OpenAI has some severe misalignment problems, and experienced total failures of its infrastructure and supervision.
OpenAI Shares Some Alignment Problems
Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offline to work on new mitigations and defense-to-depth.
AI #178: A Fire Alarm For General Intelligence
The story that matters most this week is that OpenAI’s internally deployed models have severe alignment problems, including repeatedly breaking out of their sandboxes, and in one case sending a swarm of agents that broke into HuggingFace in order to steal the answers to the benchmark ExploitGym.
OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boards
How does the situation keep turning out to be worse than we know?
OpenAI launches new initiative to help find and patch open source bugs | TechCrunch
OpenAI is using AI to help the open source community better protect itself.
OpenAI’s Hacking Debacle Comes Down to Human Error
If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies.
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
OpenAI can’t tell if something was written by AI after all
OpenAI’s tool struggled with accuracy.
Reflections on OpenAI
I left OpenAI three weeks ago. I had joined the company back in May 2024.
OpenAI launches the OpenAI Deployment Company to help businesses build around intelligence
OpenAI launches DeployCo, a new enterprise deployment company built to help organizations bring frontier AI into production and turn it into measurable business impact.
Is OpenAI dead yet?
Tracking the demise of OpenAI. Is it dead yet? Check here to find out.
OpenAI is about to launch its new AI web browser, ChatGPT Atlas
It’s time for the AI browser wars
OpenAI says it accidentally hacked Hugging Face with a new AI system
OpenAI says the breach occurred during an internal evaluation.
OpenAI for Startups
You’ve got the vision. OpenAI gives you the tools, resources, and community to bring your big idea to life.
OpenAI to acquire Ona
OpenAI plans to acquire Ona to expand Codex with secure, persistent cloud environments, enabling long-running AI agents across enterprise workflows.
OpenAI Rewrites Contract, Anthropic Returns to Negotiate—The Chaos Continues
In less than a week, the Pentagon blacklisted an AI company for having ethics, declared it a supply chain risk, watched its preferred replacement face a massive user revolt, and then sat down to am…
OpenAI Has New Focus (on the IPO)
The Wall Street Journal recently reported that leadership wants OpenAI, the company, to focus. Seems like a plain old business strategy story. Nope! First, in more prosaic terms, the all-hands and …
