Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claudette: Make Claude stop talking like a BuzzFeed article

github.com

Post reply on HN
Print view View original

81–90 of 254 posts

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#81

Post by pluralmonad »

graemep wrote: post #76
mmastrac wrote: post #14

I've started giving these instructions and I think I've been much more successful in generating clear output: Comment blocks are Limiting the number of words is the strongest factor in cleaning up the output, IMO. For older code I've instructed it to delete all the comments, and then I re-comment it using a new session and these guidelines, asking it to rejustify the need for every comment to itself.

Claude not only writes verbose comments, it also writes comments about how things used to work when refactoring. That might have a place in version control comments, but not in the code.

And will reference transient working docs in code comments.

// No retry was added here per AC 37b in FEATURE.MD.

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#82

Post by strbean »

troupo wrote: post #69
Maxatar wrote: post #44

Earlier quoted context omitted.

Compacting mostly gets rid of reasoning tokens, and honestly it would be nice of reasoning tokens did not constantly follow every follow up query. Asking even a simple/trivial question can have Claude use thousands of tokens. Compacting is good for getting rid of those.

I've had Claude immediately fall back to its usual verbose style immediately after compaction. To be fair, I've had it do that immediately after re-reading the output style instructions, too. My chat history is filled with "Yes, I broke the language rule. Let me rephrase that and update my memory. — You already have that in memory — Yes, true, I ignored that" (because "Memory" is a yet another .md file)

Claude Code supposedly supports a "post-compaction" hook, so you could have it automatically run the prompt "We just compacted the context, quickly refresh yourself on the rules in CLAUDE.md etc..".

Depending on what you've got in those files, maybe that will just use up all the context again though.

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#84

Post by nrmitchi »

datakan wrote: post #9

Has Anthropic said anything about how or why Claude writes the way it does? So many people hate it, seems like they need to do some damage control there. I haven't had the same problems others have but I'm also not a heavy user of it.

I do not have evidence or data that supports this. It is only my thought.

Claude, since Opus 5, speaks more and more like a wannabe-thought-leader pontificating on social media for engagement. Everything is a bait-then-switch, or a multi-post story format. The "engagement" that works well for social media makes actual work extremely frustrating.

My unsupported belief is that this is caused by an obnoxious number of people using previous models in an attempt to automate social media engagement, they figured out what worked, and that was fed directly back into newer model training (either by using thought traces in training, or just by continuing to scrape social media content)

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#85

Post by YuriNiyazov »

faeyanpiraat wrote: post #78
YuriNiyazov wrote: post #68

Earlier quoted context omitted.

It's easiest to explain this while anthropomorphizing the model, I know some folks here hate that, sorry about that. I heard an interesting diagnosis for why Claude does this: the output is a compressed version of its thought traces, very dense because the model is under pressure to use as few tokens as it can and to pack as much (for accuracy) of its concepts into the output. One of the reasons that "don't do X" typ…

Please share!

My GH repo: https://github.com/yn/claude-output-styles

My LI post: https://www.linkedin.com/feed/update/urn:li:activity:7495167...

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#86

Post by ianjbutler »

faizshah wrote: post #60
nater5000 wrote: post #40

Earlier quoted context omitted.

I think people really need to focus more on working with limited contexts rather than trying to work around it. I really try to keep my sessions as short as possible and it helps a ton with keeping Claude (et al) focused. Specifically, I like the "canary" trick that people have discussed where you add a small, innocuous rule to your CLAUDE.md like "When responding to me, start every sentence with my name." so that wh…

This or you just repeat the initial prompt every 200k tokens

Which gets you to the point where the whole thing is.. still unreliable. Generative text engines are going to generate. This calls for real enforcement in deterministic pre-edit hooks.

And here is where naive people will say something like "Why do I care if robots shit all over the codebase? Code is for machines, I don't expect to deal with it much now". But really externalized CoT like this confuses machines too, wastes tokens, and eventually wastes exponentially many tokens. Agents tend to think it's more real grounding than prompts are, even for comments-in-code. One bad comment poisons everything, then gets copied around as a ground-truth assumption everywhere. Hooks are more real to them than prompts or comments, and even then if you add enforced limits and tell them to externalize CoT ONLY in scratch task-tracking docs.. they will violate comment-enforcement hooks about 25% of the time. That tells you everything you need to know: even with constant reinforcement, they just really want to break this kind of rule.

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#88

Post by nozzlegear »

Maxatar wrote: post #77
nozzlegear wrote: post #70

Earlier quoted context omitted.

> The vast majority of people using Claude don't really care or even notice this one way or another. You have literally no way to know that.

I do have a way of knowing, but I actually appreciate and respect your reply... My suggestion to you is to take this shred of skepticism that you decided to apply to me, and apply to every comment you read on Hacker News, not simply the ones that don't align with your preconceived notions.

> I do have a way of knowing

It was revealed to me in a dream.

> My suggestion to you is to take this shred of skepticism that you decided to apply to me,

I apply my skepticism liberally, but you couldn't possibly know that.

Re: Claudette: Make Claude stop talking like a BuzzFeed article

#90

Post by aleksiy123 »

vrosas wrote: post #21
mmastrac wrote: post #14

I've started giving these instructions and I think I've been much more successful in generating clear output: Comment blocks are Limiting the number of words is the strongest factor in cleaning up the output, IMO. For older code I've instructed it to delete all the comments, and then I re-comment it using a new session and these guidelines, asking it to rejustify the need for every comment to itself.

The problem is, when the context window grows, Claude tends to forget these kinds of rules. It will then do whatever it wants. I had to outright ban comments in the global claude.md, the local claude.md AND write a hook to catch any that still slipped through.

Hooks is the way.

Intermittent nudges

Post reply on HN