Addendum: as portions of my text above have been quoted out of context, I would like to also draw attention to the various caveats listed at https://github.com/teorth/erdosproblems/wiki/AI-contributions-to-Erd%C5%91s-problems regarding the extent to which one can draw broader conclusions about AI mathematics capabilities from the progress in solving Erdos problems.
Today also enjoyed reading this post that explains beautifully, some alike approaches, challenges, and quality assurance measures, but instead when using #LLMs #vibecoding #GenAI for #softwareengineering in corporate regulated domains solutions:
, Here’s the nuance: while generation is probabilistic, the produced code can still be deterministic once compiled and executed — if we enforce the right controls.’
by #AjitPatil
If you have a fediverse account, you can quote this note from your own instance. Search https://mastodon.social/users/teixi/statuses/115873441818426892 on your instance and quote it. (Note that quoting is not supported in Mastodon.)