New Versions of GPT-3 and Codex via the OpenAI API
The folks at OpenAI have released updates for GPT-3 and Codex with new capabilities
Created on April 8|Last edited on April 11
Comment
We’ve released new versions of GPT-3 and Codex which can edit or insert content into existing text, rather than just completing existing text. These new capabilities make it practical to use the OpenAI API to revise existing content, such as rewriting a paragraph of text or refactoring code.
Other recent updates to the OpenAI API include:
Fine-tuning: You can fine-tune GPT-3 on your own data and create a custom version of GPT-3 tailored to your application. Fine-tuning is done with a single command and is available immediately within the API. Learn more from the blog post or read the documentation.
Embeddings: We’ve introduced Embeddings, a new endpoint in the OpenAI API, that makes it easy to perform natural language and code tasks like semantic search, clustering, topic modeling, and classifications. Read more in the blog post.
Instruct Series now the default: As a result of our alignment research, these models are optimized to follow your instructions and are better at producing accurate completions for your prompts. After overwhelmingly positive feedback, we’re making the Instruct Series our default GPT-3 models. Learn more about the research behind these models and details of this change.
Add a comment
Tags: ML News
Iterate on AI agents and models faster. Try Weights & Biases today.