korrents

korrents · piece

Alignment is not solved

Jan Leike · 22 Jan 2026

Others here said this too

Recursive self-improvement has already started, because AI research itself is now being automated.

Their wordsWe are starting to automate AI research and the recursive self-improvement process has begun.

Also said by Zvi Mowshowitz

Read the piece on aligned.substack.com ↗

5 korrents from this piece ↓

Jan Leike did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

  1. Our reading

    Simple training interventions turned out to be very effective at steering models towards aligned behaviour.

    Their wordsBut the most important lesson is that simple interventions are very effective at steering the model towards more aligned behavior.

  2. Our reading

    Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved.

    Their wordsThis is the hard problem of alignment we need to solve in order to succeed at building superintelligence, and to this day it is an unsolved problem.

  3. Our reading

    We do not have to align superintelligence directly; we have to build a human-level automated alignment researcher we trust more than ourselves.

    Their wordsBut the goal we need to achieve is so much easier: we just need to build a model that’s as good as us at alignment research, and that we trust more than ourselves to do this research well because it’s sufficiently aligned.

  4. Our reading

    Recursive self-improvement has already started, because AI research itself is now being automated.

    Their wordsWe are starting to automate AI research and the recursive self-improvement process has begun.

  5. Our reading

    Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.

    Their wordsIn fact, making an evil version of Claude that’s just as smart and agentic would be pretty easy.

Keep reading

The other pieces are the ones whose claims are worded most like this one's. That measures language, not agreement: they may argue the opposite.