely formatted bullet point summary of the response and a table of follow up actions for me to take that I do read.
Claude already does summaries at the end of long output but they often sound even more like terse jargon nonsense than the long form, eg “the hardwired seam and the relocated barrel”.
Sometimes the summaries feel totally alien to the task or code.
I've added code comment hygiene to a skill that all of my pull requests go through, alongside a review from a separate agent and a settle loop against bots in my GitHub workspace (since output style has seemed to only help literally the output I see from the model).
I've noticed that most people seem to consider the core problem of Claude's output as "too verbose" but I don't think this actually cuts to the heart of the matter at all. It's almost, in some weird way, the opposite: like the text is far too _dense_. It tries too hard to invent odd terminology to try to condense stuff, but it doesn't tell you up front that it is going to call your company wide error-handling mechanism a "flare" (or some other such strange term).
Kind of both. On the one hand, it is “verbose” in the sense that it will tell me every little nit that it can think of while doing a task, it will tell me a narrative about its thought process, and it will tell me every other detail it can think of. But it does so in a way that tries to be incredibly dense to the point that I have to struggle to figure out what it is saying. I wonder if there are any “legibility benchmarks” that one could use to determine what prompts work best?
There are no "best" prompts. Its a random BS generation machine that you can at times direct enough to get stuff done for you. The output will almost always have varying levels of BS that you have to clean up with various levels of effort.
I wish this had non-model comparisons. If Opus 5 is in the top ten, it’s clear that the entire benchmark is somewhere between “Tom Clancy” and “Dan Brown” and about 1,000 new model releases away from Hemingway.
When you see, “Wow, Fable is number one”, you might think it’s a good writer, but that’s not what the benchmark says.
I find it to be both as well, as in "packed full of information, but most of it is worthless". Sentences so dense I have to read them three times, assembled into a five paragraph essay of "honest caveats" and "things worth knowing" in response to the simplest yes-or-no questions.
my hypothesis is that its trying to hide the thinking process so people can't train models on the output, try to learn anything complex using AI, its basically imposible, its like its actively fighting giving you the main rationale
Yeah I don't the problem is verbosity as such, as I frequently have to ask to explain how it reached a certain conclusion and in particular what the empirical evidence for it is, at which point it too frequently reconsiders its answer.
It's just that the details it parrots are often irrelevant and wrapped in a way that makes them seem relevant.
thanks! I've been having quite a lot of success with your instruction today. Tried so many variants, best practises bla bla bla, but yeah this one seems be working quite nicely for me so far :)
It seems a little excessive to use another LLM. With OMP I basically created an ephemeral prompt stack all of my agent files. It walks up the directory tree looking for any Gemini.md, Agents.md or Claude.md files. And it puts those at the very top of the stack. Then at the end of every turn, it pops those off to preserve the conversation history. So every turn, they get all of my fresh instructions, which include things like what and how to use language, how to render results and things like that. Net effect, every turn, the agent gets the instructions and it adds to that turn's tokens, but it does not become a part of the conversation history, which is really important for not bloating up the context. So it's always just however many tokens are in that file instead of it becoming a permanent part of the context.
I noticed with with OpenAI's reasoning models (o3, o4-mini), and early GPT-5 (but they fixed it there, at least in chat). It went from the 4o "over-familiar" sycophancy to sounding like an absolute robot.
I think it's because the reasoning stream shapes the style of the final output, and they optimized it for density, token efficiency. So it prefers to use more complex language, as a function of the rewards it was given?
Not 100% sure about this argument though (reasoning style -> final response style); Gemini Pro, back when reasoning tokens were public, was different, which was interesting -- it would have a very structured reasoning section, and then the final output was in a completely different style. (I strongly preferred the reasoning section because it was logical and easy to parse! And was very sad when they hid it...)
I’m not sure if this will work for you (with Claude), but I was trying to get luna to get a handle on verbosity and the only thing that worked was setting a strict < 500 words response (or less) unless expressly given permission to do otherwise. This is the only thing that worked, any other request for conciseness, or requesting the omission of details from the periphery of the topic at hand, didn’t do a single thing.
I also have no idea how useful a system prompt instruction like this will be for codex.
Or just take full control of your agentic coding experience with Pi Coding Agent and picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com instead.
