Fetching from the wire…
Public story · 2026-02-21 · source-backed
A new arXiv paper introduces PCAS (Policy Compiler for Secure Agentic Systems) — deterministic policy enforcement for LLM agents that models system state as a dependency graph and enforces policies via a reference monitor. On customer service tasks, PCAS improved policy compliance from 48% to 93% across frontier models with zero violations in instrumented runs. This fills a critical gap: prior work focused on threat modeling, while PCAS provides actual enforcement with measured results.
Each link below shares sources, entities, or timing with this story.
Policy Compiler for Secure Agentic Systems introduces deterministic enforcement — a reference monitor intercepts all agent actions and blocks violations before execution. Compliance jumps from 48% to 93% across frontier models with zero violations in instrumented runs. Directl...
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...
Simon Willison highlighted Sophie Alpert's short internal policy on AI-assisted writing, whose load-bearing rule is accountability: "You must stand behind every idea and every sentence in your docs," because you can't excuse a bad passage by blaming the LLM, and doing so waste...
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...
GPT-5.6 Luna went to $0.20 input / $1.20 output per million tokens on July 30. That's an 80% cut. Terra dropped 20%. Luna's input now undercuts Gemini 3.1 Flash-Lite ($0.25/$1.50) and sits at one-fifth of Claude Haiku 4.5's $1 input. Simon Willison covered the announcement and...
Simon Willison shipped a PauseChain exception to cleanly pause a tool chain for human approval, guaranteed unique tool_call_ids (synthesizing ULIDs when providers omit them), and resume-from-history support. He says Fable produced the API design, tests, and docs across both LL...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.