Stanford PhD defense: generative models for safety in autonomous systems, tested in real flights
StanfordAILab · x · 2026-10-23
Stanford's SIS Laboratory released the recording of Marc Schlichting's PhD defense (Nov 2025) on generative models for safety in autonomous decision-making systems. The work spans failure discovery in a 1200-dimensional F-16 control system and an LLM decision-support tool for aviation emergencies that was tested in real flights.
More from Safety
- AI uncovers PHP2Shell flaw threatening the tech behind 70% of all websites — AIFlow_ML · 2026-10-23
- Ben Murphy on this week's cyber events: deployment models and open-source risks — herbiebradley · 2026-10-23
- Only 8% of cloud vendors support OIDC — dev calls to kill long-lived API keys — cramforce · 2026-10-23
- Journalist publishes a practical digital security checklist for the AI age — jammastergirish · 2026-10-23
- Stanford HAI and Stanford Medicine respond to FDA on regulating GenAI-enabled medical devices — StanfordHAI · 2026-10-23
- Ex-OpenAI futurist Joshua Achiam warns AI hacks could trigger internet lockdowns within months — jachiam0 · 2026-10-23