Search Results for "set"

...GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI).

...It implements a full agentic loop where the model can reason, decide when to use tools, execute those tools, and iterate until producing a final answer, making it useful for simple AI-assisted coding workflows. It includes a set of integrated tools such as read, write, edit, glob, grep, and bash that let the agent interact with the file system and shell commands directly from the terminal, and it keeps a conversation history with colored terminal output for readability. The project exemplifies how lightweight architectures can still support practical agent workflows without complex infrastructure, making it suitable for developers exploring agent frameworks or building custom coding assistants.

...And unlike ChatGPT, Mentat already has the context of your project, no copy and pasting is required. Run Mentat from within your project directory. Mentat uses Git, so if your project doesn't already have Git set up, run git init. List the files you would like Mentat to read and edit as arguments. Mentat will add each of them to context, so be careful not to exceed the GPT-4 token context limit.