Hugging Face's logo
lazyowl39's picture

lazyowl39

lazyowl39
9 138
mayafree's profile picture SeaWolf-AI's profile picture Sunghokim's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago
FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF
reacted to SeaWolf-AI's post with 👀 2 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-27B
reacted to SeaWolf-AI's post with 🤗 2 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-27B
View all activity

Organizations

None yet