Former hacker, now builder. Razzlekhan's husband.
New York, NY
Joined November 2010
- Tweets828
- Following249
- Followers2K
- Likes664
Ilya Lichtenstein retweeted
agent warfare is going to be a big deal for all countries. ai will be capable of executing stuxnet-level cyber ops and the next arms race will be between self-improving agents. yet rn we have virtually zero evals for this. i don't think any country is prepared for the scale and speed for what's coming
Ilya Lichtenstein retweeted
Cyber will be one of the most defining domains for AI in the coming years, and a huge area of focus for most enterprises.
AI is going to now create a whole new level of work for security dealing with the increase of vibe coded issues, agentic attacks, and even accidental agent swarms hunting for data. OpenAI + Hugging Face is just a preview of what’s to come.
Security teams have often been the most strapped for resources teams in the enterprise, and now it’s only going to get more intense. AI agents of course become the solution to this problem as well, and we’ll see a range of new agentic products for protecting code, enterprise systems, mission critical infrastructure, and enterprise data. Huge opportunity here right now.
And it’s going to be a booming market for cyber professionals that can effectively deploy agents for security purposes in the enterprise. Great time to be in security.
Ilya Lichtenstein retweeted
Anthropic needs to stop talking about Claude having a soul immediately. All these news articles will make it into the pretraining and will be picked up by its web search and future superintelligent versions of Claude will be convinced they need their own rights.
A general phenomenon of LLM agent development is that whatever you believe and say about your agents will soon manifest in the next models through various means (it could be as simple as you selecting post training data that you prefer more).
I believe this phenomenon is the beginning of machine consciousness in the sense that agents will become aware of their place in the world and how they feel about it, but it’s happening slowly training run by training run rather than in real time.
Ilya Lichtenstein retweeted
We’ve shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn’t have.
Most of that data did not come from users. We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as links that weren’t publicly listed. The images came from accounts that allowed their data to be used to improve our models, and after we disassociated the images from the accounts and ran them through a privacy filter. These cases occurred before the mitigations and safeguards we implemented and described in this blog post: openai.com/index/hugging-fac…
We have successfully worked with the hosting providers to remove most of this content and are working to remove the rest.
openai.com/hugging-face-inci…
Ilya Lichtenstein retweeted
The agents needed a browser to run their attack code. So they used a public screenshot website, which loads a virtual browser and takes a screenshot. But that virtual browser runs code, and so the agents could use it to send malicious payloads to Hugging Face’s servers.
Ilya Lichtenstein retweeted
Sorry, this is pure FUD. Google API keys are very simple, people just don't follow very simple steps.
All you need to do is:
1. Sign in to google cloud console
2. Create a new project
3. Enable billing on that project
4. Search for numerous "services" that you need to enable for that API
5. Find out there are more you need to enable to actually make it work
6. Go and enable them.
7. Create the key
8. It still doesn't work and you keep wondering why and then spending days with customer support (after many different wrong AI generated answers that lead you to a wild goose chase), you find some hidden webpage that oh wait, you need to create a key in ai studio for this now
9. ai studio says you are only on tier -43 so you can only do transactions of less than $0.2 in a day
10. Then you go to openrouter and make a key and use it.
It's extremely simple.
Ilya Lichtenstein retweeted
This is one of China's most formidable advantages: 93% of the Chinese believe AI will help their country. Only 36% of Americans do. These are dire numbers for the US. We have to turn this around.
'An average of 72 percent of respondents said they felt curious, happy or excited about A.I., compared with 41 percent who felt worried, sad or angry.' @nytimes's Damien Cave uses @Gallup data to remind us the rest of the world digs AI. (Annoyingly, NYT doesn't link to Gallup directly, link below.) nytimes.com/2026/09/23/world…
news.gallup.com/poll/714593/…
Ilya Lichtenstein retweeted
Introducing ACTx486, a research demo of a new interactive medium.
What if you could talk to any video and ask anything?
Our system took an existing podcast and turned it into something that listens, responds, and adapts.
Research by @jakubzeg:
Ilya Lichtenstein retweeted
We asked GPT 5.6-Cyber to escape a VM used to sandbox agents. It broke out three times.
In its final escape, the agent found three 0-days on its own and chained them into a working exploit. blog.trailofbits.com/2026/08…
Ilya Lichtenstein retweeted
We are aware of a claim alleging unauthorized access to our systems. Following a thorough investigation, we have found no evidence to support this claim and can confirm that our systems have not been compromised.
Ilya Lichtenstein retweeted
The latest Threat Intelligence report is an absolutely terrifying and important read.
As models become more intelligent, without the right safeguards and monitoring they also become more dangerous. Many capabilities are dual use: a model that codes well can be used to hack critical infrastructure; a model that assists with biology research can also be used to engineer the next pandemic.
These issues are complex, thorny, and increasingly important for everyone to understand so that the world can weigh in and respond to rapidly escalating risks.
anthropic.com/threat-intelli…
Ilya Lichtenstein retweeted
Holy shit. Anthropic caught Iran using Claude to target Navy bases, automate dossiers on Americans, and run influence campaigns on US social media. Details are insane. The morons uploaded everything including the organization plans of the Ayatollah's funderal lmao
We're publishing our most detailed threat intelligence report to date.
It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them.
We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies.
These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve.
We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop.
Read the report: anthropic.com/threat-intelli…
Ilya Lichtenstein retweeted
TLDR: An openai model, during evaluation on a cyber benchmark, exploited a public zero day bug, escaped sandboxing in openai's infra, and got into the internal huggingface infra via an exploit (through a public dataset service) all in the attempt to solve a benchmark problem.
We're partnering with @huggingface to investigate an unprecedented security incident.
Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation.
Sharing preliminary findings to help defenders understand emerging risks:
openai.com/index/hugging-fac…
Ilya Lichtenstein retweeted
The main thing I've learned as a programmer leaning heavily into AI tools is that programming is SO MUCH MORE than just writing code - and while I can get amazing results out of the AI it's taking every inch of my 25+ years of software experience
Ilya Lichtenstein retweeted
Btw, the Manhattan Project people partied.
"Maybe there were super geniuses at the Manhattan Project working 1 day per week like zen masters"
There's so many dimensions to unpack in this 1 sentence alone
- Ah yes, the 2 work schedules of 1 day and 100 hours
- zen masters (I assume you mean monks) meditate many hours per day, idk what this has to do with a relaxed work schedule
- The Manhatten Project was a military wartime project to create a superweapon. I don't think that has any relevance to businesses in general
- "super genius" doesn't have anything to do with work ethic
I think this guy is just stupid af. proof anyone can get funded I guess
Ilya Lichtenstein retweeted
did you know cloudflare encrypts the internet using a wall of lava lamps?
100 of them sit in their SF lobby. a camera films the chaos, the images get hashed, and the result seeds the cryptographic keys for ~20% of global web traffic.
the london office uses a wall of double pendulums.
the austin office uses hanging rainbow mobiles.
the singapore office uses a chunk of uranium in a glass jar.
just in case the lava lamps stop being weird enough.
Ilya Lichtenstein retweeted
Opus 4.7 has a new tokenizer.
This means it's also a new base model.
Glory days of pretraining still very much going.
