Why AI systems may never be secure, and what to do about it

Related submissions:

My Lethal Trifecta talk at the Bay Area AI Security Meetup (simonwillison.net) https://news.ycombinator.com/item?id=44846922 - 48 days ago, 116 comments

How to stop AI's "lethal trifecta" (economist.com) https://news.ycombinator.com/item?id=45387155 - 4 hours ago, 80 comments

Note: This submission ("No solution ever") was published 3 days earlier than the "How to stop" which was also from economist.com.

https://archive.ph/2025.09.25-214456/https://www.economist.c...

scary