A Technical Survey of Reinforcement Learning Techniques for Large Language Models — mentioned by lossolo

Fri, 18 Jul 2025 04:37:52 GMT

I understand your argument. The recipe that finally let RLHF + SFT work without strip mining base knowledge was real R&D, and GPT 4 class models wouldn’t feel so "chatty but competent" without it. I just still see ceiling effects that make the whole effort look more like climbing a very tall tree than building a Saturn V. GPT 4.1 is marketed as a "major improvement" but under the hood it’s still the KL-regularised PPO loop OpenAI first stabilized in 2022 only with a longer context window and a lot more GPUs for reward model inference. They retired GPT 4.5 after five months and told developers…

Paper and discussion history. A mention is not an endorsement.

A Technical Survey of Reinforcement Learning Techniques for Large Language Models · HackerPapers discussions

A Technical Survey of Reinforcement Learning Techniques for Large Language Models — mentioned by lossolo