Gcam
- Karma
- 86
- Created
- 9 years ago
About
twitter: https://twitter.com/grmcameronRecent Submissions
- 1. ▲ Show HN: Stirrup – A lightweight and customizable foundation for building agents (github.com)
- 2. ▲ MicroEvals – Easily run vibe checks against models (artificialanalysis.ai)
- 3. ▲ From GPT-4 to Mistral 7B, there is a 300x range in the cost of LLM inference (twitter.com)
- 4. ▲ Show HN: LLM Benchmarks Leaderboard with 60 model and API host combinations (artificialanalysis.ai)
- 5. ▲ Mistral API reduces time to first token by 10x (only place for Mistral Medium) (twitter.com)
- 6. ▲ 240 Tokens/s achieved by Groq's custom chips on Lama 2 Chat (70B) (twitter.com)
- 7. ▲ New GPT-4 Turbo (0125 Preview) slightly faster per initial benchmarks (twitter.com)