Hacker News
- ART·E: how we built an email research agent that beats o3 https://openpipe.ai/blog/art-e-mail-agent 2 comments
- Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” https://openpipe.ai/blog/using-grpo-to-beat-o1-o3-mini-and-r1-on-temporal-clue 55 comments
- Using reinforcement learning and $4.80 of GPU time to find the best HN post https://openpipe.ai/blog/hacker-news-rlhf-part-1 95 comments
- OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost https://openpipe.ai/blog/mixture-of-agents 2 comments
- Mistral 7B Fine-Tune Optimized https://openpipe.ai/blog/mistral-7b-fine-tune-optimized 103 comments
- Is AI the next crypto? Insights from HN comments https://openpipe.ai/blog/hn-ai-crypto 367 comments
Linking pages
- GitHub - Helicone/helicone: 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓 https://github.com/Helicone/helicone 7 comments
- GitHub - thedaviddias/llms-txt-hub: 🤖 The largest directory for AI-ready documentation and tools implementing the proposed llms.txt standard https://github.com/thedaviddias/llms-txt-hub 4 comments