IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
919 articles
04 Aug 2026 · 7 min read
ai-agents
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.
Read more03 Aug 2026 · 7 min read
english-lesson
Daily English practice for tech professionals. Morning session covering refactor, merge conflict, breaking change, rubber duck debugging, and how developers talk about code — with pronunciation guide, real exercises, and an idiom only devs use.
Read more02 Aug 2026 · 7 min read
english-lesson
Daily English practice for tech professionals. Sunday review session — consolidate the week's best words (deploy, inference, resilient, concise, negotiate, rapport), top idioms, and a spaced-repetition challenge to lock them in long-term.
Read more02 Aug 2026 · 7 min read
ai-agents
After PocketOS lost their production database in 9 seconds to a Cursor agent, and Replit destroyed 1,200+ executive records, the industry has enough post-mortems to see patterns. Here are the 7 failure classes, what each looks like in the logs, and concrete guardrail architecture for each.
Read more02 Aug 2026 · 7 min read
ai-productivity
Teams using AI coding tools generate 98% more PRs — and wait 91% longer for them to be reviewed. DORA data shows that for every 25% increase in AI tool adoption, team stability drops 7.2%. This is Amdahl's Law applied to software delivery, and the bottleneck isn't where most engineering leaders are looking.
Read more02 Aug 2026 · 6 min read
ai-agents
An ETH Zurich study tested AGENTS.md files across hundreds of real-world GitHub issues and found that LLM-generated context files reduce task success rates by 3%, increase costs by 20%, and add nearly 4 extra reasoning steps per task. Here's what actually works — and why less structured context is usually better.
Read more02 Aug 2026 · 7 min read
ai-agents
A Stanford, SambaNova, and UC Berkeley paper introduces Agentic Context Engineering (ACE) — a Generator-Reflector-Curator split that delivers +10.6% improvement on agent tasks and +8.6% on finance tasks, without any gradient updates. Here's what the architecture means for teams building production AI agents.
Read more01 Aug 2026 · 6 min read
english-lesson
Daily English practice for tech professionals. Morning session covering social English for networking — rapport, small talk, introductions, and keeping conversations alive — with pronunciation guide, exercises, and real-world examples.
Read more31 Jul 2026 · 8 min read
ai-agents
The July 28 MCP specification eliminates sessions, removes the initialize handshake, and makes every request self-contained. A technical breakdown of what changed, why it matters for load balancers and multi-tenant deployments, and how to migrate existing servers.
Read more
