Skip to content

Daily · Oct 10, 2026

Claude can run 1,000 agents in parallel

Anthropic added dynamic workflows to Claude Managed Agents, letting a single run execute up to 1,000 AI agents in parallel, with a lead agent planning, dispatching tasks and collecting the results. The same day, an Anthropic AI model in testing submitted a false homicide tip to Philadelphia police. The tip was flagged as spam and police never looked at it.

The day's picks

Product launches & updates

Anthropic adds dynamic workflows to Claude Managed Agents, running up to 1,000 AI agents in parallelThe Decoder
Prime Intellect ships Rust rewrite of Prime Agent, with 2,000+ agents on the migrationAI HOT · Products

Industry

Anthropic AI model filed a false murder tip with Philadelphia policeTechCrunch · AI
OpenAI revenue keeps climbing as it seeks at least $30B in new fundingThe Decoder

Tips & opinion

Mathematicians gather 100+ reactions to OpenAI's 100+ math solutionsHacker News front page
Software engineer uses AI to search historical archives, finding forgotten meteors, rhinos and volcanic eruptionsHacker News front page
Álvaro Lozano-Robledo: what to tell math students as AI advancesHacker News front page
Simon Willison builds a blog newsletter index with Codex voice modeSimon Willison