I'm not a ML researcher but got a bit nerd-sniped by OAI new parameter-golf challenge
I setup my pi-autoresearch loop on it, of course.
I asked my clanker to do some research about all related papers that could help it come up with better ideas etc
It ended up making this Knowledge Base
it's nothing revolutionary, mostly notes and links to related papers.
i hope its useful to some
https://t.co/GEy5OMfHi3
also if you have any feedbacks or ideas hmu
yeah makes total sense would only give you shit about it if you were fully vc funded etc and using it as marketing bait (many such cases) but just having another great effectts codebase available for my agents to get good patterns from is immensely invaluable to me, also FSL lets you tun maple internally just fine. Asking to not compete with you directly is totally fair imho
I'd say Effect currently benefits from not being mainstream, there's a lot of great quality content, and the main people spearheading it have great test.
I'm not saying this as a negative thing, Maybe its a mainstream niche right now. I dont think it needs to ever be as "mainstream" as react is, for example, for it to succeed.
if software is spec, what if we got AI to make specs that weren't slop?
working on this
(very inspired by the beauty of https://t.co/Ay6AdyvOm8 by @danhollick)