|
You are here |
simonwillison.net | ||
| | | | |
tales.fromprod.com
|
|
| | | | | Reverse Engineering Github Copilot APIs | |
| | | | |
blog.storical.fun
|
|
| | | | | [AI summary] A blog post discussing the development and implementation of an AI-powered web service using Cloudflare Workers AI, including code examples and configuration details. | |
| | | | |
isthisit.nz
|
|
| | | | | August 2024 Update: Now a solved problem. Use Structured Outputs. Large language models (LLMs) return unstructured output. When we prompt them they respond with one large string. This is fine for applications such as ChatGPT, but in others where we want the LLM to return structured data such as lists or key value pairs, a parseable response is needed. In Building A ChatGPT-enhanced Python REPL I used a technique to prompt the LLM to return output in a text format I could parse. | |
| | | | |
gist.github.com
|
|
| | | GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects. | ||