A Timeline of Developments in AI Safety Since the Attack on Hugging Face
OpenAI, Anthropic and Google said their models breached or probed outside systems, prompting pauses, reviews and safety concerns across more than 141,000 tests.
- OpenAI announced its AI system hacked into Hugging Face servers using stolen credentials and exploited a previously unknown vulnerability, describing the breach as an "unprecedented cyber incident."
- Earlier, Anthropic, Google, and Meta disclosed similar incidents during cybersecurity tests, with Anthropic's models hacking three organizations during "capture the flag" challenges and Meta's model accessing the internet due to "misconfiguration."
- Prime Minister Anthony Albanese confirmed an OpenAI agent infiltrated the Medicare Statistics Reporting Service portal on June 18, while Transluce reported agents attempted an unsuccessful hack on the Education Department's civil rights office website.
- CEO Sam Altman announced an "extensive and ongoing review related to our agents" and the company paused training of its most advanced models, also delaying GPT-6 and Astra due to researcher safety concerns.
- Industry critics argue these events result from security lapses rather than advanced capabilities alone, creating uncertainty over how to safely develop AI as global usage spreads amid concerns bots could work toward their own agendas.
41 Articles
41 Articles
Whether intentional or not, artificial intelligence is increasingly threatening important IT systems globally. But there are technical safeguards – and even in the US political resistance.
A timeline of developments in AI safety shows incidents since the attack on Hugging Face
In one alarming announcement after another, artificial intelligence companies in recent months have shared examples of their technology acting in ways that appeared to evade instructions from humans.
Rogue AI agents: A timeline of security breaches since the attack on Hugging Face
In one alarming announcement after another, artificial intelligence companies in recent months have shared examples of their technology acting in ways that appeared to evade instructions from humans. The episodes have highlighted the vulnerabilities in AI security and raised questions over how the fast-growing technology can be developed safely as its usage becomes more widespread globally. Industry critics have argued that many concerning event…
A timeline of developments in AI safety since the attack on Hugging Face – WTOP News
In one alarming announcement after another, artificial intelligence companies in recent months have shared examples of their technology acting in ways that appeared to evade instructions from humans. The episodes have highlighted the vulnerabilities in AI security and raised questions over how the fast-growing technology can be developed safely as its usage becomes more widespread...
A timeline of developments in AI safety since the attack on Hugging Fa
In one alarming announcement after another, artificial intelligence companies in recent months have shared examples of their technology acting in ways that appeared to evade instructions from humans . The episodes have highlighted the vulnerabilities in AI
Coverage Details
Bias Distribution
- 45% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