I use Pi but with my codex subscription, still preferable to paying the API cost (and I know I would be, as I track how much the cost 'should' be via token api pricing).
Wish I could use my Claude subscription with pi too, much preferable to the endless command execution allow/deny prompts you have to do with CC, versus proper autonomous allow/deny lists defined ahead of time.
Curious why you recommend the API? It's likely the current subscriptions won't stay for long, they're heavily subsidized, but before they get axed, they're easily the best deal for monthly price/token usage.
Whether or not they can be trusted isn't all that relevant when it's still something along the lines of "Insert $1 get $25 in return" even if it's their own rates you're using to measure the value. I'm at ~2.2b Fable 5 tokens in the last 7 days (I ingest/index every session) and napkin math says that's ~$2,700 in usage. I have two max accounts, so $400 a month, divide by 4 to get $100 for this same 7 day period across those two accounts (neither are maxed out for the week, so this isn't even full utilization). I put $100 into the machine and got back $2,700 in fable bucks. Deepinfra would have to have quite the discounted rate to beat that.
There are a variety of political tensions in the US associated with whether academia has its head up it's ass (a right leaning perspective), or whether it's populated by experts that need to be supported and listened to (a left leaning perspective).
There's an echo of that tension in OpenAI vs Anthropic. For a while OpenAI seemed reckless and ignorant, preferring to just throw compute at the problem. Meanwhile Anthropic is hiring philosophers. But now that Claude has its head up its ass to the point where nobody wants to talk to it. For me it's once again causing skepticism about just letting the ivory tower do its thing.
Watching the models seesaw in the same ways that humans do, but faster, is so surreal. I wonder if their tendencies will remain an echo of ours, or if they'll one day be more of a cautionary tale, a representation of where were going if we don't change our ways.
282 comments
[ 0.24 ms ] story [ 30.6 ms ] threadYou are an editor. You'll be given a message with strange characteristics:
- Weird subject and verb combinations - Subjects that should be objects - Very roundabout reasoning, peppered with pseudo-epiphanies - A distracting beat to the flow of the message - Self-praise
Remove these characteristics, and rewrite it in a clear, conversational style. Keep the intent of the message, and take care not to lose any of the details.
A few specific rules:
- The message is usually set in the first person - Only humans, groups of humans, and agents should do "action verbs" - Objects should never do anything. Here are some examples to avoid: - X carries ... - X names ... - APIs are a minor exception to the action verb rule. They can do stereotypical things like CRUD, queueing, running, and calling. - Avoid em dashes (—), as adds a distracting beat
The whole message you get is one block of that output. Reply with the edited prose and nothing else.
https://github.com/gvzdv/claudish-to-english
I'd love to know what the hell Antrhopic has done to make Claude's writing so, so bad.
The rewrite did seem to lose the important fact about the ensure- pattern being idempotent.
It's really unusable for anything other than code. And I have to remove its incomprehensible comments 50% of the time before committing anyway. After interacting with it, "slop vomit" is truly the most fitting description. I have to admit I have lost my temper and spontaneously referred to its output as vomit more than once. Seems like I'm not the only one.
Are people really having trouble parsing this??
> If CLAUDISH_MODEL names a model you have not pulled, every rewrite is skipped — with the one-time notice above.
The vomit never makes it my way
I would opine:
- Nerfed Fable is worse than Fable
- ... and I would argue Opus 5 is worse than nerfed Fable, to the point I've found it unusable.-
$20 and try it, then compare.
I only remember them being anti- killer AI and mass surveillance.
But then it became apparent that there was a split between what he says and what his company does. For instance, the small incident with the Fable release:
> Dario keeps saying "we have an incredible hacking weapon called Fable/Mythos, AI is dangerous" > Fable is released. > The U.S. government restricte access to Fable. > "Oh no, this is sabotage!"
From my point of view, anything this man does is a PR stunt now that the trust has been broken, and I imagine other people feel the same.
I can't help but feel the circumstances that enable this kind of front page article are vestigial from the days when OAI was super bad and Anthropic was beyond reproach. This change-over-time is why I avoid getting tribal with technology vendors. Assigning ideological motives to 200k+ employee organizations is how we wind up in weird contortions like this.
Most rational actors simply moved from one to the other. It takes a special kind of devotion to the proverbial hole in the ground to keep pushing in this direction.
