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

341–350 of 650 posts

Re: How to stop Claude from saying load-bearing

#341

Post by sushid »

esikich wrote: post #281
infogulch wrote: post #254

LLMs are far from great writers. They struggle to form long coherent sentences and lean on punctuation like emdash and semicolon to ensure grammatical correctness when splicing together short phrases. This makes me wonder if the reason why agents love weird punctuation is because the labs run the base models through a RL training step that forces them to correct their grammar; but instead of rewriting short spliced s…

They are great writers if you tell them what you want. If you're unable to properly articulate the writing style you would like as you would a software spec, well, garbage in, garbage out.

Are there any skills or publicly available repos that do what you claim here? I would love to learn to have it write better.

For me, my amateur attempt is having another LLM do a review loop to remove clearly offending phrases and a heuristic eval to change sentence structures to be more similar to mine, THEN my manual HITL loop to rewrite ~20% of the sentences anyway.

Re: How to stop Claude from saying load-bearing

#342

Post by zahlman »

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.

Because you can't actually do "good writing" by repeatedly applying the supposed idioms thereof. The tiny subsegment of humanity responsible for the RLHF don't necessarily have any good taste for writing; but even if they did, it's orders of magnitude harder to communicate than to make judgments of short samples, and communicating it by making those judgments is surely impossible.

Edit: I see that you got multiple replies all basically saying the same thing in very different words. There's an exquisite irony to that, I think.

Re: How to stop Claude from saying load-bearing

#343

Post by cindyllm »

zahlman wrote: post #339
antonvs wrote: post #275

Earlier quoted context omitted.

> I want the ability to shame and discredit anyone passing the job of prose to a machine. What about people who don’t speak your language well?

I've dealt with many people by now who would copy and paste from an LLM for that exact reason, typically entirely unaware of how obvious it was that the result came from an LLM with no style guidance, and of course completely lacking any ability to verify that their intent was faithfully conveyed. I would rather learn their language than continue interacting like that.

[dead]

Re: How to stop Claude from saying load-bearing

#344

Post by jldugger »

esseph wrote: post #276
ReactiveJelly wrote: post #229

Earlier quoted context omitted.

I asked it to remove "honest" from a draft once. "Why say honest? We're talking to our coworkers. We would always be honest." I'm going to look for prompts or skills that can train it in technical writing but I'm warning the AI enthusiasts in my company that its first drafts of code and prose are low-quality, you have to hold it to a high standard yourself. I actually took a single technical writing class in college…

> "Why say honest? We're talking to our coworkers. We would always be honest." I grew up in the US South where starting or ending a sentence with "honest/honestly" was very common. Because of behavioral / cultural norms, you might be very openly friendly with big smiles around a business customer that really grates on your nerves, or very openly nice to a neighbor that you really wish would move away and take their 3…

There's a difference between how you describe using "honestly" and how claude seems to prefer tokens like "honest" and "load-bearing." An example from some coworkers attempting to replace product managers with Claude.

> Deliberately avoid a heavyweight "alert governance" process; the lightest recurring check that keeps FP-rate honest is the right dose.

And one for load bearing:

> Five open questions still stand; the load-bearing two are the runbook-AC contradiction (ratify "high-priority set only") and pinning the "high-priority set" definition + SLO source-of-truth before Milestone 3 (small-sample noise on a low-traffic fleet).

Re: How to stop Claude from saying load-bearing

#345

Post by cozzyd »

jchw wrote: post #213
infogulch wrote: post #202

Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…

I think it might be even worse. LLMs seem to get tragically stuck on certain patterns. Maybe it's partly because a pile of weights essentially always starts from scratch in the same condition, but even within a single conversation, it will literally just latch onto words and repeat them incessantly, to the point where it becomes annoying. So for example, current Claude models love "honest". They are always producing…

you should be careful about the times it doesn't say honest!

Re: How to stop Claude from saying load-bearing

#346

Post by reaperducer »

mook wrote: post #293
reaperducer wrote: post #252

Earlier quoted context omitted.

use the wrong phrasing and suddenly you can create your own word of the day for an AI model. I have a delightful time poisoning my company's AI system this way. I invented my own word that sounds perfectly cromulent† to an ordinary person, and any brain that's read a book learns how to infer meaning from context, so it's not a problem. When I get a e-mail response from a coworker using my special word incorrectly, th…

I don't see how you can tell it's AI, instead of just your co-workers having no respect for language. See: management-speak using "double-click".

Because of the use of the specific word that I made up. No human being would send it back to me.

Re: How to stop Claude from saying load-bearing

#347

Post by overtone1000 »

jbs789 wrote: post #316
esseph wrote: post #276

Earlier quoted context omitted.

> "Why say honest? We're talking to our coworkers. We would always be honest." I grew up in the US South where starting or ending a sentence with "honest/honestly" was very common. Because of behavioral / cultural norms, you might be very openly friendly with big smiles around a business customer that really grates on your nerves, or very openly nice to a neighbor that you really wish would move away and take their 3…

If I’m having a convo with someone and they drop in “honestly” I immediately discount everything else they’ve said, and what follows. Sometimes people use it reflexively and doesn’t carry the same meaning (for me).

This reaction is surprising to me because the previous comments about its utility seem so obvious to me. I also grew up in the US south where this is often used as a filler word. The other use I observe is as a cushion for a statement that may be unwelcome or hurtful. Perhaps this is proprtional to the frequency of courteous little white lies and rhetoric that uses disengenuity for emphasis or comical effect.

"Honestly, mom, I've never liked your fruitcake. I just ate it to make you happy."

"That's why you're my favorite child! Do you want another piece?"

"I'd love one."

Re: How to stop Claude from saying load-bearing

#350

Post by abirch »

doctoboggan wrote: post #309

I do not mind when I am coding with Claude and it uses all the typical claudisms. I am much more bothered when I am reading a blog post, email, or other form of prose and I see those same claudisms. I guess they are not annoying since I know I am talking to an LLM and expect the typical responses. When I am reading prose online that I previously would have expected a human to write, it can be quite jarring to realize…

I'd love it if companies had to disclose the percent of Private Equity ownership and online work disclosed the percent of AI creation.
Post reply on HN