5 korrents from this piece
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.
Their wordsBut the most important lesson is that simple interventions are very effective at steering the model towards more aligned behavior.
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.
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.
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.
Their wordsIn fact, making an evil version of Claude that’s just as smart and agentic would be pretty easy.