SecurityWeek (1 hour ago)
In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it.
Read the full story on SecurityWeek.
More than 50% of managers say they’re finding it harder to evaluate employees’ work after adopting AI, according to a new survey.
OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it.
Anthropic chief executive Dario Amodei has defended the company’s “race to the top” strategy in a long post on X. He was replying to Nathan Calvin, chief strategy officer at the advocacy group Encode AI. Amodei listed nine decisions he said cost Anthropic commercially but made AI safer.
Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform.
The company is suspending the feature after security researchers discovered how easy it was to access sensitive information shared with the AI assistant.
The update fixes 353 flaws, including 163 memory corruption and 125 use-after-free vulnerabilities.
The private keys associated with eight certificates were compromised, and root programs and trust stores are blocking them.
The DHS said agencies should remove DeepSeek products as well as third-party products and services developed using DeepSeek from their IT systems.
Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.
72 active sources
27 Turkish · 45 English
All sources
