Live data from Hacker News

AI doesn't know how to forgive and cannot forget

tejassuds.com

21–26 of 26 posts

Re: AI doesn't know how to forgive and cannot forget

#23

Earlier quoted context omitted.

Not that it's an ideal solution, but you have all the tools you need to do something about it. You can put all your preferred writing style guidelines into an LLM and have it ingest and rewrite any text you dislike.

That's like saying a robot will be a better friend if I use a more skin-like material for its face. The LLM-voice revulsion isn't just about particular idiosyncrasies. Another commenter put it well - the "uncanny valley of text".

Only if the problem is ideological, ie. you don't like the "idea" of llm's. But if in fact your actual dislike is the style of writing, then you can simply change the defaults. It's pretty easy to make a llm conform to your preferred style, avoid the use of em-dashes, or reduce verbosity, etc.

Re: AI doesn't know how to forgive and cannot forget

#25

Earlier quoted context omitted.

[flagged]

You LLM-generated this comment too. What about you (the human, if there is one behind this account) -- what do you think? If you don't speak English, write it in Hindi and use google translate. That will be much preferable to something written by an LLM.

Wanted to say I am with you 100% here. I'd bet my dingly doo on it being pure LLM. As well as the others. My question is how can this shit be kept out of here and elsewhere... This example is easy to catch, others less so.

I almost don't want to discuss the tells, because they'll immediately be ingested into training.

I can understand someone wanting to test or play around a bit, but this could obviously become a serious problem, not to say it hasn't already, but I don't pay deliberate attention to it.

HN policy actually makes it a violation to call this shit out, technically. I suspect they will make exceptions.

Post reply on HN