Hackernews posts about RLHF
- RLHF Book (rlhfbook.com)
- Show HN: A GPU-accelerated binary vector index (rlafuente.com)
- Making Markets on Kalshi (rlafuente.com)
- Syndeo: Secure, Portable Ray Clusters (rlafuente.com)
- Show HN: Generate Markdown Summary of Codebase for an LLM (rlafuente.com)
- RLHF is just barely RL (twitter.com)
- RLHF a LLM in <50 lines of Python (datadreamer.dev)
- StackLlama: A hands-on guide to train LlaMa with RLHF (huggingface.co)
- How RLHF Works (www.interconnects.ai)
- Constitutional AI: RLHF on Steroids (astralcodexten.substack.com)
- The Full Story of Large Language Models and RLHF (www.assemblyai.com)
- Training and aligning LLMs with RLHF and RLHF alternatives (magazine.sebastianraschka.com)
- How RLHF Preference Model Tuning Works (and How Things May Go Wrong) (www.assemblyai.com)
- Alpaca RLHF-ed to beat ChatGPT (crfm.stanford.edu)
- Alfred-40B, an OSS RLHF version of Falcon40B (www.lighton.ai)
- Stability AI releases StableVicuna, a RLHF LLM Chatbot (stability.ai)
- GPT trainer says he's traumatized from the RLHF work (www.bigtechnology.com)
- Tune PaLM 2 with your own RLHF training data (github.com)
- Andrej Karpathy on X: RLHF is just barely RL (twitter.com)
- Using Hallucinations to Bypass RLHF Filters (arxiv.org)
- ColossalChat: OSS Replication of ChatGPT with a Complete RLHF Pipeline (syncedreview.com)
- RLHF reduces LLM creativity and output variety (twitter.com)
- Constitutional AI: RLHF on Steroids (astralcodexten.substack.com)
- Unpacking the HF in RLHF (maestroai.substack.com)
- Interviewing Louis Castricato of Synth Labs and Eleuther AI on RLHF (www.interconnects.ai)
- RLHF: Reinforcement Learning from Human Feedback (huyenchip.com)