Fetching from the wire…
Agents2026-09-25 · source-backed
arXiv 2609.30055 generates companies whose key facts are never stated and are contradicted by the obvious record, like a CRM logging a lost deal as "timing" when the call recording blames an outage. The best agent managed 18 of 24 attempts, four of six models managed at most 6 of 24 under any harness, and questions requiring the right one of several similar records, which renewal offer was actually signed, came out correct in 1 of 84. Answers are code-computed, so no LLM judge. Enterprise agents that read only the structured record will confidently repeat the record's lie.
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...
Simon Willison released it August 4, calling it "the most significant new version since the initial launch of the project," which from him is not marketing. The agent-relevant pieces: tools can raise llm.PauseChain to stop for human approval, and chains resume from pending cal...
Riffing on Apple's DRI management concept, he argues accountability requires an entity that can actually be held responsible, and a machine cannot (Simon Willison). It's a sharp, quotable counterweight to the "let the agent own it end-to-end" enthusiasm. I keep this one close...
0.35 adds gpt-6-astra to the CLI's OpenAI provider, so llm -m gpt-6-astra works against the same logging, template and fragment machinery as every other model in the tool. For anyone scripting cross-model evals, that means a new frontier model needs zero new plumbing to enter...
READ (arXiv 2608.06305, submitted August 6) took a 780-page government financial report and asked 51 verified questions. Top-k embedding retrieval answered 15.7% of them correctly. The same agent loop, given three deterministic tools over MCP instead of a vector index, answere...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.