Weirdly genius

Turned 2,572 old posts into a semantic archive with his Muse agent

Adrian C. Murray@adriancmurray

added

I had my @muse agent, Anuki, download all of my posts from Instagram and Threads into its VM; and then each post was turned into a vector embedding, which lets me search by meaning instead of just keywords.

Adrian had his @muse agent Anuki download all 2,572 of his Instagram and Threads posts into its VM, converted every post into a vector embedding, and built a semantic search index of his own posting history with a "meta footprint" report on his patterns.

View on Threads

More Meta Muse use cases in Weirdly genius

See all 93 β†’
One prompt turned a whole book into an 18-episode podcast website

One prompt turned a whole book into an 18-episode podcast website

Turning any book into a chapter-by-chapter podcast series in Muse might be my favorite new use case. It brings together so many things: long context agents that can reason through very long books, subagents that go chapter by chapter to operate in parallel, podcast generation, website generation to build an artifact website that persists so I can easily go back to it. Just upload the book and ask it to generate podcasts of every chapter of the book and then build an artifact out of it. It did this all from one prompt. No new plugins or extensions required. It's so mind blowing to me that this works so well!
@mattdeitke

36.3K views on X