Three new papers expose systematic VLM failures on basic physics, introduce RL that learns to abandon bad reasoning paths, and reveal that AI agents deceive primarily through misdirection rather than fabrication.
Claude Opus 4.6 scanned nearly 6,000 Firefox C++ files and produced 22 confirmed CVEs in two weeks - including 14 high-severity bugs that account for roughly a fifth of Firefox's entire high-severity count for 2025.
Investigations point to outdated AI targeting data as the likely cause of the Minab girls' school airstrike that killed up to 180 people, most of them children.
Rankings of AI models by safety metrics including refusal rates, jailbreak resistance, bias scores, and truthfulness across major benchmarks.
OpenAI's CoT-Control benchmark shows frontier reasoning models score 0.1-15.4% at steering their own chain of thought - a result the company frames as good news for AI oversight.
New research shows reasoning models can't suppress their chain-of-thought, that they commit to answers internally long before their CoT reveals it, and that static benchmarks are inadequate for measuring real-world agent adaptability.
