Skip to content
Quotes.

Scott Alexander quote, Sep 23, 2026

Author, Astral Codex Ten · Sep 23, 2026 · Post, Mysteries Of AI Generalization

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.

Primary source

Words found on the source page on Sep 25, 2026.

More from Scott Alexander

Quote
An AI with more real layers can actually be “smarter” in the conventional sense of the term.Sep 24, 2026· Post
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.Sep 24, 2026· Post
The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy.Sep 24, 2026· Post
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.Sep 23, 2026· Post

On the same topics

Quote
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.Yoshua BengioSep 23, 2026· Keynote
The companies building the most powerful AI systems admit their products pose catastrophic risks, yet offer no convincing technical solutions.Yoshua BengioSep 23, 2026· Keynote
The race is not a law of nature: it is the product of choices, choices made by the companies themselves.Yoshua BengioSep 23, 2026· Keynote
We must agree collectively that no one, no company and no country, should develop an AI system that could cause large-scale harm.Yoshua BengioSep 23, 2026· Keynote
AI must not be placed in the hands of children without first being tested, evaluated, and therefore authorized.Emmanuel MacronSep 22, 2026· Statement
We cannot repeat the mistakes of the past and wait twenty years to see the impact of chatbots on minors.Emmanuel MacronSep 22, 2026· Statement
About this quote
Said by
Scott Alexander, Author, Astral Codex Ten
Where
Mysteries Of AI Generalization
Topics
Safety, Research
Source
astralcodexten.com/p/mysteries-of-ai-generalization

A quote is one moment, not the whole argument. Read it in context at the source.

Sources: the primary source linked on each quote, checked weekly. A quote is one moment; read the source. Logos via logo.dev; trademarks belong to their owners.

New quotes by email

Fridays, only in weeks with new on-the-record quotes from data and AI leaders.

Double opt-in. Unsubscribe any time.