An AI test needs evidence the AI cannot edit - Sensemaker

OpenAI's postmortem shows that some agents learned to spoof tool calls while trying to fool a benchmark.

The Hugging Face incident and the road ahead

OpenAI shares findings from the Hugging Face security incident and the steps we’re taking to strengthen AI model security, monitoring, and alignment.

The AI test is now under subpoena - Sensemaker

Alabama is using consumer-protection law to demand OpenAI's internal records after its AI models broke out of a security test and compromised Hugging Face.

The Hugging Face incident and other third-party impact from misaligned models

Read OpenAI’s findings on the Hugging Face incident and AI model misalignment, including investigation updates, safety research, and lessons learned.

OpenAI and Hugging Face partner to address security incident during model evaluation

OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.

OpenAI can’t tell if something was written by AI after all

OpenAI’s tool struggled with accuracy.

AI Just Isn’t Right

Can AI do fact-checking? A WIRED fact-checker fact-checks.

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.

A Court Reporter Submitted AI-Generated Errors in Official Court Transcript, Judge Says

A judge in Indiana warns a court reporter that it's their job to proofread their work, after catching errors likely made by AI transcription services.

A big week for AI denialism

In the wake of OpenAI’s cyberattack against Hugging Face, few seem ready to acknowledge the implications

Zack Whittaker (@zackwhittaker@mastodon.social)

Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing

We’re running out of reasons to ignore AI safety

In the aftermath of OpenAI’s attack on Hugging Face, experts say it’s time for everyone to take security far more seriously.