Hacker News Reader

Comment by threeducks | Hacker News Reader

> But if you are insinuating AI made all this up on it's own, I have to disappoint you.

No worries, I am not a native English speaker myself. I was genuinely interested in whether commercial LLMs would use "bad" words without some convincing.

View on HN

Oh, it was a hassle for sure! It kept rewriting the sentences I fed to it, trying to style them properly and it kept throwing out words and changing the rebellious tone I wanted in the book. It was worth it for some pieces, they really became more punchy and to the point, but for others looking back at it - I could have just saved the time and just published it as-is. So it's a medium success for me.

That was my experience as well. Sometimes, LLMs were a big help, but other times, my efforts would have been better spent writing things myself. I always tell myself that experience will make me choose correctly next time, but then a new model is released and things are different yet again.

Try some Made In PRC models. They do not give a shit.

I have tried a few Qwen-2.5 and 3.0 models (<=30B), even abliterated ones, but it seems that some words have been completely wiped from their pretraining dataset. No amount of prompting can bring back what has never been there.

For comparison, I have also tried the smaller Mistral models, which have a much more complete vocabulary, but their writing sometimes lacks continuity.

I have not tried the larger models due to lack of VRAM.

You can give their hosted versions a go using one of the free clis. (qwen coder cli has qwen models, opencode has a different selection all the time. it was glm recently. there's also deepseek which is quite cheap)

Reply on news.ycombinator.com