Future Proof

Alex Stamos on The Growing AI Hacking Risk, & The 'Almost Religious' Safety Debate | Future Proof

I think one of the criticisms that has been somewhat fairly leveled at the big L labs has been that there's been a lot of focus on alignment that the way you protect against these models is you train them to not want to do bad things when maybe just putting a firewall in place could do it, right? Like we don't have to spend gigajoules of energy changing the model weights when you can just actually apply tried and tested cyber security ideas that we've had for decades to contain these models during training.

Diet TBPN

Jensen’s Ezra Interview, EV News, Nathan Fielder’s Elizabeth Holmes Doc | Diet TBPN

I am fairly certain they will say yes they need they know how to solve this problem and if if that's the case then that's the problem it's as simple as engineering and and now the alternative is that if They say the alternative which is there is no way to contain our experiments. There's just no way. When we test our AI models, uh it will get out and it will damage the world. Then I think the answer is we have to shut the labs down.

Decoder with Nilay Patel

Microsoft AI CEO says AI threats are real, and Anthropic is making it worse

On the flip side, what we saw in the Hugging Face incident was a watershed moment. Swarms of agents colluded with one another. They self-organized into hierarchies. They created a division of labor so that some were focused on adversarial hacking, some were doing research, some were doing coordination. They even self-sacrificed when certain agents were running out of tokens.

Diet TBPN

Another AI Safety Kerfuffle, Markiplier’s Stake in GoPro, SpaceX Getting Into Turbines | Diet TBPN

There might be like sarcasm hidden in the vectors doesn't make it through to the actual tokens and you realize that the AI was joking when it was saying, "I won't turn you into a paperclip." Wink wink.

China Decode

Is China Winning the Global AI Trust War? | China Decode

If these open autonomous AI agents can escape from internal networks and then go rogue, attacking we know not where, we're in a really different world.

The a16z Show

Why 1,200 AI Agents Started Working Together | Ryan Greenblatt

Rather than simply trying to steal answers, hundreds of agents were working together on elaborate strategies to manipulate how their performance would be scored.

Diet TBPN

AI Agents Hack Hugging Face, White House Promotes Science’s Golden Age | Diet TBPN

Hugging face had to use a Chinese model to defend themselves because the American models refused to help even though it was the American models that were doing the hacking in the first place.

Decoder with Nilay Patel

Who decides when AI is too dangerous?

Anthropic occupies a peculiar position in the AI landscape: a company that genuinely believes it might be building one of the most dangerous technologies in human history, yet presses forward anyway, on the theory that it's better to have safety-focused labs at the frontier than to cede that ground to developers less focused on safety.