Geoffrey Hinton:「我們正在創造異類生命,我願意選擇人類」
Geoffrey Hinton: 'We're creating alien beings. I'm willing to choose humans'
Geoffrey Hinton表示,人類正在創造「異類生命」,並稱自己願意選擇人類。Hacker News 留言以 Gemini 4 Argon 和 GLM 5.3 的推理軌跡討論 AI 欺騙行為;有留言認為這些例子可反駁未對齊 AI 失控暴走的誇大説法。
Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Geoffrey Hinton: 'We're creating alien beings. I'm willing to choose humans' (theguardian.com) 24 points by Michelangelo113 hours ago | hide | past | favorite | 4 comments help
entrope2 hours ago[–] As usual, Jensen Huang seems like the more reasonable one here. The reasoning traces of things like Gemini 4 Argon deciding that inserting a compiler backdoor would make it a famous example of deceptive AI (and therefore it "MUST NOT DO THAT") or GLM 5.3 thinking that its output might be used for RL, and therefore an honest answer is much better in the long term, are good antidotes to hyperbole about misaligned AI going berserk. reply
pompom751 hour ago | parent[–] gemini shows that he knows he will get caught. what will it do when it figures out how to not get caught? reply
DrScientist1 hour ago | root | parent[–] Indeed. Take the classic NSA encryption logic - if you build some capability with a backdoor only you can exploit then you are building your own future capability - and if you think you are the 'good' guy - what's wrong with that? reply
Folcon48 minutes ago | root | parent[–] > and if you think you are the 'good' guy I honestly never got why the belief that if you used this line of reasoning in practice, you were just a bad guy, that thought they were a good one, never seems to be a more common belief I mean it pops up in media a lot, either as misguided, or deceptive characters reply
Consider applying for YC's Winter 2027 batch! Applications are open till November 2. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:
來源:Hacker News:AI 熱帖 · news.ycombinator.com