AnalysisCybersecuritySeptember 29, 2026

Anthropic red team: GLM-5.3 hijacks control flow in 4% of trials

Read original source →simonwillison.net

On 100 randomly selected tasks from Anthropic's internal Binary Exploitation benchmark, GLM-5.3 achieved full control flow hijacks in 4% of trials and Claude Mythos Preview in 6%. Earlier models including Claude Opus 4.6 and GLM-5.2 succeeded in none.

1 source

More stories today

Open the live feed