Lesser Wrong Feed

 OpenAI’s surveillance language has many potential loopholes and they can do better
 Wed, 04 Mar 2026 04:25:43 GMT
 Mass surveillance, red lines, and a crazy weekend
 Wed, 04 Mar 2026 04:24:15 GMT
 Lie To Me, But At Least Don't Bullshit
 Wed, 04 Mar 2026 02:20:10 GMT
 LLM coherentization as an obvious low-hanging fruit to try?
 Wed, 04 Mar 2026 00:59:42 GMT
 Milder temperature makes a hell stable
 Tue, 03 Mar 2026 22:25:57 GMT
 Mass Surveillance w/ LLMs is the Default Outcome. Contracts Won't Change That.
 Tue, 03 Mar 2026 21:18:35 GMT
 A Tale of Three Contracts
 Tue, 03 Mar 2026 20:30:32 GMT
 An Alignment Journal: Coming Soon
 Tue, 03 Mar 2026 20:27:07 GMT
 Current activation oracles are hard to use
 Tue, 03 Mar 2026 19:33:06 GMT
 Question: Why is the goal of AI safety not 'moral machines'?
 Tue, 03 Mar 2026 18:16:38 GMT