We trained SWE-grep and SWE-grep-mini, fast agentic models specialized in highly parallel context retrieval. They match the retrieval capabilities of frontier coding models, while taking an order of magnitude less time. Available now in Windsurf’s new Fast Context subagent, and our new SWE-grep demo playground!
We explore reinforcement learning in a multi-turn setting, using intermediate feedback from the environment, and masking model thoughts to avoid exploding context over multiple turns.
Testing OpenAI’s newest o1 series of models with Devin for autonomous coding tasks
One of our goals at Cognition is to enable Devin, an AI agent specializing in software development, to contribute code successfully to large, complex codebases.