✳flâneur — a map of the web's best reading

The New AI Consciousness Paper - by Scott Alexander

astralcodexten.com · 3,891 words · saved by 1 readers

Most discourse on AI is low-quality. Most discourse on consciousness is super-abysmal-double-low quality. Multiply these - or maybe raise one to the exponent of the other, or something - and you get the quality of discourse on AI consciousness. It’s not great. Out-of-the-box AIs mimic human text, and humans almost always describe themselves as conscious. So if you ask an AI whether it is conscious, it will often say yes. But because companies know this will happen, and don’t want to give their customers existential crises, they hard-code in a command for the AIs to answer that they aren’t conscious. Any response the AIs give will be determined by these two conflicting biases, and therefore not really believable. A recent paper expands on this method by subjecting AIs to a mechanistic interpretability “lie detector” test; it finds that AIs which say they’re conscious think they’re telling the truth, and AIs which say they’re not conscious think they’re lying. But it’s hard to be sure th

The New AI Consciousness Paper ... Scott Alexander Nov 20, 2025 490 979 71 Share I. Most discourse on AI is low-quality. Most discourse on consciousness is super-abysmal-double-low quality. Multiply these - or maybe raise one to the exponent of the other, or something - and you get the quality of discourse on AI consciousness. It’s not great. Out-of-the-box AIs mimic human text, and humans almost always describe themselves as conscious. So if you ask an AI whether it is conscious, it will often say yes. But because companies know this will happen, and don’t want to give their customers existen

Explore this link on the map →

saved by

related reading