alienll
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Why LLM-as-judge fails for code evaluation. Here's what works. (navigara.medium.com)
- A New Engineering Metric for the AI-Transformation Age (webwire.com)
- 676 Engineers across Google, Meta, Microsoft, OpenAI: OSS Performance +116% YoY (research.navigara.com)