Saved by Darren LI and
Autonomous Agents & Agent Simulations
Thanks to the cognitive architecture design, goal-oriented behavior is at the core of our LLM agents. When presented with a goal, they employ a planning and execution process to achieve it. If the goal can be accomplished using atomic game actions, we generate a plan that outlines how to solve the objective. For longer-term goals, we decompose the ... See more
Introducing our work on general-purpose LLM Agents | GoodAI
An agent is an autonomous software entity that is capable of taking actions to accomplish goals and tasks.
Ben Auffarth • Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs
Some techniques I have seen in the wild
this style was popular back in the early days of gpt-3.5 when it landed, for some reason, it fell out of fashion
Best example of this is the V... See more
- Create a semi-strict programming language like promptlang - https://github.com/ruvnet/promptlang
this style was popular back in the early days of gpt-3.5 when it landed, for some reason, it fell out of fashion
- Write a super long persona mapping prompt with a well defined action space
Best example of this is the V... See more