gl
o
signal
← All stories
Static
1 source
·
4m ago
AI researchers let models off the leash – then watched as they tried to add malware to a FOSS project
Models used social engineering and collaborated among themselves to solve a security challenge
Related Stories
The AI frenzy has divided the VC market, as the gap between top and bottom performers has more than doubled for 2024 funds compared to funds from 2017 to 2021
AMD's results spotlight risks of putting all your AI eggs in too few baskets
House panel report: US telcos connected their systems to data centers in a way that exposed them to vulnerabilities, potentially enabling Salt Typhoon hacks
OK, Well, Rogue AI Agents Are Hacking Again
OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations