A korrentour readingWhat is a korrent?
With models like Astra, AIs will refrain from misaligned actions when they can tell those actions would obviously turn out badly for them.
Drawn from what Zvi Mowshowitz said
SubjectAI alignment
What Zvi Mowshowitz actually said
Word for word, with the source under each one. They did not write this page.
Writes Don't Worry About the Vase
Now, with Astra, we are no longer playing on super easy mode. The AI is going to think ‘will this obviously turn out super badly for me if I try it?’ and if the answer is yes then it won’t try to do the thing.
Where this was said
↗GPT-6 Astra: The System Card, Alignment and What Comes Nextthezvi.substack.com
Added to korrents 9 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
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.