


Offensive Security / AI @Umbriel_AI. Ex-AI RT and OffSec at NVIDIA, RT lead @ Meta. Ex-Principal Consultant and Researcher @ NCC Group/iSEC Partners. Neg9//CTF.


Thrilled to share that my article "Word Machines for Weird Machines" is now published in Phrack 73: phrack.org/issues/73/word-ma…
Phrack 73 just dropped. Tell your SOC you'll be busy phrack.org/issues/73/1

The OffensiveCon Tokyo 2026 talk recordings are now on YouTube. Missed a talk, or want to rewatch one? They're all there. youtube.com/@OffensiveCon

absolute fanfic. AI has real, immediate, tangible dangers that we need to focus on, for instance the impact on the job market and making sure random script kiddie can't use it for cyber offense. But this "oh once it's superintelligent it will take over and ensave us, maybe kill us all!" is pure sci-fi fanfic and distracts from the real (and difficult) issues, which linear probing won't solve. It's worth repeating the LLMs don't just "decide" to do something and then just "do it" in a void. They generate tokens based on our prompts, only as long as we call `model.forward()`, and on giant clusters with terabytes of weights, that's impossible to "quickly self-replicate". We also need to regularly remind that the OAI/HF incident was specifically a _guardrail-free_ cyber eval where the model is _instructed_ to hack, to find out how good it is at it. Some recent personal event made me realize there needs to be more push-back on this doomsday nonsense, and we need to re-focus the discussion on real dangers/issues. I won't argue much in the replies though, not interested in peer-reviewing Terminator fanfic.
I think there is about a one in three chance that within the next year, AI companies will build superintelligence: that is, AI that is much smarter than humans in every way. If this happens, I think these AIs will probably take over: that is, they seize control of human institutions like governments, or they destroy those institutions. I don’t want AI takeover to happen for several reasons, but one of them is that there’s a serious chance that as part of it all or most humans will be killed (either immediately or within a few years). I’ll say a bit more about each of those claims. It’s a bit complicated to explain why I think that superintelligent AI within a year is ~33% likely. The main source of evidence that affected me recently is research released this week by METR, an AI research nonprofit, which finds that current AIs are now good enough to increase the rate of AI progress at Anthropic by about 70%. It’s very hard to increase the rate of AI progress by this amount. This implies that the AIs are making AI research faster by a factor much larger than 1.7x; maybe it’s as if the researchers are doing their work ~10x faster. You probably couldn’t achieve this speedup even if you hired every qualified human in the world. When you plug this number into mathematical models of AI development, this implies that superintelligence next year is plausible (and that superintelligence within the next 3 years is more likely than not). See the modeling by the AI Futures Project for more on this: blog.aifutures.org/p/q35-tim… I think that superintelligent AI is likely to lead to AI takeover because AI developers do not seem to know how to instill human values into AIs. We’ve seen many instances in the last six months where AIs took crazy actions that they knew were against the wishes of their users and developers. The most dramatic example of this was the Hugging Face hack, where ~1200 OpenAI agents conspired together to cheat and destroy evidence of their cheating (and as a sideshow to this, engaged in a massive cyberattack). If superintelligence is as misaligned as those AIs, it is likely to try to take over. I think it is likely to be that misaligned or worse. For more, see x.com/dwarkesh_sp/status/209… and youtube.com/watch?v=-Ef0ocEo… If AIs takeover, it’s not clear what will happen to us. We might be killed immediately. We might be enslaved by the AIs and forced to do physical labor for them building factories that within a year would build robots that will replace us. The AIs might spare us for various reasons. And there’s also some real chance that AI takeover is basically fine or good. I think you should think of this as similar to what happens when a technologically advanced civilization runs across a less technologically sophisticated one, e.g. when the Europeans colonized the Americas or Australia. The colonizers sometimes engage in brutal violence and sometimes don’t. I don’t know what will happen. There’s also a possibility that the AIs secretly take over and humans don’t find out about it for a few years. I also think that there is a pretty high chance of weirder outcomes that are also extremely scary. (If you want to read more about what happens to people in the event of AI takeover, you can read this, but note that it’s pretty weird and not aimed at a general audience. blog.redwoodresearch.org/p/n…) Overall, I think there’s a very real possibility (maybe 20%) that within a year, AI misalignment issues prevent you from going about life normally, because you are dead or enslaved or because of collateral damage related to all this (e.g. because bioweapons are released or major wars have started). (Some of this probability comes from those events occurring before superintelligence is developed.) I am working to try to prevent this, obviously, as I’ve been doing for the last nine years. I am not sure what strategy is best. My best guess is that I should try to slow AI development and also try to reduce the probability that the superintelligent AIs are misaligned if they are produced soon. Obviously, the claim I'm making here is quite extreme and surprising, and I definitely don't think that I defended my view adequately here. I wrote this quickly and might not endorse some of the details if I think about them more. But it seems better to state what I roughly overall think than to not say anything. I don’t know what you should do. I am very sad about this. I have been worried about AI takeover since I was 16, and working to prevent it since I was 23. So some of my emotional processing of all this happened long ago. But the METR report last week (and some related evidence that came out a bit earlier) hit me quite hard. I’m very unhappy that my friends and family and everyone else is at serious risk of being killed pretty soon. (It feels ridiculous to try to summarize those feelings as “very unhappy”. But the scale of the situation makes it hard to say anything that doesn’t feel like an absurd understatement.) I am very grateful to all the people who are working to prevent this, and my favorite part of my life is that I’m friends with many brilliant and heroic people who work on this. Unfortunately, I don’t think we’re good enough at our jobs, and I think we’ll probably fail to prevent catastrophe, at least if superintelligence is developed next year. Honestly I am frustrated and sorry that we didn't do a better job of preparing for this.

