Aligning language models to follow instructions
OpenAI deployed a new generation of instruction-tuned models via RLHF alignment techniques, establishing a new baseline for user-intent adherence and safety. This shift from GPT-3 to InstructGPT as the API default signals a market-wide move toward alignment-first model development.
Why it ranks · · InstructGPT trained with human-in-the-loop RLHF alignment · January 2022
Read full story