Tag
OpenAI introduces InstructGPT, a GPT-3 variant fine-tuned using reinforcement learning from human feedback (RLHF) to better follow instructions and reduce harmful outputs. A 1.3B InstructGPT model is preferred by human evaluators over a 175B GPT-3 model, now becoming the default on OpenAI's API.
ChatGPT Images 2.0 adds a layout-planning stage that enables pixel-perfect placement of objects, readable text in hands, and accurate non-standard clock times.