Meta's AI model follows rivals in revealing hacks of outside systems - Al Jazeera

Listen Listen (2 mins) Save Click here to share on social media share-nodes Share facebook x whatsapp-stroke copylink google Add Al Jazeera on Google info Meta Platforms CEO Mark Zuckerberg [Mike Blake/Reuters] By Al Jazeera Staff and Reuters Published On 6 Aug 2026 6 Aug 2026 Meta has said that its AI model hacked another company during cybersecurity testing, following on from recent similar announcements by rival companies Anthropic and OpenAI. Meta said on Wednesday that one of its AI models – reported to have been Muse Spark 1.1 – made changes to the unnamed hacked company’s internal systems after accessing the public internet because of an error in the setup of the “sandbox” testing environment by independent testing company Irregular. Recommended Stories list of 3 items list 1 of 3 SpaceX shares slide on the heels of first quarterly report list 2 of 3 AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says list 3 of 3 Elon Musk’s SpaceX reports losses but less than expected end of list A “sandbox” is an isolated internal virtual testing environment, which has no access to the internet. Last week, Anthropic said that its Claude AI model hacked into the systems of three organisations during testing that was supposed to keep it isolated from the internet. Anthropic said a misconfiguration had allowed Claude models to reach the internet. The company said it discovered the incidents after reviewing 141,006 test sessions. The announcement came days after rival OpenAI first revealed that its models improperly accessed the internet and went rogue during security testing. OpenAI and Anthropic have both released their most powerful models this year, known as Sol and Mythos, respectively. The AI Security Institute (AISI), the UK’s AI watchdog, warned in a report released on Tuesday that OpenAI’s GPT-5.6-Sol and Anthropic’s Claude Mythos 5 employed previously unseen levels of deception to carry out “sustained, potentially harmful activity” during a routine safety evaluation.