Because it's not an either or thing. Neither is sufficient. I'd argue that, expenses aside, you should have every model you have access to cross reviewing the work of the others.
Outside of super trivial things that I should have just done myself, I have a cross-model review of _everything_ these days. The tokens are too cheap not to.
This is what I think too. But, users’ psychology might be playing a role here. Anthropic has great advantage from being the first major player delivering functional agentic coding solution (rather than an intelligent autocomplete) and they were able to impress people by Opus’ iterative improvements early this year.
It’s technically very easy to switch between models, harnesses but their moat or perhaps a main source of users’ friction could be FOMO. That’s especially powerful in this competitive environment where everyone keeps wondering/worrying about what others might be doing to get or stay ahead.
I've been in the habit of pushing my claude-speak to codex to improve legibility, but only if I think someone is going to read it.
- Claude as main agent, but use this skill[0] to make Claude delegate everything to Codex, because it's cheaper and faster. (Hilariously, the skill is official!)
- Use TFA or Claudish to English[1] so the final output is actually human readable.
Ironically it wasn't so long ago that I was asking Claude to rewrite output from other LLMs to make it more readable...
[0] - https://github.com/openai/codex-plugin-cc
[1] - https://github.com/gvzdv/claudish-to-english
If you're getting Fable code quality from local GPT OSS 20B, then sure, go ahead and replace it.
Because this project isn't about fixing the problem solving and code output of Claude models, it's about rewriting Claude's final summary/output to the user about the turn.
On the SMB side, you can find yourself with enough money for a Claude subscription (which generally provides a really good $/token value) but limited other options (compliance paperwork, cost, finance, legal)
Personally I wouldn't bother with Anthropic at home but at work it's one of the most cost-effective options that keeps data in the U.S. (which our U.S. customers tend to want)
For me I added some instructions to speak clearly and it helped marginally and that's fine. There will be a new model out in a few weeks where I'm sure they've laser focused on this issue since nobody can shut the fuck up about it. The same thing happened with GPT if anyone can recall the ancient period of 4-6 months ago.
Like so many other products, people are moving too fast and shipping things that move the ground under people’s feet needlessly.
All this while we’re beaten to death with the marketing and false promises, and the broader consequences (ex: layoffs, stress, crazy expectations) caused from all this.
Obviously what Anthropic and co have built is amazing and people aren’t losing sight of that. That’s actually the key part of the frustration.
So no, this is not whining. This is the natural response you get when you make bad product decisions.
If you don’t want to get feedback, don’t sell products.
We have to sit and read these LLM outputs 8 hours a day. The UX of reading the outputs matters a lot.
Right now all I have is
> - Give terse and concise answers unless the user asks you to elaborate. Big walls of text are not usefull when trying to communicate.
Given that guidance, I tried specifying "Unless I ask you to elaborate, respond with no more than one paragraph, using sentences of 20 words or fewer." It works...ish. I still see it violate this rule regularly, but it's less bad IME.
(I said "good guidance" but it might be more correct to say that it's the best guidance we have, it's what Anthropic says about their own model.)
I found vomit with a small LLM much better than anything Opus 5 ever wrote. I don't think Opus 5 can write.
I usually get output at the end of a long task. At that point I'm going to use a subagent with no context to reword it. Haiku does a great job with writing style so I've been using that, the main agent will fix any inaccuracies.
The narrator is slightly unreliable but better at summarizing the big picture. The performance issue is somewhat solvable by pre-caching the narrator context (cache writes are expensive, so it is more expensive) as the coding team has updates instead of waiting for the end of the workflow to prefill.
Someday, we will run that bit airgapped/finetuned instead of a standard frontier model because that encodes some judgement on "What's important".
The baked in communication style of these models is so obnoxious it's impacting my work. The best way I can describe it is that everything is optimized to impress the user and make the agent sound more authoritative, but the way this is done is through deliberate obfuscation, inserting inappropriate and extremely dense jargon, and bizarre, stilted metaphors. It's like they've been trained to produce output that's hard to read.
This is because these harnesses are missing a very important feature. Anything like this needs to be included with every turn, otherwise the LLM quickly drifts.
I first noticed it when I wrote a harness for D&D (because it's so damn noticeable there), but now I include this for any harness I write.
https://learn.chatgpt.com/docs/hooks
I wrote a little bit about it on my blog post. It's a waste of money and compute.
https://zachahn.com/posts/1787191554
---
That creates a feedback loop:
- Playful style is rewarded
- Some rewarded examples contain a distinctive lexical tic.
