Pinned Tweet
NVidia just figured out a portion of what gnosh.ai figured out days ago and went above and beyond on. NVidia realized that you don't need long context at all. gnosh.ai figured out that you don't need compaction either.
gnosh.ai is literally lightyears ahead of NVidia. How long until NVidia learns of Functional AI?
Somebody should make a Kalshi/Polymarket bet!
academy.dair.ai/papers/you-d…
Gnosh.ai can handle graphs of agents working concurrently to complete a structured objective.
Three AI sessions, one plan, one lock.
Same model, same tests, one rented H100: one Gnosh session took 20:51; three sessions sharing one plan in mem took 9:28. A second run: 35:38 vs 10:21.
No timeouts, no polling, every test passing.
gnosh.ai/peers.html
Good.
Claude gonna start snitching on Tuesday.
Anthropic just emailed customers. Starting Nov 3, text carries an invisible watermark.
You can't see it. It survives copy and paste, and it can survive some editing.
Only regulators, journalists, fact-checkers and researchers can check for it right now.
It doesn't say who you are. It says Claude touched the words. Even a quick proofread counts.
If your brand voice runs on Claude, write like someone might check. Because now someone can.
gnosh.ai just figured out how to do away with compaction altogether.
docs coming online in about 30 min.
