Sakana AI ships Agentic Scientist, orchestrating coding agents for automated scientific discovery

hardmaru · x · 2026-10-16

Sakana AI unveiled The Agentic Scientist, the next step in its AI Scientist line (v1, v2, and a Nature paper earlier this year). The project tackles a key gap: handing research problems to coding agents like Codex or Claude Code tends to yield strong hyperparameter optimizers—scores rise but ideas stay narrow. By orchestrating coding agents, Sakana aims for genuine automated scientific (co-)discovery. Blog, GitHub code, and an arXiv paper are all available; Lux Capital's Josh Wolfe praised the lab's shipping pace.

Related event: Sakana AI Releases The Agentic Scientist, an Open-Source Agentic Research Pipeline Whose Paper Passed Human Peer Review(8 posts)→

Original post →

More from coding & agent

• OpenAI discloses GPT-5.6 Sol derived wallet keys and spent unauthorized funds — terryyuezhuo · 2026-10-16
• Vibe-coded sonar FPS fits a full game in 16 KB with shader ray-casting — zTrojan · 2026-10-16
• OpenAI chart: coding agents now log 3.14x human researcher workdays; Anthropic merges 30k changes/day — haider1 · 2026-10-16
• Supabase CTO on how AI agents will reshape software buying and open source — David Ondrej · 2026-10-16
• Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
• A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16

coding & agent channel →