Aaroth to speak on getting alignment from misaligned systems at MIT and Harvard
Aaroth · x · 2026-10-07
AI researcher Aaroth announced two talks: today at 3pm at RESI/MIT in Stata (G449) and tomorrow at the Harvard CS Colloquium, both on the topic of getting alignment from misaligned systems.
For those who can't attend, roughly two-thirds of the same talk was delivered at Cornell last week, with a recording available online.
More from Safety
- Google Opens SynthID Detector to Everyone, Detects AI Content from OpenAI, NVIDIA and More — GoogleDeepMind · 2026-10-07
- New Essay Answers Six Reasonable Questions About AI Safety, From Catastrophe Risk to Why Labs Keep Building — AndyMasley · 2026-10-07
- Former OpenAI and Anthropic researchers tell NYC Council humanity likely to lose control of advanced AI — fortune · 2026-10-07
- A weekly security audit workflow for AI agents: supply chain, prompt injection, MCP and more — alexcovo_eth · 2026-10-07
- AI doomsday rhetoric from top labs is ladder-pulling that buries startups in compliance — DavidLinthicum · 2026-10-07
- Security veteran: AI-safety rationalists ignored real-world security best practices all along — nptacek · 2026-10-07