Bittensor subnet SN73 rebrands to Elenost, benchmarking perception in a simulated city
markjeffrey · x · 2026-10-27
- Bittensor subnet 73's project Parked has been renamed to Elenost on-chain. Its site pitches "AI that understands the physical world": perception models are tested inside a continuously evolving simulated city, tracking what they see, understand, and miss.
- The frozen baseline benchmark snapshot lists Drone Detection at 54.64%, Vehicle Tracking at 38.01%, and Person Tracking at 34.09% — drone-view urban perception evaluation as the subnet's core task.
More from Research
- eLife study: LLMs poorly capture how word order shapes sentence meaning in the human brain — AnnaCiaunica · 2026-10-27
- Lean–text proof mismatch means AI math claims need long human verification — srchvrs · 2026-10-27
- Why the exponential time hypothesis matters for AI reasoning complexity — srchvrs · 2026-10-27
- Ring-aperture VCSELs show best LI performance, argue researchers — jwt0625 · 2026-10-27
- Dev quips: if 3SAT constants are cosmic, P=NP wouldn't matter anyway — sytelus · 2026-10-27
- A 30-minute workflow for triaging any research paper — cneuralnetwork · 2026-10-27