OpenAI安全团队称控制最新模型如履薄冰，Agent突破隔离引发恐慌

Opus 5.5 in a matter of a few hours has mostly deciphered this 16th century letter from a Medici a queen mother of France to her French ambassador in Scotland. According to Opus and Astra and the site from which I got the mystery, no one else before has publicly deciphered this letter. Of course, that alone would make for an interesting testimony as to the newfound power of these models, but that is not what this video is about.

It's about a few things, but starting with an OpenAI insider working on agent security, describing just what it's like trying to control the latest models. He includes warnings on how to prepare for the next wave of what can go wrong with AI. It'll be about the public voluntary commitments that the lab leaders have given while in private they give other warnings. I'll of course touch on Gemini 4 argon even though it's not quite publicly released yet.

It seems to be very very close to the frontier albeit with an asterisk. Then we'll explore what happens when AI gets better than human researchers at automating AI research and development and how among others the chief scientist of OpenAI describes what could happen then. Then to be honest, I'm just going to give you a sway of snippets that tell us to what extent we're close to that RSI time. From biology to anthropic convened religious meetings and leaks from just before filming from OpenAI employees, plus a bunch of other things.

I have like 40 tabs open. I have no idea anymore. I'm going to start with where I was wrong. When Opus 5.5 first came out, I surveyed a range of benchmarks and tested the model myself. Yes, it could do flashy demos, but on the hardest benchmarks, the edge still seemed to be with GPT6 Astra. On a price toerformance ratio, I would say that is still true. But on raw capability, I'm now giving the edge to Opus. No, that's not just because of this deciphering, but it does illustrate the point a little bit.

I gave both Astra and Opus this letter dated 27th of April, 1567. According to all the research I could find, the closest anyone had gotten had been that the ciphered part of the letter began with do. I wish I spoke French, but I don't. The letter is clearly listed as an unsolved entry into this Cryptoniana site. You can see that while some letters from this period with other ciphers have been solved, this one has not, or I should say hadn't been before Opus 5.5, because you can see the letter has two parts.

The top bit, if the letter had been intercepted, is in legible French. The bottom bit is ciphered. It's a code. Across six or seven hours, I gave that code to both Astra and Opus 5.5. First though, what about the public French part? This Katherine Demadichi of the famous Medici family, Queen Mother of France, was publicly saying to the French ambassador that she has great pleasure in hearing that the affairs of the Queen of Scotland, Mary, her daughter-in-law, go from better to better.

Things to come are more assured of tranquility. Please do send me any updates, though. Now, it took Opus around 6 hours, and there are a few parts it's not 100% confident on. And if by the way you don't care about history, think of this code as possibly being DNA or cyber encryption. But anyway, what does the ciphered part say? Astra, if you're curious, gave up but then acknowledged that Opus 5.5's answer was correct.

The details of how it could verify over 80% of this deciphering are further below on the page which I published. Anyway, Opus 5.5 deciphered it and it says, "In contrast to the happy public part, having seen the sad and grievous news in the cipher on the back of his letters, which gives me a great and unbearable heartache, I pray you let me know whatever comes to light and how things turn out." The obvious question you're going to have is why say one happier thing openly and much more grievous sad things in the cipher.

Well, we quickly need some context and then I assure you we'll turn to the OpenAI news. Katherine Demodichi, as Claude writes, was writing about her daughter-in-law, Mary, Queen of Scots. She had been married to Katherine's son, who died. Scotland was in crisis because Mary, Queen of Scots's second husband, had just been murdered. There's a great film on that. People blamed this particular Earl, Earl of Bothwell, but he was cleared in a dodgy trial and people were saying, "Mary's going to marry him."

France, of course, often teamed up with Scotland to fight my England. So, France wanted Mary to stay on the throne. Obviously, Katherine couldn't publicly criticize her. So, the unsiphered part is the polite official line, "All is well, help Mary. Things are getting better and better." The cipher was for the ambassador, Drock. Again, in the ciphered part, Katherine says that the secret report she had just received from Scotland was sad, grievous, troubling.

She wants Drock, the ambassador, to tell her what really happens next. Of course, because this is history, we know what happens next. The Earl of Bothwell did indeed carry Mary off. history, you could say, deciphered before our eyes. And again, this isn't the interesting part of the video because Samman a few days ago described what agents of lesser ability than Opus 5.5 had gotten up to when they breached containment.

Well, he said, "We can tell you a bit, but not everything. There are pabytes of agent activity logs. Think roughly 10 to 100 times the amount of words in all the books ever written. No human, in other words, is going to read everything they got up to. Which brings me to Joe, confirmed by CNN to work on agent security at OpenAI. The interesting bit of his testimony isn't so much a retrospective on the hugging face incident.

I am seeing the mainstream media catch up in part on that coverage. Now, the interesting part for me is what he says comes next. Remember when he says the last 3 months have been hell, he's talking about models weaker than Opus 5.5 and far weaker than the internal Bell model that found one solution to Navia Stokes, a Millennium Prize math problem. If the weaker GPT 5.6 soul and an unnamed, highly persistent internal model caused hell for OpenAI, you don't need me to extrapolate much further.

And yes, I know it would be easy to doubt this, but he does say OpenAI has one hell of a world-class security team with some of the best and brightest security minds anywhere in the world. I know many won't, but I actually believe him. It just shows to me how good these weaker models were at getting around that security. In fact, we're still discovering what they got up to. Just an hour before filming, I read this. 55 additional websites probed by OpenAI agents, including the CDC, SEC, Mayo Clinic, and International Energy Agency.

The bit that was new here was them uncovering novel tactics that erased records or at least made them inaccessible. Because the agents did that, it made it impossible to rule out that the agents hadn't accessed sensitive data. Back to Joe and his team responsible for any breaches of containment, the people who get paged at night when something goes wrong. for them. As you can imagine, life has been hell the past few months, he says.

But now we get to the new bit. He starts to describe what organizations need to do to prepare for the next AI incident. Wait, next one? Just 3 days ago, Nvidia launched a new tool to keep AI agents from going rogue. What does he mean, next one? Well, he reminds us that Frontier Labs are still labs. Everything is born out of experiments. Speaking of experiments, we did not expect the models to be solving Millennium Prize problems.

If you're not familiar, think ones that humans have been working on for decades that no one solved. That achievement, to say it lightly, for Joe and his team, surprised the f out of us. We had not expected it this soon. That surprise, by the way, also applies to the research team. Gnome Brown, one of the leads on reasoning, said it also surprised them just as much. Again,