In which we cover OpenAI's new paper on fine-tuning GPT-3 with human feedback, Facebook's new paper that presents a single algorithm that can work on different modalities, and more!
Share this post
The Gradient Update #17: OpenAI's InstructGPT…
Share this post
In which we cover OpenAI's new paper on fine-tuning GPT-3 with human feedback, Facebook's new paper that presents a single algorithm that can work on different modalities, and more!