IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

2 articles

03 Oct 2026 · 4 min read

agents

950 Agents, 21 Hours, 210M Tokens: What Anthropic's CRISPR Search Actually Proves About Fan-Out

Anthropic's life-sciences lab ran 950 agents in parallel to surface a possible new CRISPR-like enzyme system. The funnel math is a genuinely useful fan-out pattern — but the scientist pushback is the part worth reading closely.

04 Aug 2026 · 7 min read

ai-agents

OpenAI Astra Solved 10 Open Math Problems — And the Real Lesson Is About Trust

Astra cracked a decade-old Erdős conjecture and published Lean-verified proofs on GitHub for $2,000 of compute. Fields Medalist Timothy Gowers called one proof Annals-worthy. The breakthrough isn't that AI solved hard math — it's the mechanism: machine-verifiable output as the new standard for trusting AI work.