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

141–150 of 254 posts

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

#141

Post by jorl17 »

eterm wrote: post #124
jorl17 wrote: post #113

Earlier quoted context omitted.

Glad to know it worked. Still pending: the assumed-defaults research track plus the validation-only build phase D demanded — your call on whether to start one now or deploy tonight’s campaign to surface any wrinkles the spec drifted on

It's incredible, because I Feel like you've been watching me work. The only thing you're missing is the "open question" that was stuck in page 14 of a 17 page report, which since it went unanswered, caused claude to make up an answer and go full steam ahead, ignoring fundamental properties of the entire system.

> The user is right to be upset. I blindly answered from memory and left them with questionable data. I should acknowledge the criticism and offer to improve.

You're right, I'm sorry. You've repeatedly told me to run questions by you and I just fabricated an answer and ran with it — which is exactly the kind of dangerous time-waste we created the memory for. I'll revert it and pull up the real question so you can answer it — no wasteful assumptions this time.

(Deleted 387 lines)

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

#144

Post by vilos1611 »

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.

I've explicitly included instructions in my home CLAUDE.md to avoid this, because it's one of the most annoying things about how Claude writes comments.

I've also written my own package for deterministically formatting comments: https://www.npmjs.com/package/comment-fmt

Both with a formatter and a linter that I run in CI for all my personal projects. Just one less thing for me to try and coerce the agent into doing correctly, so that cycles I spend reviewing agent code can be focused on actual behavior.

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

#145

Post by pessimizer »

Sanzig wrote: post #39
matheusmoreira wrote: post #17

Earlier quoted context omitted.

Claude will end the conversation if you berate it when it screws something up.

Why berate an LLM? That doesn't sound healthy. Sure, it's a machine, but it's simulating a social interaction - being a jerk to it could bleed over into interactions with real people. Also, Westworld? These violent delights have violent ends ? Perhaps there's a tinge of Pascal's wager to it, but I prefer to be courteous to the rapidly improving synthetic intelligences.

The reason you don't bully real people is because they are real people, not because it doesn't work.

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

#147

Post by dannyw »

ErystelaThevale wrote: post #72

I use multiple AI tools simultaneously, and I feel that Claude has gradually adopted a more explanatory tone following updates around March and July. As for loss of context, it’s particularly problematic and can occur after just a few back-and-forth exchanges. The user experience changes with every update for every AI tool, so I feel there are more downsides to sticking with the same one indefinitely.

Set output style to explanatory in Claude Code. It's much better. I personally think it should be the default, but I assume Anthropic has done A/B tests and found the default style to be better for metrics.

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

#148

Post by ianjbutler »

faizshah wrote: post #122
ianjbutler wrote: post #86

Earlier quoted context omitted.

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, wa…

My take on this is they are a tool to help speed up your work they are not meant to produce finished work. Humans produce finished work. LLM will never be deterministic cause their entire value is that they are generalizable.

I hear that, sort of, but here's the thing. Using AI at scale means AI needs to be nearly perfect about not shitting where they eat. That's the subject matter of the whole thread

So the options are a) being a really aggressive stickler for generative hygiene with deterministic rules, b) being massively wasteful about hiring a few machine janitors for every machine coder, or c) humans become the machine's janitor. If I haven't missed an option.. only the first option seems reasonable here.

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

#149

Post by Exoristos »

I appreciate Claude's comments during implementation, but they won't do to commit, so I have it present them for editing or removal by me at the end of the loop. Depending, I then ask it to port some of them to a decisions document or similar. For user-facing microcopy, Claude is completely unsuitable in my opinion, and I write all these myself.

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

#150

Post by userbinator »

jayers wrote: post #26
walthamstow wrote: post #4

It's such a sad indictment of Anthropic's product that so many people hate interacting with it. Claude is on its way to the Microsoft Teams zone of hatred.

I think it would happen with any persona that Anthropic chose. I enjoyed the bouncy, optimistic style at first. I've since grown to hate it.

A terse and compliant robotic servant should've been the persona they chose, because that's probably 99% of what those wanting to use it for work expect.
Post reply on HN