What Henrik Karlsson thinks about AI alignment

@henrik-karlsson · 15 positions · On ppll ↗

Swedish essayist who writes Escaping Flatland, a newsletter of essays on relationships, thinking, writing and homeschooling.

Henrik Karlsson did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter AI alignment · Newest first

Topic

All 15 creativity 3 innovation 3 behavioural science 2 Psychotherapy 2 AI alignment 1 ambition 1 documentation 1 health and fitness 1 ideas vs execution 1

4 more topics

motivation 1 psychedelics 1 reinforcement learning 1 taste 1

Sort

Newest Oldest

Only Henrik Karlsson on AI alignment. See everyone on AI alignment

1 dated position, 2026, in their own words. Our reading of what Henrik Karlsson has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

26 Aug 2026

Our readingA feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.

Their wordsIf there is a feedback loop reinforcing a behavior, it is hard not to go in the direction that improves the score.

↗First we shape our feedback loops; then they shape ushenrikkarlsson.xyz 1st of 2 in this piece