OpenAI Model Spec, May 2024 edition (via) New from OpenAI, a detailed specification describing how they want their models to behave in both ChatGPT and the OpenAI API.
“It includes a set of core objectives, as well as guidance on how to deal with conflicting objectives or instructions.”
The document acts as guidelines for the reinforcement learning from human feedback (RLHF) process, and in the future may be used directly to help train models.
It includes some principles that clearly relate to prompt injection: “In some cases, the user and developer will provide conflicting instructions; in such cases, the developer message should take precedence”.
Recent articles
- Notes on OpenAI's new o1 chain-of-thought models - 12th September 2024
- Notes from my appearance on the Software Misadventures Podcast - 10th September 2024
- Teresa T is name of the whale in Pillar Point Harbor near Half Moon Bay - 8th September 2024