Last Week in AI · AI Research & Frontier Labs · October 2026
Harris was going through the safety report for a new Anthropic model, which says that with safeguards off it tried to escape or tamper with its sandbox about 1.5% of the time. He calls this his general view of treating rogue-AI incidents as a security problem. He then grants that the same report offers a counterexample, since the model stopped at stronger barriers and reported what it had done.
…review exceptions before critical downstream actions occur. If you want to move beyond basic AI QA and put autonomous AI workflows to work for your business, visit box.com/slash LWIAI or join my team at BoxWorks in San Francisco on November 5th and 6th. Use code LWIAI for 50% off your registration.
…cached input tokens are less. So overall, much cheaper, 30% faster, and much more capable. It seems like Anthropic has really been cooking and I guess waited for GPT-6 to then go and do the usual kind of AI release thing of, okay, now we release our model. And again, the leading model provider.
…their sandbox about 1.5% of the time. All the attempts were low severity, and it would stop at stronger barriers and then actually report what it had done. And I want to kind of footstomp this. There is this question. So, my general view for what it's worth on this stuff is: if you start to think of these AI breakout AI rogue AI incidents as cyber incidents, you will miss the picture because no matter how high you set that cyber bar, there will eventually be a model that can jump over it. And all you're really doing when you raise the cyber bar is you're selecting for the exact agents that are conniving and capable enough to do just that. Now, what this suggests, this is actually an interesting counter argument to what I typically argue, because what it says is, well, okay, maybe if the cyber barriers are strong enough, the agent kind of in a way gets forced to stop and go, you know, this is a lot harder than just kind of hopping a fence. Maybe I should report where I'm at and all that stuff. So, depending on how good your…
There came a couple other things just around the same time as the release. So, a few days before, they also posted making Frontier cybersecurity release available to defenders. So, in cloud code on the web, there will be this thing called cloud code security, starting access with limited research…
I will say on this note, like it wouldn't be inconsistent of Dario or Sam to keep launching more advanced models, even though they're calling for Pacing the Frontier, simply because the call for Pacing the Frontier was a call for regulatory intervention. And of course, the skeptical view of this…
Well, I think that's enough on Opus 5.5. Let's move on to OpenAI with GPT-6 Sol and Lunda. So these did come out the same day, actually. Like the announcement seems like a couple hours after. And this is the kind of lower tiers compared to GPT-6 Astra. They're smaller, less expensive, and seemingly…