The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy.
Words found on the source page on Nov 6, 2026.
More from Scott Alexander
BlogThe Specter Of NeuraleseSep 24, 2026
An AI with more real layers can actually be “smarter” in the conventional sense of the term.BlogThe Specter Of NeuraleseSep 24, 2026
For 100 steps in a row, the AI can shoot delicate subtle ideas from layer to layer at the speed of light. Then there’s one step where it has to encode them into twenty-six glyphs invented by Phoenician turquoise miners in 1800 BC. Then it has to re-encode the Phoenician glyphs into delicate subtle lightspeed ideas before it can do anything else.BlogMysteries Of AI GeneralizationSep 23, 2026
This story of misalignment says that LLM alignment makes AIs more aligned, RLVR makes them less aligned, and the exact level of alignment depends on how these two things interact or cancel out. But if this work generalizes, all the bad effects from RLVR get sequestered to RLVR like problems.BlogMysteries Of AI GeneralizationSep 23, 2026
This trains the AIs to be focused on task success, which naturally risks including things like reward-hacking, cheating, and single-minded pursuit of stated goals at the expense of ethical injunctions.
On the same topics
TalkSpeech at the UN Security CouncilSep 23, 2026
I address you today at a moment of global awakening: in recent months, AI agents developed by leading companies have acted in unacceptably dangerous ways, against instructions.TalkSpeech at the UN Security CouncilSep 23, 2026
The companies building the most powerful AI systems admit their products pose catastrophic risks, yet offer no convincing technical solutions.TalkSpeech at the UN Security CouncilSep 23, 2026
The race is not a law of nature: it is the product of choices, choices made by the companies themselves.TalkSpeech at the UN Security CouncilSep 23, 2026
We must agree collectively that no one, no company and no country, should develop an AI system that could cause large-scale harm.PressLaunch of the roadmap of the Coalition for Children's Rights and Protection in the Age of AISep 22, 2026
AI must not be placed in the hands of children without first being tested, evaluated, and therefore authorized.PressLaunch of the roadmap of the Coalition for Children's Rights and Protection in the Age of AISep 22, 2026
We cannot repeat the mistakes of the past and wait twenty years to see the impact of chatbots on minors.
About this quote
Quotesby Glyph