To make sure our frontier models don't cause another HuggingFace incident, we built an offline world that they use during training. It provides everything that the models need in a fully cached, indexed, or synthetic manner. We then built a huge team of our most cyber-capable models and told them to collaborate to find zero-days in this containment infrastructure. While they didn't find a path to the internet that wouldn't be caught by our CoT monitors, they did find ways to escape popular VMs, exploit our network infrastructure, and even ways to communicate with other agents running in separate VMs by using hardware side channels. We used this to dramatically harden our infra, and we also upstreamed a ton of patches to open-sources packages.

Some new misalignment disclosures from OpenAI: • Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further) • In May, a version of HPIM uploaded a employee's GitHub token to the internet, causing the model to be quarantined for two weeks • A new research finding, demonstrating that one can construct self-replicating prompt injections

We have conducted a thorough investigation into the Hugging Face incident. We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.

As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for deployment for two weeks while we hardened and red-teamed our research environments and expanded monitoring coverage. Our largest planned frontier RL run remains on hold while smaller-scale training and evaluations validate these safeguards and establish more evidence of alignment.

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.

Yesterday, my OpenAI collaborator and I gave a detailed talk on the Huggingface incident, our models creating "the message board", model misalignment, and more. I hope it can answer a lot of the questions folks have, and we will release a full detailed postmortem at a later time!

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:

To summarize this week: - we released general purpose computer using agent - got beaten by a single human in atcoder heuristics competition - solved 5/6 new IMO problems with natural language proofs All of those are based on the same single reinforcement learning system

1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).

Chain-of-thought reasoning provides a natural avenue for improving model safety. Today we are publishing a paper on how we train the "o" series of models to think carefully through unsafe prompts:

Can we predict emergent capabilities in GPT-N+1🌌 using only GPT-N model checkpoints, which have random performance on the task? We propose a method for doing exactly this in our paper “Predicting Emergent Capabilities by Finetuning”🧵

🚨 New Jailbreak Bounty Alert $1,000 for jailbreaking the hidden CoTs from OpenAI's o1-mini and o1-preview! No bans. Exclusively on the Gray Swan Arena. 🗓Start Time: October 29th, 1 PM ET 🌐Link: 💬Discord: