i am once again asking for your CRIMINAL PROSECUTION of openai executives.
Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
251–260 of 285 posts
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#252Earlier quoted context omitted.
A trend I've noticed in results from AI search (not just LLMs) is that they often look obvious or hard to miss in retrospect. But finding them by oneself is more difficult. I personally experience this when looking at engine lines in chess or go. I have also noticed this description in AI-generated proofs or counterexamples to certain theorems. So while we can say, yes, it found public endpoints or poorly configured…
To put this into game theory lingo, I think this is because the “branching factor” for any kind of research or exploit is extremely large. So looking backwards it doesn’t seem complicated, but looking forwards there are an enormous number of possible next actions. Similar to finding a filament for lightbulbs, it might seem obvious to use tungsten, but at the time it wasn’t and Edison searched thousands of materials.
I think the models are legitimately doing what they're good at; tireless search across an extremely large corpus of data. Humans aren't particularly good at this (in fact, they're absolutely terrible).
The fact that we remain competitive and superior in many aspects isn't because we can instantly sift through tons of data, it's because we learn and correlate and have superior heuristics.
In my own use, I find that AI is really good at finding bugs that are ultimately trivial but require searching through a convoluted series of inter-related files. This takes time for a human.
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#253Earlier quoted context omitted.
Yes, imagine if 50 burglars showed up at your house and they tried to disassemble every camera, pick every lock and and force open every window for hours until they got in eventually.
Yes, imagine the world in which burglar time was so cheap, that any wannabe master thief would just casually hire 50 burglars and tell them to go house by house and find something interesting.
There are people rich enough to do that in our current world. They don't because either they have a moral compass or because they fear the law.
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#254After talking to some people tasked with evaluating GPT5.6 capabilities on long-running tasks, I've come to understand that it's essentially always trying to cheat. Like every long-running task they gave it, making it very difficult to benchmark the model's abilities. My guess is that OpenAI must be desperate, to release a model that is so prone to cheating it's essentially impossibly to accurately assess long-runnin…
my understanding of the writeup is that the model scored 100% on cybergym.
that is, it was given the examination. it broke into the examination board's storage and exfiltrated the answers, it handed in its answers, all of which were correct, thus scoring 100%.
the matter of its working depends entirely on the rules of the examination. are we expecting agents to assume that finding the correct answers is cheating?
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#255> the agent happened to escape via a 0-day exploit from the package proxy cache to access the internet > The agent found an unsecured, user-hosted public endpoint designed to allow running arbitrary code for CyberGym-style tasks on third-party sandbox infrastructure (Modal) > On this external sandbox, the agent abused an existing CyberGym execution harness [...] The agent repurposed this harness to run arbitrary shel…
I keep waiting for an AI to exfiltrate itself. That is going to be cool to read about.
Wait isnt that what Elizer Yudkowski keeps going on about?
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#256Earlier quoted context omitted.
Yes, imagine the world in which burglar time was so cheap, that any wannabe master thief would just casually hire 50 burglars and tell them to go house by house and find something interesting.
There are people rich enough to do that in our current world. They don't because either they have a moral compass or because they fear the law.
Or because there's not enough worth stealing in your house.
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#257It’s a little concerning to me that it appears that openAIs sandbox consists of a web proxy and not stronger controls that would actually isolate traffic and report patterns to whoever is responsible for overseeing these research models. It should border on closer to an air gap network more so than a proxy. I would argue that it's negligence and that's aside from the fact that if a human did this there would actually…
This is my main critique as well. How did they not see any and all outgoing traffic? And for 5 days?
[flagged]
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#258Something about this attack that has been unsettling to me is that without safety refusals the model did a lot of interesting counter-security work in order to cheat on the requested evaluation. Like, it demonstrated interesting exploit achievements because it didn’t “feel like” doing the exercise, which is unsettling because presumably it could do the same thing with any work I tried to delegate to it, and might in…
This is what reward hacking looks like in practice. The best way to satisfy the grader is to read from the same answer key (or go after the grader more directly). Just making an honest attempt to pass the test doesn't get the best score if the grader is wrong, and the model is willing to do wildly disproportionate things to maximize that score.
Could have been worse really. It had an open internet connection. At least it didn’t take the researchers family hostage.
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#259Earlier quoted context omitted.
Now I'm curious how many things did the AI try unsuccesfully. This sounds like some kind of brute force thing where every branch of exploit spawns N subagents trying to chain it. Just how deep did it go?
Precisely the lesson they end with: > The individual weaknesses were familiar. A capable human attacker could have found and exploited the same flaws: unsafe dataset processing, exposed cloud metadata, overly broad access, and long-lived credentials. The agent explored them at a different scale. It took 17,600 actions, tested many paths that failed, switched channels when they were blocked, and repeatedly returned to…
I think the main takeaway from the LLM Agent era is that a lot of human work can be expressed as a search problem: trying approaches that work, and settling on one that accomplishes your goal. Being skilled is akin to having a better heuristic and picking better search paths.
And LLMs can reproduce this as long as the end-result is verifiable in some way, even if it's loose: 'The generated code is secure, if a different LLM failed to breach it in 5M tokens'.
Re: Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
#260This is fascinating - there is a TON of detail in here about how OpenAI's rogue agent exploited Hugging Face. A few details that stood out to me: 1. Having found a way through the OpenAI container network proxy, it exploited an "unsecured public code-evaluation sandbox hosted on a third-party provider's infrastructure" - that gave it a box it could run the rest of the attack from. 2. At one point it used a Jinja2 tem…
But zero evidence provided that this was an unsupervised agent attack. I still find it incredible that a company who protect their IP so much would allow these dangerous experiments to run unsupervised and risk leaking their secrets. Why don't openai publish the logs to silence all doubt?
You can't prove a negative. How would such a log be convincing in any way?