Hacker News new | past | comments | ask | show | jobs | submit login

NN's absolute can go beyond what they have learned and aren't just producing the "average".

Some good examples outside the typical LLM/images work:

* Deep Mind's work on AlphaFold, which generates predictions on proteins that haven't been seen before

* AlphaGo which plays games better than any human (so clearly can't be "the average")

If we look at LLMs, something like writing code in the style of Shakespear isn't really something that's been seen before.




> Deep Mind's work on AlphaFold, which generates predictions on proteins that haven't been seen before

I have used AlphaFold a bit in my own work, and if I showed it 'unusual' proteins like rare mutants it usually generated garbage. Some evidence for this exists in the literature; see for example https://www.biorxiv.org/content/10.1101/2021.09.19.460937v1 or https://academic.oup.com/bioinformatics/article/38/7/1881/65... or

>AlphaFold recognizes a 3D structure of the examined amino acid sequence by a similarity of this sequence (or its parts) to related sequences with already known 3D structures

https://www.biorxiv.org/content/10.1101/2022.11.21.517308v1




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: