Dario: I need a trillion dollar IPO, let's fuck with prompt caching on Fable 5 and bleed these plebs dry!

Insane that Fable doesn't write to cache after the initial system prompts. Notice that it wrote 4.9k tokens to cache when the session began and never again. I feel rugged! This planning session cost me 8.9k sats. 😭 Deepseek V4 Pro caches everything and costs much less, proportionally. (see image below) ps: this is routstrd top that shows cache r/w data

Why aren't we inviting Bitcoiners to Nostr? I invite @Matthew and @grubles to come back to Nostr. I'm currently trying bark-cli

Second Docs

Install Bark CLI - Second Docs

Let's scale Bitcoin!

But but i paid for the blue check mark!! These scammers!! 😭 And adding phone feature is broken lol. App by a $1.5T fiat company.

Ooo what is that? A Routstr node connected over FIPS? 🤪 View quoted note →

Better defaults - GLM 5.2 and Kimi K2.7 Better routing/switching Better cache hits This is also what we think about for Routstr. Our goal is to help the community here save on AI token spends.

X (formerly Twitter)

Brian Armstrong (@brian_armstrong) on X

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. B...

“It’s too bad Nostr’s user base is shrinking” “Maybe” View quoted note →