DARWIN-Family
Collection
비드래프트 • 54 items • Updated • 43
lazyowl39
lazyowl39
AI & ML interests
None yet
Recent Activity
liked a model about 23 hours ago
FINAL-Bench/Darwin-180B-RSI liked a model 4 days ago
FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF reacted to SeaWolf-AI's post with 👀 4 days ago
The cost of a judging gate is usually quoted as a number. This puts it on a Tetris board.
Three boards get the same piece order, and on every move the same proposal and the same noise — a paired comparison. The gate decides one thing: keep this move, or draw again. Each board gets the same 60 seconds of gate time.
The text-writing gates get through 15–22 moves. The generation-free gate gets through 40–50. The boards that stop simply run out of clock.
It does not win on accuracy: on the same 2,018-question LODO set, JEV scores AUC 0.7350 against ZTC-Judge-27B's 0.7289. The separation is elsewhere. Clock — 2.1 s vs 0.0615 s per call, and on a 200-candidate agent screen one judging call measured 3.206 s generative vs 0.033 s readout, same server. Calibration — a gate is a threshold, and at ECE 0.4985 (vs ZTC 0.0245) a threshold stops carrying information. Mechanism — a text judge can name option 42 when there is no option 42; a scoring readout cannot. Not a lower error rate. No path.
The curve in the ZTC panel is real online fitting, scored prequentially — predict first, learn after — with base weights untouched. Not recursive self-improvement.
Limits, also stated on the page: Laya's AUC and latency are not our measurements and are set equal to JEV's, so calibration is the only measured axis it differs on. The page is a simulation driven by measured constants.
KO / EN / ZH.
https://huggingface.co/spaces/FINAL-Bench/Tetris-JEV-LAYA-ZTC
https://huggingface.co/FINAL-Bench/ZTC-Judge-27BOrganizations
None yet
upvoted 3
collections 8 days ago
upvoted a collection 15 days ago
upvoted a paper about 1 month ago
upvoted 4
collections about 1 month ago