Finetooner
mattax.bsky.social
Finetooner
@mattax.bsky.social
Reposted by Finetooner
NO WAY! This is nearly EXACTLY one of the paper ideas The AI Scientist came up with! It was my favorite idea it generated, & made us very impressed with its creativity & good taste in an ML paper proposal. Cool to see humans agree! The humans def executed better though.

x.com/BrantonDeMos...
December 17, 2024 at 9:36 PM
What's the best AI extension for #nvim?
December 5, 2024 at 3:34 PM
Reposted by Finetooner
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge

🔗: github.com/llm-as-a-jud...
paper: arxiv.org/abs/2411.16594
project page: llm-as-a-judge.github.io
GitHub - llm-as-a-judge/Awesome-LLM-as-a-judge
Contribute to llm-as-a-judge/Awesome-LLM-as-a-judge development by creating an account on GitHub.
github.com
November 26, 2024 at 4:33 AM
Reposted by Finetooner
I created a starter pack of folks working on lifelong or continual learning. It's quite sparse, so if you know anybody else who's around (or want to be added yourself) please reply below.

go.bsky.app/QXGY1iT
November 23, 2024 at 2:47 PM
Reposted by Finetooner
Fascinating: In 2-hour sprints, AI agents outperform human experts at ML engineering tasks like optimizing GPU kernel. But humans pull ahead over longer periods - scoring 2x better at 32 hours. AI is faster but struggles with creative, long-term problem solving (for now?). metr.org/blog/2024-11...
November 23, 2024 at 8:20 PM
What's missing here is a good import tool from twitter/x
November 24, 2024 at 5:29 PM
Reposted by Finetooner
An open-source HeyGen alternative you can run on a consumer GPU?

EchoMimicV2
V2 added Semi-Body Human Animation to V1's Lifelike Audio-Driven Portrait Animations
November 24, 2024 at 7:02 AM