Google's live from Paris event private/deleted immediately • Hacker News Board

Post by telotortium » Sat, Feb 11, 2023, 2:10 AM UTC

jerf wrote: post #390

Jensson wrote: post #389

Earlier quoted context omitted.

You don't remember where you learned the things you know from? How can you trust anything you think then? Can such people get anything done at all, seems basically impossible to learn new things then since you can't know if it is better than what you thought before? So I don't think that remembering sources is a hard problem to solve, likely making the AI work well is probably easier if it remembers sources.

I don't think remembering sources is an intrinsically difficult problem. I think it's hard for language models , and indeed, after further thought, I'm pretty sure they shouldn't remember sources: https://www.jerf.org/iri/post/2023/understanding_gpt_better/ But the problem in general is probably not a particular stopper. A bigger problem is people thinking that we should be taking language models and using them as AI…

Steve Hsu has recently claimed[1] to have started a startup in stealth to solve the hallucination problem over a corpus as large as 10,000 pages of dense, college-level textbooks, to the point where it can answer the end-of-chapter questions in the textbook with almost 100% accuracy (albeit not math questions) - I hope without using the answer key. Not sure if their approach is more robust than Supabase[2] or similar approaches, and no indication of whether it might scale up to something on the order of a search engine corpus, but it's something.

[1] https://www.youtube.com/watch?v=peHkL_MaxTU&t=1558s [2] https://news.ycombinator.com/item?id=34695306