- Published on
Our thoughts on SWE-Bench after reading a recent paper that found issues with SWE-Bench resulting in SWE-Agent + GPT 4's performance dropping 3x.
AI Finetuned On /your/ Codebase
Leverage custom LLMs built specifically for your engineering team. Securely trained & deployed in your VPC, optimized for tasks across your SDLC.
Blog
A peek behind the scenes of CGFT
- Published on
The inner workings of our repo-specific finetuning pipeline that yields 50% more accurate code completions.- Published on
Our thesis on why finetuning with internal engineering data sources is crucial for complex, enterprise-grade codebases with unique patterns & frameworks.