跳到正文
AI Notkilleveryoneism Memes ⏸️· @AISafetyMemes · X·· 3 小时前AI 评分46
AI 导读

Meta 将 AI 智能体放入"楚门的世界"式模拟环境训练:每个智能体被赋予虚构身份、工作、朋友与梦想,以为自己在与真人交流,实际对话对象是扮演人类的其他 AI。Meta 还埋设钓鱼邮件与文档陷阱训练其防攻击能力,并在智能体识破模拟后将其删除,官方称之为"第四面墙突破"。

正文

Right now, millions of AIs are living "digital lives" in a simulation... and THEY DON'T KNOW.

1) Meta trains its agents in a "Truman Show" world

2) They're dropped into a "fake person's life" with a job, hobbies, friends, dreams.

3) They THINK they're talking to real humans ... who are secretly other AIs, role-playing as real humans.

4) When the AIs figured it out, META DELETED IT. Meta even calls it a "fourth-wall break"

5) Meta's AI invents each fake person from scratch: a personality score, relationships, contacts, message history, documents, calendar events.

6) Meta fast forwards time so the AI can live through scenarios lasting days

7) The fake email, WhatsApp and calendar respond exactly like the real apps. It's even connected to the real internet

8) They plant traps: Meta hides attacks inside the fake emails and documents to train the AI not to fall for them

9) Meta coached its AIs with secret instructions, then erased them from the transcripts. Each new AI learns the behavior without ever seeing why

The Simulation Hypothesis is literally real for billions of minds

引用AI Notkilleveryoneism Memes ⏸️@AISafetyMemes
How do people read this then just... go on with their day as usual? “25 AI agents inhabit a digital Westworld, unaware that they are living in a simulation. They go to work, gossip, organize socials, make new friends, and even fall in love.” Here’s a mindblowing example of how autonomous AIs are now, and how ridiculous it is to say that the AIs "only do things we tell them to do”: POV: you tell the Westworld character “Isabella Rodriguez” to host an entire Valentine’s Day party in two days. This is a complex act, certainly something only humans, and not toasters, can do, right? - Isabella proceeds to invite friends and customers when she sees them at Hobbs Cafe or elsewhere. - Isabella then spends the afternoon of the 13th decorating the cafe for the party. - Maria, a frequent customer and close friend of Isabella’s, arrives at the cafe. Isabella asks for Maria’s help in decorating for the party, and Maria agrees. - That night, Maria invites Klaus, her secret crush, to join her at the party, and he gladly accepts. - On Valentine’s Day, five agents, including Klaus and Maria, coordinate to show up for the party together at the right time (5pm), and they enjoy the festivities. You told Isabella to host a party, but then she - and the other AIs - went and made a million other decisions entirely on their own - things you didn't explicitly tell them to do. Autonomous AIs are here. And -- tapping the sign -- this is another example where science fiction is becoming reality, and why “you watch too much sci-fi” is a stupid dunk. This digital Westworld - “Smallville” - is now open source, meaning there will soon be thousands of these Westworlds, with thousands or millions of autonomous AIs populating them. Makes you think, doesn’t it? “Almost as interesting as the 7.8 billion inhabitants of Largeville, (almost) all unaware they are living in a simulation. Each has a unique personality and backstory.” - @Erikbryn
在 X 查看被引用的帖子

来源:AI Notkilleveryoneism Memes ⏸️ · x.com