instruction-following

Tag

Cards List
#instruction-following

Aligning language models to follow instructions

OpenAI Blog · 2022-01-27 Cached

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.

0 favorites 0 likes
#instruction-following

Instruction Following with ChatGPT Images 2.0

YouTube AI Channels · 2026-04-22 Cached

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.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback