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

How to stop Claude from saying load-bearing

jola.dev

Post reply on HN
Print view View original

81–90 of 650 posts

Re: How to stop Claude from saying load-bearing

#81

Post by orbital-decay »

jchook wrote: post #12

SillyTavern folks have been perfecting the unslop solutions for years now. Gotta be a way to draw from their progress.

There are no real solutions, it has to be fixed during the training. ST folks have tried many non-working ways over the years, but two workarounds are more or less worth considering:

- Samplers that increase prose variance. They require running the model locally, they dumb it down, and never fix the actual issue, which is mode collapse leading to semantic collapse and rigid mapping of input to output concepts. The model still expresses the same ideas in different words.

- Let the model write anything if it couldn't resist, but check and fix it in the verification pass. This solves the semantic problem, but cannot solve the variance since the second pass is also subject to rigid mapping, i.e. you replace it with the same stuff over and over. The verification prompt can be randomized to a degree using pretty clever schemes to give it some variance, but of course this also fails in predictable ways.

Re: How to stop Claude from saying load-bearing

#82

Post by yusefnapora »

p-e-w wrote: post #15
pocketarc wrote: post #11

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT. Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t…

> Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death I don’t get it. If nobody likes this writing style, how can it be the result of human feedback? Something else is going on.

It's not that nobody likes it, in fact the problem is that people like each instance of it well enough in isolation. Millions of people think it's "good enough," so it gets amplified and repeated until every PR description starts to sound like a toothpaste jingle.

Re: How to stop Claude from saying load-bearing

#83

Post by cindyllm »

anon373839 wrote: post #64
p-e-w wrote: post #15

Earlier quoted context omitted.

> Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death I don’t get it. If nobody likes this writing style, how can it be the result of human feedback? Something else is going on.

Because LLMs are pattern-extenders that have nothing to say. The training overfitted to the grace notes in good writing. And since LLMs can’t wield language with purpose or experience the feeling of the words, they use these devices arbitrarily. I think this is the same flaw as coding agents seeing in every problem the call for a “smoke test” or the use of some unnecessary design pattern. The truest part of AI is the…

[dead]

Re: How to stop Claude from saying load-bearing

#84

Post by chrisandchris »

bunderbunder wrote: post #52
Retr0id wrote: post #26

Earlier quoted context omitted.

> What, if anything, do people do for writing? I use a keyboard, personally.

Amen. At work our documentation isn’t just getting littered with annoying jargon. It isn’t just all the hallucinations, either. (Since when has documentation ever been 100% trustworthy?) It’s that it’s so poorly written and structured that it’s becoming borderline incomprehensible. My company is currently considering making, “Why should I bother to read something you didn’t bother to write?” an official policy becaus…

If it wasn't worth your time writing, it isn't worth my time reading.

Re: How to stop Claude from saying load-bearing

#87

Post by tpholland »

retsibsi wrote: post #68
dfc wrote: post #53

Earlier quoted context omitted.

What's the difference between the two usages?

"Belt and braces" (UK) vs. "belt and suspenders" (US). I'm pretty sure the phrases have the same meaning, they just use a different word to refer to the thing that holds pants|trousers up.

And the word "suspenders" in British English means what Americans would call a garter belt, hence it sounding particularly odd over here.

Re: How to stop Claude from saying load-bearing

#88

Post by lemontheme »

dintech wrote: post #37
hnarayanan wrote: post #34

I maintain a list of phrases I beg it not to use that it frequently ignores: - smoking gun - blast radius - landed - spine - earned its keep - grammar - spike - cutover - bake - sprint, epic, story points (all Agile vocabulary) - paper-cuts - amazing, incredible, perfect

‘Landed’ and ‘honest’ are also words it seems to overuse.

Claude is obsessed with making things land. More than once I've reminded it that it's not a pilot.

Re: How to stop Claude from saying load-bearing

#89

Post by drcongo »

tpholland wrote: post #87
retsibsi wrote: post #68

Earlier quoted context omitted.

"Belt and braces" (UK) vs. "belt and suspenders" (US). I'm pretty sure the phrases have the same meaning, they just use a different word to refer to the thing that holds pants|trousers up.

And the word "suspenders" in British English means what Americans would call a garter belt, hence it sounding particularly odd over here.

The US usage is much kinkier

Re: How to stop Claude from saying load-bearing

#90

Post by drcongo »

tpoacher wrote: post #13

Just ask it to aim for a Flesh-Kincaid ease-of-readability score of around 70. Or use ELI5 style. Or both.

Flesh Kincaid sounds like an excellent name for a Scottish porn star. I'd never heard of this, turns out it's Flesch, but thanks for the TIL!
Post reply on HN