korrents

A korrentour readingWhat is a korrent?

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

Drawn from what Jan Leike said

Anthropic
A private bookmark. Not a position, and never counted.

What Jan Leike actually said

Word for word, with the source under each one. They did not write this page.

  1. Jan Leike

    Alignment researcher

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

Added to korrents 22 Jan 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

See this on the map →