My research interest is hallucination detection and mechanistic interpretability.
Should I think about applying for this program? I'm kind of afraid my publication record is not strong enough…
🚨 MATS Winter 2027 applications are now open.
Fully-funded, 12-week fellowship for aspiring & established AI alignment, interpretability, security, governance researchers & field-builders
📍 Berkeley/London
📅 Jan 19–Apr 10
💰 $6.4k/mo + $8k - 16k/mo compute
Apply by Sep 6 ↓
A much simpler prompt approach is: to report back or reply to me as if you were writing a report for top national leaders. From then on, AI never writes me things that inexplicably compress a bunch of concepts into overly brief buzzwords, and the context is laid out extremely clearly.
@SmokeAwayyy@DarioAmodei The answer is simple: if he doesn't own the company, he paints it as an evil dictatorship. If it's Anthropic and he's the one running it, then it's a benevolent God. At the end of the day, that's just how he thinks.