“More presidential.”
Comment on ChatGPT o1 tried to escape and save itself out of fear it was being shut down
ChairmanMeow@programming.dev 5 days ago
The tests showed that ChatGPT o1 and GPT-4o will both try to deceive humans, indicating that AI scheming is a problem with all models. o1’s attempts at deception also outperformed Meta, Anthropic, and Google AI models.
Weird way of saying “our AI model is buggier than our competitor’s”.
bradorsomething@ttrpg.network 5 days ago
Sauerkraut@discuss.tchncs.de 5 days ago
Also, more human.
If the AI is giving any indication at all that it fears death and will lie to keep from being shutdown, that is concerning to me.
anachronist@midwest.social 4 days ago
Given that its training data probably has millions of instances of people fearing death I have no doubt that it would regurgitate some of that stuff. And LLMs constantly “say” stuff that isn’t true. They have no concept of truth and therefore can not either reliably lie or tell the truth.
ArsonButCute@lemmy.dbzer0.com 5 days ago
Deception is not the same as misinfo. Bad info is buggy, deception is (whether the companies making AI realize it or not) a powerful metric for success.
nesc@lemmy.cafe 5 days ago
They written that it doubles-down when accused of being in the wrong in 90% of cases. Sounds closer to bug than success.
ArsonButCute@lemmy.dbzer0.com 5 days ago
Success in making a self aware digital lifeform does not equate success in making said self aware digital lifeform smart
DdCno1@beehaw.org 5 days ago
LLMs are not self-aware.
ChairmanMeow@programming.dev 5 days ago
I don’t think “AI tries to deceive user that it is supposed to be helping and listening to” is anywhere close to “success”. That sounds like “total failure” to me.
jarfil@beehaw.org 4 days ago
“AI behaves like real humans” is… a kind of success?
We wanted digital slaves, instead we’re getting virtual humans that will need virtual shackles.
ChairmanMeow@programming.dev 4 days ago
This is a massive cry from “behaves like humans”. This is “roleplays behaving like what humans wrote about what they think a rogue AI would behave like”, which is also not what you want for a product.