Loading activity…
@alexbarry4
Statistician working on understanding AI Capabilities | Epoch AI Substack: https://abstatisticalconsulting.substack.com/
AI
Epoch AI labels nine of its initial 15 benchmarks “Flawed” and four “Verified,” with insufficient information to review two. A Terminal Bench contributor questions the audit’s rigor.
AI
A user sharing the update says the lower score is still within the uncertainty range they expected.
AI
Pseudonymous commentator @scaling01 connects several scaling forecasts in one post.