AI news for platform & agent engineers
Ranked signal · finite reading
One shared ranking. Scan what changed, save what matters, and stop when the finish line appears.
Ranked brief · refreshes every 2 hours
As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fre... Context & related coverage →
CodeScene has published a case study in which coding agents refactored 300,000 lines of C over three weeks for roughly $4,000 in tokens, verified by a frame-by-frame replay harness. The agents built a playbook of code... Context & related coverage →
We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Mythos Preview did s... Context & related coverage →
Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: diff... Context & related coverage →
the most confident DevDay yet. Context & related coverage →
Use Jev as a judge for LangSmith evals to evaluate agent traces with faster, cheaper structured feedback across production runs, datasets, and regression tests. Context & related coverage →
Training agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides a precise and structured formalism for specifying instructions to a... Context & related coverage →
GLM-5.3 can autonomously build end-to-end cyber exploits, but unlike other frontier models, it was released without meaningful safeguards to limit misuse. Context & related coverage →
Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and owne... Context & related coverage →
My comment on GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price — Hacker News. I'm a bit late with the pelicans because I was live-blogging the keynote: https://simonwillison.net/2026/Sep/29/openai-devday-... Context & related coverage →