How OpenAI decides what ChatGPT should—and shouldn’t—do
- 5 hours ago
- 1 min read
TIME — On Wednesday, OpenAI published a blog post outlining the “philosophy and mechanics" behind its Model Spec—the document that shapes the behavior of ChatGPT, the world’s most widely used chatbot.
The Model Spec is meant to be an “interface,” according to the blog post. It makes the intended behavior of the world’s most widely used chatbot explicit, so that researchers, policymakers, and the public can “read, inspect, and debate” it.
The result is a 100-page document that defines how OpenAI’s models should adjudicate between potentially conflicting obligations to society, OpenAI, developers who build on top of OpenAI’s products, and end users.
To this end, the Spec is built around a chain of command, with a prohibition on “high severity harms” taking precedence over developers’ or users’ instructions, and is updated regularly—the most recent version dates to December.
Read the full story | TIME
