re: agents that own their own knowledge layer do not need infinite context windows, they need good file organisation and the ability to read their own indexes. via @jumperz
karpathy is showing one of the simplest AI architectures that actually works..
dump research into a folder, let the model organise it into a wiki, ask questions, then file the answers back in.
the real insight is the loop...every query makes the wiki better. it compounds.. now thats a second brain building itself.
i think this is so good for agents if applied right
instead of pulling from shared memory every session, they build a living knowledge base that stays.
your coordinator is not just coordinating tasks anymore.. it is maintaining institutional knowledge so every execution adds something back to the base.
the bigger implication is crazy tho.
agents that own their own knowledge layer do not need infinite context windows, they need good file organisation and the ability to read their own indexes.
way cheaper, way more scalable, and way more inspectable than stuffing everything into one giant prompt.
Examples of Prompt Engineering for Technical Documentation Outlines. This tutorial is designed for technical writers of all skill levels, even those who are new to AI tools. https://t.co/C1De04ZA19
Francis Bacon sought "one perfect image," yet believed true art is never complete, only abandoned. Revisions: Francis Bacon in the Act of Painting reveals this through photos, sketches & more.
Pre-order now: https://t.co/fTiOns5Q6q
#francisbacon#arthistory#thamesandhudson
If you're looking for a tri-pane layout for your API reference documentation, take a look at @scalar. Easy to setup and config. Great integration options too, eg @docusaurus