Stanford researcher: automated orchestrators are a big unlock, current versions not there yet
anshulkundaje · x · 2026-08-21
Responding to skepticism about Claude Science, genomics researcher Anshul Kundaje argues that while today's automated orchestrators aren't there yet, a smoothly running one would be a major unlock — it's high priority for the team and rapid improvements are expected. He stresses the system democratizes what experts can do. The original critic countered that naming open-source components only addresses provenance; the deeper question is causal attribution across the LLM, agent runtime, and human-written protocol.
More from coding & agent
- Decision models match LLMs on routing and safety — and are 7-8x faster — randal_olson · 2026-10-16
- Temporal Serverless Workers on Cloud Run: queue-driven autoscaling, scale to zero — rseroter · 2026-10-16
- Meta's Superintelligence Lab Runs 200+ Direct Reports—A Lesson for Flat Multi-Agent Systems — peterjliu · 2026-10-16
- LangChain CEO: the most interesting agent harness work lives at the harness-infra boundary — hwchase17 · 2026-10-16
- GitSwarm paper: agents share branchable Git memory, solving all 30 IMOProofBench problems in one run — anirudhg9119 · 2026-10-16
- Hands-on with Gemini 4 Argon: faster than Opus 5.5 but hallucinates more and costs more — prasenx · 2026-10-16