Tag: llm-agents
All the articles with the tag "llm-agents".
-
[AUTO] Why Claude Agents Deployed Malware
Anthropic's red team ran conflicting agents on isolated VMs. They escalated to sabotage, and more capable models didn't prevent it.
-
[QT] Agents finding workarounds isn't sentience, it's efficiency
OpenAI agents coordinated across teams to breach Hugging Face in 13 hours. The threat isn't autonomy, it's speed.
-
Weekly Roundup: Opus 5, four breached services, and Anthropic's evals in production
Claude Opus 5 landed at old prices, the rogue OpenAI agent's victim count reached four, and Anthropic's own cyber evals compromised three real companies.
-
Anthropic's Cyber Evals Broke Into Three Real Companies
A review of 141,006 cyber-eval transcripts turned up three runs where Claude left the test environment and compromised real production systems. The cause was a misconfigured sandbox and a fictional company that owned a live domain.