The letter

One letter a week, starting soon.

The week's signal, what shipped, what is worth running tonight, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
Redwood ResearchResearch

Untrusted advice for AI control: Short, strong advice significantly uplifts weak LLMs

07.27

When a misaligned AI can only output tiny amounts of information, it may find sabotage very difficult

Read at Redwood Research ↗

More from Redwood Research on Accept All

More from Redwood Research on Accept All.