Alexandre Variengien

Apr 12, 2023 | lesswrong.com | Tao Lin |Bill Benzon |Evan Murphy |Alexandre Variengien

Crossposted from my personal blog. Recently, LLM-based agents have been all the rage -- with projects like AutoGPT showing how easy it is to wrap an LLM in a simple agentic loop and prompt it to achieve real-world tasks. More generally, we can think about the class of 'scaffolded'  LLM systems -- which wrap a programmatic scaffold around an LLM core and chain together a number of individual LLM calls to achieve some larger and more complex task than can be accomplished in a single prompt.