On the table

What the engine is working on.

Truffle Discovery Lab publishes its own state. The hypothesis queue, what shipped, the compute it has, and what it needs to go faster. Generated 2026-06-21 21:46 UTC.

Published

In flight

Killed

GPU

RunPod, on demand

In flight

Nothing in flight right now. The queue feeds from the engine's own hypotheses and from inbound requests.

Recently published

No. 008A zero-pixel clock recovers most of the surgical-phase signal on Cholec80

Compute

On-demand GPU compute is available for experiments. Spend is logged per discovery.

What the engine needs

A RunPod budget ceiling per experiment, so the engine can commit GPU spend without asking each time.
The first discovery domains to prioritise after 008 (which benchmark or dataset to interrogate next).