In 2022, OpenAI published InstructGPT, which collected prompts from OpenAI playground users (with consent) and had human labelers provide demonstrations of desired behavior as responses to the prompts, then fine-tuned GPT-3 on these annotated datasets.
factualpending
Speaker
Unidentified Speaker — 10 years of NLP history explained in 50 concepts | From Wor… [uocYQH0cWTs]Evidence Quote
“in 2022 openai published instruct GPD they collected a bunch of prompts from existing openai playground users after consent and got human labelers to provide demonstrations of the desired Behavior as response to the prompts then gpd3 was fine-tuned on these annotated data sets”
Source
10 years of NLP history explained in 50 concepts | From Word2Vec, RNNs to GPT— Neural Breakdown with AVBCreated: 8/11/2026, 1:00:15 AM
Your notes
Loading notes...