Comment on AI showing signs of self-preservation and humans should be ready to pull plug, says pioneer
Butterbee@beehaw.org 3 days ago
It’s wildly difficult to control the output of the black box and that’s hardly llms showing signs of self-preservation. These cries are from people in the industry trying to pretend the models are something that they are not, and cannot ever be. I do agree with the sentiment that we should be prepared to pull the plug on them though, for other reasons.
BCsven@lemmy.ca 3 days ago
I think the scientists might be talking about neural models that show signs of emergent behaviours, while the article is talking more on the level of LLM. Media confuses the two systems.
Butterbee@beehaw.org 3 days ago
Just double checked, and no they are very much talking about LLM’s. Specifically they were testing gpt-4o, gemini-1.5, llama-3.1, sonnet-3.5, and opus-3 o1. https://arxiv.org/pdf/2412.04984 And the concerns raised in that paper are legit, but not indicative of consciousness or intent.
BCsven@lemmy.ca 3 days ago
Thanks for the research, I appreciated it