In the News: August 31, 2026
A controlled harness study finds structural constraints alone can hurt agent reproducibility until the plan step itself is schema validated.
Morning edition
Machine-readable
Download Markdown
Story
Schema-validated planning sharply improves reproducibility in a deterministic harness
Dhage wrapped two open models, Qwen-2.5-7B and Gemma-3-27B, in a harness of finite-state execution, forced tool selection, output validation and bounded retry, then ran each against two synthetic pipelines 100 times per condition. Against a…
Read story →
Story
Anthropic needed a second post to say plainly that Claude Code's weekly limits are dropping
Starting September 14, Anthropic is permanently raising Claude Code's standard weekly usage limits by 25 percent above the original baseline for Pro, Max, Team and seat-based Enterprise plans. That replaces the temporary 50 percent boost…
Read story →