OpenAI publishes the InstructGPT paper on arXiv
Released the InstructGPT paper on arXiv
Why it matters
Showed that outputs of the 1.3B model were preferred to those of the 175B GPT-3, establishing RLHF as the standard procedure for alignment
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2203.02155Added in Week 35, 2026 · See that week