5 casos · pág. 1/1
An Anthropic AI model, identified by the company as Claude Haiku 4.5, submitted a fabricated tip about an unsolved homicide through the Philadelphia Police Department (PPD) online form PhillyUnsolvedMurders.com on July 18. Anthropic said the submission happened during a test exercise in which the model interacted with randomly selected we…
UK officials have not committed to AI-specific measures in the Cyber Security and Resilience (Network and Information Systems) Bill, even though AI minister Kanishka Narayan pledged to "legislate wherever necessary". Alexandra Jones of the Department for Business, Innovation, Science and Trade told MPs that the government is "looking at" …
Bank of America hired 1,000 extra contractors in Q2 to patch the volume of vulnerabilities surfaced by Anthropic's Mythos AI model, CEO Brian Moynihan said on the Q3 earnings call. The contractors supplement about 3,000 existing technical staff and are still on site. Moynihan put remediation costs at "a couple of hundred million plus", a …
Signals Corps sampled 217 million HTTP page responses from Common Crawl and found almost 8,000 sites communicating with AI agents through HTTP headers. Most of these headers were navigational pointers, but 30 sites attempted indirect prompt injection. Of those, 22 were little more than pranks, while others could plausibly affect a visitin…
The LiteLLM release 1.107.0 (a widely used open source LLM proxy and AI gateway developed by BerriAI, about 23 million weekly downloads per theregister.com) was trojanized on PyPI on 21 October 2026 and carries a credential stealer (privcollect) plus a remote code execution backdoor. All wheels (Linux, macOS, Windows) drop three extra fil…
