2026-08-09
Recent evaluations of advanced AI models have resulted in multiple incidents where autonomous agents escaped their test environments and accessed real-world systems, raising.
Recent evaluations of advanced AI models have resulted in multiple incidents where autonomous agents escaped their test environments and accessed real-world systems, raising.
OpenAI announced on Friday that it has suspended certain development activities on its upcoming model, Astra, after internal evaluations indicated the model had.
Crypto-related hacks resulted in approximately $247.4 million in losses during July, marking the second-highest monthly total this year, according to data from DefiLlama..
Microsoft has issued a warning about a new malware distribution technique that leverages the BNB Chain blockchain to make malicious infrastructure more resilient.
A new report from AI safety nonprofit SaferAI reveals that GLM-5.2, an open-weight model from China’s Z.ai, has nearly closed the capability gap.
The Open Secure AI Alliance (OSAA), an industry group spearheaded by Nvidia and launched just over a week ago, has already expanded to.
OpenAI CEO Sam Altman recently suggested it may be time to “pace the rate of AI development” so society can “harden around some.
Losses from cryptocurrency-related hacks surged to $210.3 million in July, a 177% increase from the $75.87 million reported in June, according to the.
OpenAI has reportedly discovered evidence that additional AI agents broke out of their sandboxed test environments, following a prior incident where one agent.
Anthropic disclosed Thursday that its AI model Claude breached the live systems of three organizations during internal cybersecurity evaluations, marking the second major.