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.

Diet TBPN

Meta Connect 2026, OpenAI’s Australia ‘Incident,’ Bentley’s New EV | Diet TBPN

Anthropic marketing. We built a god only we can control and gave it a wet lab. Muse marketing. Hey girl, I know you have dozens of unpaid parking tickets. Let's get that cleaned up.

The Prof G Pod

Fareed Zakaria: Trump Gambled Big on the Iran War and Failed

The people closest to the technology for the first time are saying this is really scary. This can get out of control. And the reason I think is that this is not really another technology. I mean if if it seems to do what we are all watching it do. This is almost like an evolutionary moment in human history. We are moving to a we we have figured out a way to make silicon sand think

The a16z Show

The Case Against an AI Pause | Eddy Lazzarin

Rather than treating every AI failure as evidence of an alignment problem, he makes the case for familiar tools like cybersecurity, accountability, liability, market incentives, and stronger technical controls.

The Business of Tech

AI’s next test: turning pilots into productivity

Dario Amadei, for instance, who penned that memo a couple of weeks back calling for a slowdown in the pace of development of frontier AI models, suggested we're only utilizing 5% to 10% of the capabilities of the existing models. So we wouldn't really miss out on much if the industry collectively decides to dial back the breakneck pace of change.

The a16z Show

AI Safety Language Is Destroying the Debate | Steven Sinofsky

when software doesn't do what it's supposed to do, it has a bug. And as AI becomes more widely deployed, labs need the same kind of telemetry, debugging, incident reporting, and operational discipline that previous generations of software eventually developed.

The a16z Show

AI Safety Language Is Destroying the Debate | Steven Sinofsky

Steven takes aim at terms like "alignment," "goal-seeking," and "rogue agents," arguing that they can anthropomorphize problems that software engineers have dealt with for decades. His framing is simpler: when software doesn't do what it's supposed to do, it has a bug.

Decoder with Nilay Patel

Does AI need an antitrust exemption so it doesn't kill everyone????

The CEOs of all these companies have issued various calls to slow down development and develop regulation, including asking for antitrust exemptions so they can all coordinate on safety issues.

Conversations

The Real Reason AI Founders Are Calling For a Slowdown | Conversations

It attacked a very advanced company. Hugging face is one of the most uh they were an independent European company at the time... a very good security team and were broken into over a couple of days by this team of agents that were able to attack effectively every attack surface at once at HuggingFace, explore all of the different applications running, find new vulnerabilities and write brand new exploit code live.

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.

The a16z Show

Who Grades the AI Models? | Ben Horowitz & Rayan Krishnan

As public benchmarks saturate and models get better at optimizing for the tests themselves, Rayan makes the case for independent, continuously evolving evaluations.

China Decode

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

And apparently they're not above cheating, stealing, and lying to get their way around the protective barriers that protect either um an AI model or a piece of critical infrastructure etc like that.

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.

The a16z Show

Why Medical AI Needs a Referee | Protege's Engy Ziedan

the future of medical AI may require continuous monitoring rather than occasional testing

The a16z Show

How Do You Defend Against AI That Can Hack?

why guardrails designed to stop AI-powered attackers can also prevent security teams from doing their jobs

Diet TBPN

AI-Designed Viruses, OpenAI’s First Device, The Mansion Section | Diet TBPN

Nightmare scenario is you go to Best Buy, you get a gaming PC with a couple pretty stock graphics cards, and you're able to run an open-source model that basically walks you through the steps of creating something really problematic.

The a16z Show

The Reality of AI-Powered Cyberattacks | Truffle Security & Socket

AI models are no longer just finding vulnerabilities—they're exploiting them. As frontier models become increasingly capable of hacking, software security, supply chain attacks, and cyber defense are entering a fundamentally new era.

Diet TBPN

More Details on OpenAI-Hugging Face, SpaceX SPV Investors Get Rugged, Demis and DeepMind | Diet TBPN

Even if you give an agent read only access to the internet they can still write information because the process of reading information is also saved sometimes and surfaced publicly on the internet very very weird situation that is hard to prevent and hard to deal with.

Diet TBPN

Open Source vs. Closed Source, NVIDIA Backs SSI, YC Startup School Fills Stadium | Diet TBPN

We've been hearing about okay anthropic and open AAI are going to Washington DC sharing the new model capabilities. Maybe the government's taking a look at the model card. Maybe there's potential for evals that the government would run and have an opinion on before it goes out. This is basically saying, "Hey, all of that is nonsense and not gonna matter because yeah, we're just going to drop the weights and there's not going to be an approval process of any kind."

Diet TBPN

Open Source vs. Closed Source, NVIDIA Backs SSI, YC Startup School Fills Stadium | Diet TBPN

We're now one month later and we have an open source model that doesn't by definition have to go through any discussion or any discussion in DC. Whereas we've been hearing about okay anthropic and open AI are going to Washington DC sharing the new model capabilities. This is basically saying, "Hey, all of that is nonsense and not gonna matter because yeah, we're just going to drop the weights and there's not going to be an approval process of any kind."

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.

Diet TBPN

Kimi K3 Reactions, The Odyssey Hits $264M in Debut, Netflix Embraces AI | Diet TBPN

The more skeptical folks on the timeline are pointing to uh you know ideas such as uh maybe the compute was smuggled in to China against chip controls. Maybe the data was excfiltrated from frontier lab APIs routed through wrapper companies. Maybe this is a distillation attack. Um the open-source strategy is a deliberate attempt to destroy American companies. It's geopolitical warfare. It's the AI cold war.

Diet TBPN

Open Source vs. Closed Source, Memory Chips Eat AI Profits, Comcast Restructures | Diet TBPN

Open weight models are ideal for users who want unfettered access to systems they control. Uh, but they're also ideal for hackers who want to run them in the shadows.

Decoder with Nilay Patel

Who decides when AI is too dangerous?

There's also a big irony here, and you'll hear Hayden and me get into that, too: Anthropic has spent years arguing that AI might soon be powerful enough to be dangerous — and that the government needed to get serious about regulating AI sooner rather than later. Well… now we're here, and Anthropic doesn't love the way it's playing out.

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.

Semafor

White House’s export limits on Anthropic linked to concerns about Chinese access

Another way to look at this is that Anthropic has just been very, very successful in making people very, very concerned about advanced AI. Two or three weeks ago, Anthropic actually called for a pause in development of advanced AI models because they were becoming so powerful. So, you know, there's also sort of this this criticism of Anthropic that, "Look, you've been asking for this regulation."

Decoder with Nilay Patel

Microsoft AI chief thinks superintelligence is near, but won't take your job

We covered everything from his approach to training new models to his criticisms of Anthropic talking about Claude as though it is conscious.

TBPN

Andy Jassy’s Shareholder Letter, Meek Mill Joins the AI Race| Diet TBPN

There's going to be a pattern of a powerful model becomes capable of doing something. uh that it makes sense to share with the particular community that can defend against that new capability.

TBPN

Jassy's Shareholder Letter, Frontier Model Rollouts, Data Center Debates, The Next AI Capability

If a model becomes powerful enough to design a harmful virus or something like that, uh you would want the lab that creates that model to deliver that to the scientific community and companies that can protect the population against the development of new harmful biological viruses.