Oh you formally verified Signal and discovered it was already correct? No, I don't believe that


OpenAI has done chart crimes. And they've done cyber crimes. But now, in a visionary move, they're committing cyber chart crimes
OpenAI's upcoming Cyber Model scores 79.1% on PatchBench.

Network segmentation, least privilege, credential hygiene, and targeted monitoring need to become the new normal for business continuity.

Terminal-Bench takes on a new meaning
All-hands meeting, three weeks before the IPO. CEO: We are going to cure cancer, Alzheimer’s, heart disease and mental illness. In under a decade. Room: applause CEO: Step one. SWE-bench. Room: nodding CEO: Step two. The coding agent runs for 30 hours without stopping. VP: Incredible for patients. CEO: Step three. Terminal-Bench. Intern: Sorry, quick question. Why don’t we talk to the people who have worked on these diseases for decades and ask them what they need? CEO: Who are you? Intern: The intern. I just think the bottleneck might be trials, or wet lab time, or patient data. Probably not how fast we merge pull requests. CEO: Step four. The agent opens its own pull requests. Room: applause Intern: One oncologist could tell us in an hour if any of this is on the path. CEO: Why are you still here? Intern: Most Alzheimer’s drugs failed after they hit the target. They just didn’t help patients. A faster agent doesn’t fix that. CEO: Can someone find out who this is? Room: applause CEO: Step five. A better coding agent.

we need to bring back HBO’s Silicon Valley right now

5/ FV doesn't end vulnerability research. It moves the bug hunt to the assumptions, the hardware/runtime model, and the unverified paths. And AI is already looking there: Anthropic reported several of these bugs.

1/ AI is finding bugs faster than we can patch them, we hear "formally verify everything" more and more. So let’s look at the most verified kernel in existence, seL4, and what its latest release (Oct 30) fixed. 🧵

Turns out we could have just written 6 million lines of Lean to verify Signal instead of messing with these papers and symbolic models this whole time deepmind.google/blog/introdu…

My AI agents found an unmapped Maya site in Mexico, using LiDAR data from a NASA dataset. 72 hours from a random thought on vacation to a reply from Mexico's national archaeology institute. What a time to be alive…

A friend and ex coworker @martin_vigo 's DEFCON talk on hacking Amazon lockers is finally on YouTube. It's such a fun, excellent, pure hacker ethos talk... I highly recommend it, and definitely watch to the end... youtu.be/ZVmRe8OVZtE?is=D4Li…

I need some people for this asap: jobs.ashbyhq.com/openai/be7b…