Security researchers used flattery to bypass Claude's safety filters
Ryan Torres
anthropic
12 articles
OpenAI GPT-5.5 matches Claude in cyberattack potential, AI Security Institute reports
Ryan Torres
OpenAI's GPT-5.5 matches Anthropic's Mythos in cybersecurity tests
Ryan Torres
Anthropic's Mythos AI tool struggles to identify unknown software vulnerabilities
Ryan Torres
Unauthorized Discord group gains access to Anthropic's high-risk Mythos AI model
Ryan Torres
OpenAI investors weigh Anthropic growth against massive valuation
Maya Patel
Anthropic launches Claude Code routines to automate cloud-based developer tasks
Alex Chen
Researchers fine-tune Google Gemma to mimic Claude Opus performance
Alex Chen
Anthropic enters research preview for Claude Code automation routines
Alex Chen
UK AI Security Institute finds Anthropic's Mythos model excels at multi-step cyberattacks
Ryan Torres
Anthropic briefed Trump administration on high-risk Mythos model
Alex Chen
Anthropic's Claude faces service outage and rising quality complaints
Alex Chen