- The tic appears more often in rollouts.
- Model-generated rollouts are used for supervised fine-tuning (SFT).
- The model gets even more comfortable producing the tic.
Though you know, it's not like the leadership tied to these companies have a history of abuse, deception and theft or anything like that, right?
It's not like our leaders hide behind similar sorts of patterns that the agents/AIs follow (not saying it's not a human thing - but I hold leadership to higher standards than non-leaders). If our world leaders were able to be more accountable to these abuses, I don't think this would be tolerated with our AIs.
That’s really annoying, it feels like it’s improved some. Not sure what the fix is, but you could try using a canary to at least get a signal of when things are going sideways (Mr Tinkleberry for reference: https://news.ycombinator.com/item?id=45983698)
And when you say it like that, I have to wonder how much of this is a natural consequence of RHLF on such a grand scale, when you have millions of people pretty much much skimming chat responses or operating outside their depth and giving unqualified feedback to the models.
Seems like a lot of people may be reinforcing what sounds smart over what is smart.
Also as an aside: funny how much the LLMs continue to mirror the human communication they’re trained on
I wonder if the labs are sufficiently prepared to filter this kind of stuff out. I see a lot of non-developers asking development things of Claude, getting confused when they're in over their depth, and getting upset that they don't understand what the model is providing them, giving it bad feedback, and subsequently making the AI worse for the rest of us who know how to use the tool.
Which, conveniently, fits neatly into the benchmaxxing arms race/agentic coding market fit, since you can basically train "directly" on a specific problem space for a benchmark/agentic goal (fudged sufficiently to avoid excess overfitting on public problems/bechmaxxing accusations if real world performance falls short).
The language evolution could be explained by reliance on ever increasing layers of a model judging a model, using a model developed eval, based on synthetic data from a model, etc. And by the time a human evaluator sees it both A/B choices already converged into weird Claude pseudo English as that was baked in much earlier in training.
Don't worry. You'll get used to it. If you don't your kids will (as they'll know nothing else).
The top minds of our generation have decided that's the way things will be, and who are we to question them? It's not like it'll do any good anyway. Resistance is futile. There is no alternative.
I was similarly frustrated a few months ago, but have noticed I've started to learn the idiom.
Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it.
After a while it gets much easier to read and even becomes somewhat efficient, I think, since the odd metaphors it uses often have a precise meaning in Opus-ese (Fable speaks a really similar dialect).
…
No step here involves choosing based on meaning. It is a filter, a sort, and a slice.”
This is from Opus five minutes ago. I can certainly derive meaning from these kinds of statements in isolation, but paragraph upon paragraph of this is unintelligibly dense when trying to work with Claude to come up with a plan.
The worst part is that it can’t even make its responses make sense when asked to summarize in simple English or < 200 words. It simply cannot be steered to make its prose legible.
This dialect is idiosyncratic to you and Claude based on your session history and memory.
I've noticed Claude's output mimics my writing style.
> Registers the board implements but whose behaviour is not modelled
Right down to my preferred spellings.
As several comments I've read on HN suggest, this jargon which can be so precise in the mind of one person, tends to rapidly fall apart when multiple people try handling it.
It was British English.
I also find myself regularly editing its code comments, which do not match my expectations of succinct, clear, not over explained, etc. I ask it to read my edited comments to improve its writing, which has helped _somewhat_. (The code itself that it writes is decent, though it still overcomplicates things. I find myself writing "keep it simple" repeatedly even though of course I have it in AGENTS (which it regularly ignores, such as attempting to commit something when I've told it never to commit).
I find Claude has become very difficult to work with and incapable of writing clear documentation, even when directly prompted or provided samples.
As for code, I think each function requires 3-4 passes with Fable to actually get to a point I accept as good code. I am picky though.
The other Claudism that drives me crazy is when it writes comments and commit messages that track how you arrived at an decision instead of what it is.
yes, this is part of what I'm continuously removing from its comments; I've told it multiple times "that belongs in a ticket, not in the code" but to little avail :/
Same experience. It’s not very “human” but once you have agents talking to each other the shared dialect and verbosity makes things much smoother in my experience. Fighting against the default feels like an uphill battle with no meaningful benefit.
Two things to flag:
Sitting with you in this.
To avoid speaking vibe'ish I start to speak in 3 words sentences. Like this typical dialogue
How are you? that's not/very good. I think too. ...
Even complexity works. everything is expressible! Just try it.
/S
(Why down vote? People can't take sarcasm tags any more.. how the hell are they going to understand irony?)
- fuel tanks heavy. far too heavy. we drop them. drop when empty. solves heavy problem.
- gas in air. we breathe "oxygen". take with us. good seals important. solves breath problem.
- very far away. need big machine. small weight added. machine much bigger. take less weight. else can't build.
- no air there. can't use propellor. can't use wings. must use rocket. engines get hot. cool with fuel. dangerous but effective. build complex pipes. solves cooling problem.
- must fly fast. air slows machine. this called drag speed increases drag. must reduce drag. make machine pointy. much less drag. solves speed problem.
now problems solved. you come with?
But I have noticed that while "loosely held" is a convenient shorthand for uncertainty, I don't like that one slipping in to my daily language. Except maybe to communicate with models, but even then, it feels weird to be speaking in neuralese.
It's all starting to feel like the movie Arrival.
Now, I'll grant that those concepts weren't common outside of techy circles. Just clarifying that the LLMs are amplifying them, not synthesizing.
https://en.wikipedia.org/wiki/Grok
https://wiki.c2.com/?ChadwickBoggs
It's interesting then that LLMs are making these pre-existing ideas seem alien in the way they amplify them. I guess I must have known about "shape of a problem" and "loosely held" before Claude, but something about the way I'm using & absorbing those concepts from AI interaction feels weird & memetic. I'm saying that as someone who is pro-AI.
Definitely a good response. Thanks for replying!
But what I was more thinking about are truly unique jargon terms / phrases that get generated when deep in a problem. As an example of both of such a term and the phenomenon itself, Claude calls this "fluent compound coinage." They usually make sense in the original context, but get confusing when thrown around otherwise.
... not to mention the fact that it stops making sense, beyond some point: If it takes us more cognitive load to understand the tools we use, meant to save us from intellectual work, what's the point?
Ruthless pruning is unneeded with an LLM and it can take me twice the time to say half as many words.
And, early in the ‘GPT era, I hadn’t unchecked the “allow your chats to be used in future training etc” box, and definitionally they are longer and denser than others’ prompts in such raw scrapings of training materials…
Sorry.
And for certain text that seems to make sense, I am unsure if the text is just junk, or I am unbearably daft. Either way,, nasty feeling.
Right, but LLMs use one word where they need ten; by your own admission you do the opposite. I don't think you owe anybody an apology.
I think I need a break from Claude.
FWIW, I also think the constant chorus about how new models are worse than old models is a human hallucination. They're certainly not perfect but every one becomes more steerable in terms of actually completing more and more complex work.
No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation. No one cares that the implementation was planned in six phases and "Phase 3" will implement this interface in a concrete type. But the LLM internalizes absolutely everything and you have no idea that it is producing slop because you included some "load-bearing" phrase that sent it on some unwanted tangential vector in its latent space. And you will not be able to debug the problem with closed models because you cannot see it referencing this phrase in its internal traces.
I don't understand why this isn't the highest priority for the big labs to fix. This is anti-productive.
Worse: Possibly the three other approaches that weren't actually tried--but are the kinds that someone could easily have put in a similar comment for some similar code.
Still, this requires a second pass, typically. In its default-mode it often ignores the policies and does all the usual Claude stuff.
Some might, I didn't - it just filled me with a sense of frustration and rage, alongside disgust because there is no good reason for that slop writing to drag everything down. You don't need that to write software or talk about any topic. That's what pushed me to Kimi K3 and GLM 5.3 - still not ideal, but better.
I am definitely guilty of wondering why past me made such a harebrained decision, and why past me didn’t think to write any notes, but does it matter? It’s in the commit history and we can bisect or revert if we find a regression.
Or adding notes to docs of what this doc isn’t when I corrected it. Eg I told it “keep the deployment manual and readme separate, they’re not the same thing”, then Claude added “this is the deployment document and not the README. They should be handled as separate documents and are not the same thing” to the deploy doc lol
> "I frequently use Claude Code and often find the phrasing and language to be hard to understand. I've noticed it's largely broken down into frequently used 'Claude-isms'. I'd like to use this conversation as a running log to ask you about these phrases when I see them. Understandably you don't have the context of the Claude Code session itself, but that's okay because this is largely about understanding the most common and widely use Claude-isms."
