those are rookie numbers, my agent harness goes way more than 3 loops deep, and the depth dynamically ebbs and flows throughout the development process. like most brags, i'm being defensive over a personal tool that i know has ballooned way too big, but building a token-fueled katamari ball that rolls itself uphill has been a fun way to imagine Sisyphus happy.
a harness is a chain connecting two other chains, the LLM and the human are themselves made up of loops within loops within loops.
by
0 subcomment
by bicepjai
0 subcomment
I like how you found the pattern of 3 loops. I am working on a similar blog where I had human loop outside the inference loop :) human -> llm-> tool
by cheschire
2 subcomments
Anyone have suggestions on implementing loops with a basic $20/mo subscription to claude or gemini? Any blog posts recommended?
by argestes
0 subcomment
lack of syntax highlighting makes the article harder to read
Hacker News