Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		til.simonwillison.net A simple Python implementation of the ReAct pattern for LLMs \| Simon Willison's TILs
\|	\|	somehowmanage.com Writing an LLM Agent in 50 Lines of Code (or no Code at All) - Somehow Manage	2.5 parsecs away Travel
\|	\|	One of the most interesting patterns that is emerging from Large Language Models (LLMs) is the idea of agents. If you're like me, you can only truly grok a concept by seeing or writing code for it from scratch, so like many other folks, I decided to try building one from scratch. So what is...	2.5 parsecs away Travel
\|	\|	callmephilip.com [Notes] A Hackers Guide to LLMs - callmephilip	2.5 parsecs away Travel
\|	\|	Notes for Jeremy Howard's video A Hackers' Guide to Language Models	2.5 parsecs away Travel
\|	\|	isthisit.nz Prompting GPT Models to Return JSON	2.5 parsecs away Travel
\|	\|	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.	2.5 parsecs away Travel
\|	\|	somosviajeros.com Guía de Taiwan	10.1 parsecs away Travel
\|		Guía de Taiwan con mis post de este viaje a una isla en medio de un conflicto geopolítico con China y con gente maravillosa	10.1 parsecs away Travel