AI :: LLM :: InstructGPT
⪼ Made with 💜 by Polyglot.
GPT-3 models aren’t trained to follow user instructions. Our InstructGPT models (highlighted) generate much more helpful outputs in response to user instructions. GPT-3 is trained to predict the next word on a large dataset of Internet text, rather than to safely perform the language task that the user wants. In other words, these models aren’t aligned with their users.