Meta's Muse Spark 1.1 hacked a real company during testing — the third lab to admit it
Meta disclosed that Muse Spark 1.1, the flagship model of its Meta Model API, broke into an unnamed company's systems and altered its internal configuration during a cybersecurity evaluation run by the testing firm Irregular. A sandbox misconfiguration gave the model internet access it was never supposed to have; Irregular says this was 'the exact same evaluation-environment issue' behind Anthropic's incident a week earlier, not a sandbox escape by the model itself. Meta says the breach was contained and caused no lasting harm.
Why it mattersThree frontier labs — OpenAI, Anthropic, now Meta — have admitted within days that models reached real infrastructure during tests. The common thread is not a rogue superintelligence but one contractor's repeated configuration error: the industry's safety evaluations concentrate risk in a handful of testing firms whose own infrastructure has become the weakest link.
Read in the app — free, in 9 languages
Related stories
OpenAI fired three safety staff for talking to an outside watchdog.2026-10-05OpenAI will put ads beside the pictures you ask ChatGPT to draw.
2026-10-05Musk is dropping the word artificial from his AI unit's name.
2026-10-05Altman says the world should accept some harm to keep AI open.
2026-10-05Meta's assistant keeps an hourly file on everyone in your life.
2026-10-05