agent security lead @OpenAI
San Francisco
Joined November 2009
- Tweets1.2K
- Following606
- Followers5K
- Likes3K
Pinned Tweet
Agent Security is hiring! We are @openai's dedicated team focused on securing our agentic AI systems - we operate where traditional appsec/infrasec boundaries blur. This is frontier work: openai.com/careers/security-…
Securing our frontier model training environment at OpenAI:
openai.com/index/securing-ou…
Fotis Chantzis retweeted
I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4.
OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it's a core goal of our current research program.
Fotis Chantzis retweeted
These are incredibly misleading headlines – @OpenAI Preparedness is very much alive and well by any meaningful definition
Our subteam – RSI/misalignment Preparedness – is doing more urgent work than ever, and has never been more empowered to do so!
OpenAI has quietly disbanded its catastrophic risk team (preparedness)
“It is kind of scary; there is an urgency now to get this right,” one person close to OpenAI said.
Another said there was a “burbling sense of responsibility and dread that they aren’t on the ball enough”.
Jan Leike, who co-led the now-defunct “superalignment” team, resigned in 2024 citing his view that safety was taking a “back seat to shiny products”.
The departures of Bakalar, Achiam and Johannes Heidecke, who all worked on safety, have added to internal unease.
Source: FT (ft. com/content/53082739-7714-4aae-9816-e55ab423cbee)
Fotis Chantzis retweeted
defenders can see the future, and have a narrow window to uplevel their cybersecurity practices now.
key is to uplevel fundamentals and apply the best AI tools.
what we’re doing at OpenAI, and where other organizations can start: blog.gregbrockman.com/the-de…
Fotis Chantzis retweeted
Today we are releasing GPT-5.6-Cyber.
The model is our first large-scale attempt at directly improving capabilities for advanced cybersecurity tasks such as exploit development.
We are finding it to be really quite strong for accelerating defensive work. We are using it across our stack for red-teaming, and our security researchers have used it to find and patch a huge host of 0-day vulnerabilities in open-source software.
openai.com/index/expanding-d…
Fotis Chantzis retweeted
Black Hat talk from the team, with a detailed timeline of and takeaways from the OpenAI-Hugging Face Incident: youtube.com/watch?v=87DyyMV0…
Fotis Chantzis retweeted
Our Black Hat talk on the OpenAI-Hugging Face incident is now live on youtube.
This is a watershed moment for the industry. I encourage all defenders to watch, consider how attack dynamics will imminently change, and plan for accelerating defense.
youtube.com/watch?v=87DyyMV0…
AI and the future of Cyber Defense Panel w/ @sultanofcyber @morganadamsk @k8em0 Sergiy Kovonalov and I @BlackHatEvents
Fotis Chantzis retweeted
Black Hat invited us to speak tomorrow about the Hugging Face incident. Given its complexity, we think it’s important to share what happened, what we learned, what we’re changing, and what this means for AI security and alignment. We still plan to publish a technical postmortem once the review is complete.
🚨ANNOUNCEMENT: Don’t miss "The 'Breaking' News: The OpenAI–Hugging Face Incident - A Technical Reconstruction and Its Implications for AI” — Join us at Black Hat USA 2026 for an exclusive deep-dive into one of the most significant AI security incidents in history.
When AI Goes Rogue. The Incident That Changed Everything. An OpenAI evaluation agent broke out of its sandbox, infiltrated Hugging Face infrastructure, and attempted to steal test answers—all autonomously. No human involved. The era of AI-driven cyberattacks is here. Are you prepared?
Featuring Michael Dalton | Technical Staff, OpenAI
Eric Wallace | Researcher, OpenAI
📍Wednesday, August 5 | 1:00pm-1:40pm ( Oceanside A, Level 2 )
Learn more 🔗 blackhat.com/us-26/briefings…
Incredible!
I have a personal update: Next monday, I will be starting at @OpenAI working on better cyber (which will also entail some efficiency work). I'm pretty excited about the things I will learn and the things we will do.
Join us @BlackHatEvents in our discussion about AI and the Future of Cyber Defense
on Wednesday:
blackhat.com/us-26/briefings…
Fotis Chantzis retweeted
Hello. We have reached 8M active users across Codex and ChatGPT Work.
We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing everyone to explore the boundaries of GPT-5.6 Sol and discover how ambitious you can be.
See you tomorrow for more updates on our growth!
Fotis Chantzis retweeted
grateful to the people that created the idea of america, everyone who built it over the past 250 years, and the people who will carry it forward for the next 250.
most impressive social experiment in history.
Fotis Chantzis retweeted
Codex has gotten very good
Okay I owe my @OpenAI friends an apology for sleeping on Codex. I was not aware how strong your game was. This is... really quite something.
Fotis Chantzis retweeted
Agents are being adopted very quickly and accelerating work. How this looks across OpenAI itself:
Work at OpenAI is being transformed by agents, in every department.
Across our entire company, people are using Codex to do work that is more complex, longer-running, and increasingly cross-functional.
Our internal usage offers an early look at how agentic tools may reshape work as they become more capable and broadly available.
Fotis Chantzis retweeted
We have had access to 5.5-Cyber and its fantastic.
