How to stop Claude from saying load-bearing • Hacker News Board

Re: How to stop Claude from saying load-bearing

#21

Post by Wowfunhappy » Tue, Jul 14, 2026, 12:12 PM UTC

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 humans do like it, in reasonable quantities. The AI overlearns this and does it too much.

Re: How to stop Claude from saying load-bearing

#22

Post by mchinen » Tue, Jul 14, 2026, 12:12 PM UTC

I enjoyed this.

I'm surprised there's no LoRa layer or auto RL or adversarial step to reduce the stock phrases as they pop up. Is it really so hard to push these out? Or is it just whack-a-mole no matter what you do?

Re: How to stop Claude from saying load-bearing

#23

Post by jappgar » Tue, Jul 14, 2026, 12:13 PM UTC

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.

every one-hit wonder asks the same question.

we liked it until we didn't.

Re: How to stop Claude from saying load-bearing

#24

Post by itopaloglu83 » Tue, Jul 14, 2026, 12:13 PM UTC

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.

Maybe it’s the dead internet.

All the bots and other LLMs providing feedback, so in reality it’s reflecting the reality in a sense.

Re: How to stop Claude from saying load-bearing

#25

Post by Bawoosette » Tue, Jul 14, 2026, 12:14 PM UTC

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.

For "agentic use and coding," they are trained to take useful actions, not produce desirable natural language writing.

Re: How to stop Claude from saying load-bearing

#26

Post by Retr0id » Tue, Jul 14, 2026, 12:14 PM UTC

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…

> What, if anything, do people do for writing?

I use a keyboard, personally.

Re: How to stop Claude from saying load-bearing

#27

Post by Wowfunhappy » Tue, Jul 14, 2026, 12:14 PM UTC

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…

For what it's worth, Anthropic seems to be keeping Opus 3 available on claude.ai, perhaps for this reason, so you're free to use it if you want to.

Re: How to stop Claude from saying load-bearing

#28

Post by mapmeld » Tue, Jul 14, 2026, 12:14 PM UTC

foo-bar-baz529 wrote: post #7

Is this a belt-and-suspenders solution?

This is the worst one for me. I can maybe think of what it means, but I never heard it before, and could easily be imagining a meaning.

Some of the other Claude-isms (quickly googling, especially 'gate' and 'canonical') I feel the issue is they sound right, but aren't specific enough to why we are doing something.

Re: How to stop Claude from saying load-bearing

#29

Post by hnarayanan » Tue, Jul 14, 2026, 12:15 PM UTC

rbinv wrote: post #9

joren- wrote: post #5

I'll make sure that the script is idempotent.

Great thinking on your end! I will run the smoke-test once you're ready.

I might need to do a spike as this is a core part of the spine. I will verify it and let you know when it's landed.

Re: How to stop Claude from saying load-bearing

#30

Post by michelb » Tue, Jul 14, 2026, 12:15 PM UTC

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.

i hate it, but plenty of people DO like it and plenty of people talk and write like that. It’s just corpspeak, being used a lot in the valley and beyond. And all upcoming hustlers running startups now feel the need to speak like that, feeding this machine.