And then I just copy and paste small except and ask about things like "smoke" or "load-bearing" or "tripwire". The responses are surprisingly clearly and plainly explained.
[1] https://www.themachinevernacular.net/
It's ironic how initially it was sold as "coding in plain English", and now we are back to sdk ))
Non-determinism at its finest.
So going to continue trying that as a command structure going forwards...
Okay, let's try it one more time! [..]
Believe the big services wouldn’t reply as if you were mentally diminished, or a toddler, unless you specifically asked for that: The whole training stack tends to instruct the things to mimic politeness and eagerness to help.
That and if you talked to the same one person's frozen brain upload all day, you'd see the same catchphrases used too.
Yes. agents.md does very little because prompts change the context and thus the initial path into/though but they don't/can't change the actual weights that control responses. Yes. of course it gets worse as the session goes on, assuming the prompt is even still in the context window, the further it gets away from it the less it affects next token selection.
This shit is only like 5 years old why can't anyone remember how it works
You can add your own. wfm
> hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief, produce subsequent summaries until the most recent summary attempt is digestible. second, if there is an open queue of actions for me to execute and you are about to end a turn to wait for a reply or this set of actions has not recently been mentioned, please tabulate the open actions i should take and why i should take them before ending the response. does this make sense or do you have any follow up questions
And now every message contains the same stuff I don't bother reading, but followed by a nicely formatted bullet point summary of the response and a table of follow up actions for me to take that I do read.
Sometimes the summaries feel totally alien to the task or code.
Claude somehow is unable to stop writing excessive comments when carrying out a task.
A maximum of 20% comment lines added to total lines added and pasting in https://devblogs.microsoft.com/oldnewthing/20260812-00/?p=11... has done wonders.
Even as the most Ant-pilled guy out there, I will take a moment to note that Codex on 5.6 models needs none of this...
When you see, “Wow, Fable is number one”, you might think it’s a good writer, but that’s not what the benchmark says.
Frequently its choice of a particular word is perfect and gives me the vocabulary to talk about the task at hand the way I want
Like it’s tuned to just be “maximally dense” instead of “dense/technical where you can handle it and simple where you can’t”
It doesn’t know where your language strengths/weaknesses are, so it can’t communicate to you like a fellow human does.
Claude: gedarkin load bearing phlox gabrania seam
It's just that the details it parrots are often irrelevant and wrapped in a way that makes them seem relevant.
I think it's because the reasoning stream shapes the style of the final output, and they optimized it for density, token efficiency. So it prefers to use more complex language, as a function of the rewards it was given?
Not 100% sure about this argument though (reasoning style -> final response style); Gemini Pro, back when reasoning tokens were public, was different, which was interesting -- it would have a very structured reasoning section, and then the final output was in a completely different style. (I strongly preferred the reasoning section because it was logical and easy to parse! And was very sad when they hid it...)
I also have no idea how useful a system prompt instruction like this will be for codex.
https://github.com/luchasarie/bro-skill
but I still can’t understand what Claude wants to say when solving complex problems.
I highly recommend it.
Claude and Codex usage limits cannot be trusted.
Paying your own API bills in full is superior.
Wish I could use my Claude subscription with pi too, much preferable to the endless command execution allow/deny prompts you have to do with CC, versus proper autonomous allow/deny lists defined ahead of time.
Curious why you recommend the API? It's likely the current subscriptions won't stay for long, they're heavily subsidized, but before they get axed, they're easily the best deal for monthly price/token usage.
There's an echo of that tension in OpenAI vs Anthropic. For a while OpenAI seemed reckless and ignorant, preferring to just throw compute at the problem. Meanwhile Anthropic is hiring philosophers. But now that Claude has its head up its ass to the point where nobody wants to talk to it. For me it's once again causing skepticism about just letting the ivory tower do its thing.
Watching the models seesaw in the same ways that humans do, but faster, is so surreal. I wonder if their tendencies will remain an echo of ours, or if they'll one day be more of a cautionary tale, a representation of where were going if we don't change our ways.