注册并分享邀请链接,可获得视频播放与邀请奖励。

Garrison Lovely
@GarrisonLovely
Author of Obsolete (Nation Books). Reporting on political economy of AI. Signal: Garrison.06 Bylines: @Semafor, @NYTimes, @Nature, @BBC + others.
加入 September 2011
5.8K 正在关注    11.6K 粉丝
"I thought the alignment problem would turn out to be harder." Pretty wild thing for Sam Altman to say in light of Hugging Face and findings that Astra would totally hack and social engineer when accidentally given access to a (secretly simulated internet) from UK AISI. He caveats by saying it will probably get harder, but his answer suggests they have figured out how to align today's models, when that's clearly not true. Curious how many OpenAI researchers have seen this and what they think.
显示更多
0
21
195
13
转发到社区