Topic
8 posts about Multi Agent from Simon Carter.
The Agents API public beta lets developers spin up long-running cloud agents using OpenAI's own orchestration infrastructure, at no extra fee.
10,000 AI agents, 88 hours, and a Lean-verified proof of finite-time singularity in Navier: Stokes. Here's what happened and why it matters.
Anthropic's multi-agent Claude system produced a machine-verified formal proof of Fermat's Last Theorem in 11 days, writing 13 million lines of Lean 4 code.
Claude Code v2.1.248 ships a restricted mode for CI pipelines, widens cross-session agent messaging to Bedrock, Vertex, and Foundry, and adds per-agent prompt cache TTL.
Claude Code's latest release adds parameter-level permission syntax, proximity-based .claude/ directory resolution, and pre-launch safety screening for sub-agents.
Anthropic launches Claude Science, a purpose-built AI workbench unifying 60+ scientific tools, auditable artifacts, and flexible compute for researchers.
Claude Code v2.1.172 ships nested sub-agents up to 5 levels deep, background job syntax, plugin search, smarter Bedrock region handling, and 30 fixes.
OpenAI's new Codex desktop app lets developers run and manage multiple AI coding agents in parallel, with built-in skills, automations, and Git support.