Fetching from the wire…
Public story · 2026-03-12 · source-backed
LLM as post-hoc critic for step-level Q-values. +7.7% WebShop, +13.8% ALFWorld over GRPO. Third paper in the online RL-for-agents cluster this week. arXiv:2603.08754
Each link below shares sources, entities, or timing with this story.
After 20+ years maintaining Paint.NET, Rick Brewster concluded WINE's Direct2D would never be complete enough for what he needed, so the app now carries its own from-scratch reverse-engineered Direct2D implementation. He puts it at 180,000 lines against 700,000 for the rest of...
Allen Bargi's August 15 post hit 302 points arguing that AI collaboration rewards context-sharing, examples, and feedback over precise instruction (Hacker News). The pushback holds that the piece conflates management with leadership. mikeocool calls it "the most low effort ver...
SkillPyramid extends Voyager-style libraries with a hierarchical topology plus a self-evolution loop, raising average reward 38% and cutting execution steps 27.7% across ALFWorld, WebShop, and ScienceWorld. The takeaway: don't append every successful trajectory as a new flat s...
40. HBR — AI intensifies work 41. Import AI #441 42. Simon Willison — AI hit piece 43. Cameron Wolfe — GRPO++ 44. CISPA — Moltbook study 45. arXiv — SkillRL 46. Google DeepMind — Gemini 3 Deep Think 47. OpenAI — Codex-Spark 48. Zhipu — GLM-5 ---
Satya Nadella said companies routing everything through a single proprietary lab may not survive. His argument: you hand that lab your most sensitive business context, and the lab can turn it against you as a competitor. His prescription is an orchestration layer — keep the ha...
Willison launched datasette-apps (0.1a2) on June 18, hosting self-contained HTML+JS apps in a sandboxed iframe that run SQL against your data, read-only by default. He frames it as "Claude Artifacts reimagined for Datasette," artifacts backed by a JSON API to a relational data...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.