Stanford turns papers into AI agents; two unrelated studies surface unreported ADHD genetic link
VraserX · x · 2026-09-22
Stanford has turned scientific papers into AI agents that can reproduce the underlying research and talk to other paper agents. In one demo, agents built from two unrelated studies surfaced a previously unreported genetic connection to ADHD risk.
The framing: this is a far better vision for AI science than "chat with a PDF" — making human knowledge active, where papers reason together and produce new findings.
More from AGI Musings
- Ex-Pentagon AI Official: Adopting AI Is an Institutional Problem, Not a Model Problem — ChinaTalk · 2026-09-22
- Box CEO Aaron Levie bets big on personal agents, as Meta agent spending could push ARPU past $227 — inductionheads · 2026-09-22
- The week labs asked to slow down: Claude does 26% of Anthropic's work, Gemini breached 3 firms — alex_verem · 2026-09-22
- White-collar work has ~3 years left, argues ChrisGPT, before agents abstract it away — ChrisGPT · 2026-09-22
- Who Owns the Design When AI Made Half of It? UX Magazine Series Concludes — uxmag · 2026-09-22
- David Patterson: 10,000 Agents Solved a Conjecture — AI Is About to Replace Entire Organizations — davidpattersonx · 2026-09-22