Optimus launches: an autonomous RL agent harness that runs experiments itself
_AustinCalvert_ · x · 2026-10-18
iacon launches Optimus, pitched as "the Claude Code moment for RL" — an autonomous RL agent harness. Give it a codebase, an API key and a goal; it spawns sub-agents running hundreds of parallel experiments, learns from its own run history, and builds an evolutionary tree where each failure seeds the next batch. If a task can be scored, it can be RL-trained: LLMs, agents, robots in sim, game NPCs — removing the manual grind previously reserved for top-tier labs.
More from coding & agent
- Claude Opus dissects agent music synthesis: chroma analysis and spectrograms as stand-ins for hearing — teortaxesTex · 2026-10-18
- Agent spawns its own 'procedural audio composer' subagent and synthesizes a vaporwave track in Python — teortaxesTex · 2026-10-18
- Dev builds ChatGPT plugin that has his Dot monitor news hourly and alert him — koltregaskes · 2026-10-18
- Work IQ MCP in GitHub Copilot cuts hours of manual issue tracking to under 30 minutes — DanWahlin · 2026-10-18
- Working with AI: sort your work by AI-verifiability, then design verifiers or be the judge — danshipper · 2026-10-18
- Personal agents vs. websites that block them: real-phone computer use may win — lucasmeijer · 2026-10-18