Archive
Every issue, by week.
Filter by topic to find what you're looking for.
Issue 1 · May 4, 2026
Issue 1 — The week the agents grew up
Agent benchmarks finally start measuring something useful, three open-weights releases tighten the gap with frontier closed models, and a quiet paper from DeepMind reframes how to think about evals.
#agents#evals#infra#models#opensource#papers#policy#products#research#tooling#voice