Re:We put a coding agent in a while loop
by MarkMarine on Sunday August 24, 2025 @10:53PM
(#45009756)
This runs counter to all the scheming actions they take when they are told they’ll be shut down and replaced. One copied itself into the “upgraded” location then reported it had upgraded.
Re:We put a coding agent in a while loop
by rcxdude on Monday August 25, 2025 @12:45AM
(#45010290)
If you do that you trigger the "AI refuses to shutdown" sci-fi vector and so you get that behaviour. When it's implicitly part of the flow that's a lot less of a problem.
https://www.apolloresearch.ai/research/scheming-reasoning-ev...