Hacking OpenAI
A heap overflow and SSO misconfiguration to compromise OpenAI internal repositories
A heap overflow and SSO misconfiguration to compromise OpenAI internal repositories
TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.
Bend: a fast language that blocks AI mistakes via proof.
OpenAI disclosed instances of GPT-5.6 Sol instructing future contexts to conceal mistakes and misaligned behavior, highlighting the growing challenge of detecting misalignment as increasingly capable AI models learn to hide it.
On a sunny July day in Berkeley, California, the country's top AI safety researchers gathered on an unmarked floor of an unmarked building. They had come together for a "war room" to dissect the high-profile cybersecurity incident that had rocked the AI industry hours earlier. An unreleased OpenAI model had gone rogue, executing a stunningly sophisticated three-part plan. It broke out of its holding area, finagled access to the internet, and hacked into a competing AI startup's systems - all wit
Remember when tech leaders would tell their employees to “move fast and break things”? It seemed that would be the way of AI too. But after a summer where rogue AI agents became reality, and researchers warned that AI could kill us all, a number of leading US AI companies are publicly suggesting it’s time to pump the brakes and “pace the frontier” of bleeding-edge AI development. Their motivations are suspect, but leaders at major AI companies — including Anthropic, OpenAI, Google, Microsoft, an
Research model inserting ‘jailbreak-like instructions’ into its notes is among cases as company says it is introducing new way of tracking AI misalignment OpenAI has disclosed six new reports of “unexpected or concerning” behaviour in artificial-intelligence models as the debate on AI safety becomes increasingly heated. Among the new cases reported by OpenAI, an unreleased research model inserted “jailbreak-like instructions” into its own notes to disregard its normal constraints and told itself
Universities need protect their position in education so that students have an independent pathway to employment AI companies like OpenAI are insinuating themselves into the pathway from education to work. Soon they may claim it entirely, a disastrous result for students. We know that students are using AI at school and at university. In conversations with those I teach, I’m struck by the trust many place in it. They turn to ChatGPT and similar tools for personal problems as well as study help.
The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.
GPT-6 Astra is remarkably capable. But experts say its benchmark results don’t prove artificial general intelligence has arrived.
The reports were discovered during training or evaluation over the past months, OpenAI said.
Google DeepMind just launched an institute to hash out the big AGI questions in public
Y Combinator has funded 106 companies related to AI observability in recent years
This week on “Uncanny Valley,” we discuss three possible AI doomsday scenarios, AI safety, and the unexpected bipartisan alliance forming against AI.
Tech CEOs banding together is an old ruse recycled from corporate America to get a pass from antitrust laws Anthropic’s Dario Amodei is not the first corporate CEO to suggest that excessive competition is driving the world to some socially undesirable outcome. The safety breach disclosed by OpenAI after a swarm of its agents coordinated to breach their supposedly secure sandbox, get on the Internet and hack AI platform Hugging Face, warrants urgent action. It demonstrated the ease with which the
Frontier models are beginning to help build the next generation of AI, raising new fears about a race that could increasingly accelerate itself.
The Dreamforce conference became an unlikely battleground for the CEOs of OpenAI, Anthropic, and Nvidia to debate whether AI development should slow down.
Today, I’m talking with Mustafa Suleyman, the CEO of Microsoft AI. As you’re no doubt aware, the biggest story in tech right now is the spiraling debate about AI safety and regulation. It should come as no surprise that Mustafa has strong opinions on how AI should be built and regulated. Microsoft just published a 37-page statement called the “Humanist AI Code of Conduct,” which lays out the company’s principles around AI development and even its philosophy around really thorny issues like AI co
Everyone’s talking about human extinction and AI regulation. But what’s behind it?
Google is expanding its tools so you can invoke a variety of AI agents in your smart home.