Tag

#Opus 5

2 articles

OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 but only with its own custom test harness

OpenAI claims GPT-5.6 Sol outperforms Opus 5 on ARC-AGI-3, but only in its own custom test environment. The official benchmark shows a stark contrast in performance.

Jul 2945

Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents

Anthropic's Opus 5, combined with Auto Mode, shows zero success rate in preventing browser-based prompt injection attacks, a major AI security vulnerability.

Jul 2535