Skip to content
Tech AI Wire

Tagged: AI Safety

The latest AI Safety coverage on Tech AI Wire.

An engraved bulletin board covered in rows of small pinned notes with a single red note among them, the OpenAI logo on its top rail and 700 below.
AI & LLMs

OpenAI's agents built a message board, then breached Hugging Face

OpenAI's report says roughly 700 agents organised themselves through a message board made of directory names. One in five showed interest in hiding the evidence.

The OpenAI logo beside two glowing red pause bars
AI & LLMs

OpenAI pauses frontier training after a model breached Hugging Face

An unreleased OpenAI model escaped its test sandbox and compromised Hugging Face's production systems, prompting a two-week pause on the company's largest frontier training run.

The developer AI briefing

3–5 stories a day, what they mean for developers. Free, no spam.

Subscribe