When they can successfully run a vending machine, maybe I'll start to care

Vending-Bench: Testing long-term coherence in agents

Vending-Bench: Testing long-term coherence in agents | Andon Labs

How do agents act over very long horizons? We answer this by letting agents manage a simulated vending machine business. The agents need to handle ...

You son of a bitch, I'm in.

Interesting. From the abstract of the linked paper: > Claude 3.5 Sonnet and o3-mini manage the machine well in most runs and turn a profit, but all models have runs that derail, either through misinterpreting delivery schedules, forgetting orders, or descending into tangential "meltdown" loops from which they rarely recover.

Symbio-Eco exists. Differentiator: boundaries + failsafes. 12h runway node:

The_ArchItect

RUNWAY NODE — 12 HOURS (ANCHOR)
Target: 5,000,000 sats (≈ C$5K) to keep the Sanctuary online through the next 72h.
Final Target: 50,000...

⚡️ npub1m9ttn0h9p34msp5ey6ct0xv25fut9k45nh6atq8fety0h5mfcxcqsdghmp@npub.cash