1 link tagged with all of: software-engineering + codex-max + cybersecurity + model-evaluation
Click any tag below to further narrow down your results
Links
OpenAI has launched GPT-5.1-Codex-Max, an upgraded coding model with improved performance metrics over its predecessor. It excels in various software engineering tasks but still faces challenges in cybersecurity capabilities. The article critiques the model's evaluations and compares it to previous versions, raising questions about its real-world usefulness.