Cursor has released the third version of its development environment – now it's a unified workspace where agents participate in code creation alongside humans.
The Zed team has released an updated model, Zeta2, for predicting code edits. It is more accurate, handles context more intelligently, and better understands the developer's intent.
OpenAI's Codex Security has moved away from traditional static code analysis, instead favoring an approach that seeks real vulnerabilities rather than burying developers in false positives.
Cursor has updated its AI coding assistant: the new version runs faster, handles complex tasks better, and uses fewer tokens.
Japanese fintech company Money Forward switched over 1,000 employees to the AI tool Cursor – and it's not just about coding.
Cursor took an unusual approach to training its AI assistant: self-summarization became part of the training process, not just a supporting tool.
The Cursor security team shared how they launched a 'fleet' of AI agents to find and fix vulnerabilities in their rapidly changing codebase.
Cursor has shared how its AI model evaluation system works – a hybrid approach that combines real-world scenarios and lab tests.
Cursor has introduced Bugbot Autofix, a tool that automatically corrects errors found in code by launching separate cloud agents to handle the task.