Hacker News new | ask | show | jobs
by Rohansi 107 days ago
It's relevant for data it hasn't been trained on. LLMs are trained to be all-knowing which is great as a utility but that does not come close to capturing an individual.

If I trained (or, more likely, fine-tuned) an LLM to generate code like what's found in an individual's GitHub repositories, could you comfortably say it writes code the same way as that individual? Sure, it will capture style and conventions, but what about our limitations? What do you think happens if you fine-tune a model to write code like a frontend developer and ask it to write a simple operating system kernel? It's realistically not in their (individual) data but the response still depends on the individual's thought process.
2 comments
esafak 107 days ago
I don't know if LLMs are trained to imitate sources like that. I also don't know what would happen if you asked it to do something like someone who does not know how to do it. Would they refuse, make mistakes, or assume the person can learn? Humans can do all three, so barring more specific instructions any such response is reasonable.
link
Rohansi 107 days ago
> Humans can do all three, so barring more specific instructions any such response is reasonable.

Of course, but reasonable behavior across all humans is not the same as what one specific human would do. An individual, depending on the scenario, might stick to a specific choice because of their personality etc. which is not always explained, and heavily summarized if it is.

link
simianwords 107 days ago
>If I trained (or, more likely, fine-tuned) an LLM to generate code like what's found in an individual's GitHub repositories, could you comfortably say it writes code the same way as that individual? Sure, it will capture style and conventions, but what about our limitations? What do you think happens if you fine-tune a model to write code like a frontend developer and ask it to write a simple operating system kernel? It's realistically not in their (individual) data but the response still depends on the individual's thought process.

Look, I don't think you understand how LLM's work. Its not about fine tuning. Its about generalised reasoning. The key word is "generalised" which can only happen if it has been trained on literally everything.

> It's relevant for data it hasn't been trained on

LLM's absolutely can reason on and conceptualise on things it has not been trained on, because of the generalised reasoning ability.

link
Rohansi 107 days ago
> LLM's absolutely can reason on and conceptualise on things it has not been trained on, because of the generalised reasoning ability.

Yes, but how does that help it capture the nuances of an individual? It can try to infer but it will not have enough information to always be correct, where correctness is what the actual individual would do.

link