Claude: How to use system prompts. Documentation for the new system prompt support added in Claude 2.1. The design surprises me a little: the system prompt is just the text that comes before the first instance of the text “Human: ...”—but Anthropic promise that instructions in that section of the prompt will be treated differently and followed more closely than any instructions that follow.
This whole page of documentation is giving me some pretty serious prompt injection red flags to be honest. Anthropic’s recommended way of using their models is entirely based around concatenating together strings of text using special delimiter phrases.
I’ll give it points for honesty though. OpenAI use JSON to field different parts of the prompt, but under the hood they’re all concatenated together with special tokens into a single token stream.
- Weeknotes: Getting ready for NICAR - 27th February 2024
- The killer app of Gemini Pro 1.5 is video - 21st February 2024
- Weeknotes: a Datasette release, an LLM release and a bunch of new plugins - 9th February 2024
- LLM 0.13: The annotated release notes - 26th January 2024
- Weeknotes: datasette-test, datasette-build, PSF board retreat - 21st January 2024