Andrej Karpathy contributing to open-source AutoResearch, an agent that runs AI research end-to-end
JaynitMakwana · x · 2026-09-07
AutoResearch, an open-source agent workflow for AI/ML research, says Andrej Karpathy is contributing. Give it a research idea and it plans, runs experiments, analyzes, and reviews autonomously. The team emphasizes anti-hallucination design: every claim is checked against experiment logs, source records, and blind review, with everything written to disk for human verification.
Related event: AutoResearch: Open-Source Agent Turns Ideas into Paper-Grade Evidence(3 posts)→
More from coding & agent
- Building a neutral Codex-class harness requires running the original inner harness, dev says — joshalbrecht · 2026-09-07
- Dev Builds Timestamped Summary Site for All MLOps Community Talks, With an MCP Server — strickvl · 2026-09-07
- Shipping an Obsidian plugin with GPT-6 Astra: scan limits, SVG icons, review delays — vista8 · 2026-09-07
- Grok Build 1.0.22 ships subagent messaging, first-party MCP server and safer Auto mode — mark_k · 2026-09-07
- Agents on a 16GB MacBook Air M5: Qwen 3.5-9B 4-bit can't yet build a working app — Fluid-Author-9566 · 2026-09-07
- Remastering old i2v videos with MiniMax H3: a depth-map + reference workflow — WaitAcademic1669 · 2026-09-07