Loved hearing @clefourrier on @latentspacepod on missing in current LLM benchmarks! In particular Calibration - In QA contexts, how calibrated are the log likelihood probabilities for the correct answers? This is key for "measuring hallucination" in LLMs, and defo the way forward
- 1 reply
- 0 recasts
- 0 reactions
@dwr is there a typefully - esk tool for casting in farcaster? I feel like it would help a lot
- 0 replies
- 0 recasts
- 0 reactions
Powerful tech communities and my impression on what they're good at: Runescape -> Bots & Infra Furries -> Computer Networking Minecraft -> AI/ML Femboys -> System Architecture / Cybersec Touhou -> Math Eastern Europe -> Competitive Programming Any missing?
- 0 replies
- 0 recasts
- 0 reactions