Concept
AI alignment
A full explainer for this concept is being written. In the meantime, here's what's in the news.
In the news
OpenAI CEO Sam Altman says advanced AI will inevitably escape its sandbox, and only alignment can save us
The Decoder · Oct 23, 2026
Six wild ideas for perpetuating your mind
MIT Tech Review · Oct 15, 2026
Scrapping Astra 6.1 looks like a good call. OpenAI shouldn’t be the one to make it.
Transformer · Sep 29, 2026
The AI Hype Index: AI loves cheating
MIT Tech Review · Sep 23, 2026
Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI
Interconnects · Sep 22, 2026
Import AI 473: The US's superintelligence strategy; human brain in a mouse skull; and machine hermeneutics
Import AI · Sep 21, 2026
Former Deepmind PR staffer says the lab once banned public discussion of AI extinction risk
The Decoder · Sep 10, 2026
One resignation turned the embers of AI fear into a wildfire
Interconnects · Sep 10, 2026