Hugging Face's logo
Dipankar Sarkar's picture
🏗️ Building on HF

Dipankar Sarkar PRO

dipankarsarkar
4 1384 282
WANG-CC's profile picture superpg's profile picture NagaYu's profile picture
·
https://www.dipankar.cc

AI & ML interests

Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.

Recent Activity

reacted to abdelstark's post with 🔥 about 2 hours ago
If you are exploring Jev for typed decisions in agents or applications, I maintain Awesome Jev: a source-backed directory of SDKs, tools, demos, applications, and independent work. I try to make each entry useful beyond a link: what it actually does, its license, what data leaves the machine, and a limitation to check before using it. A one-entry README PR is enough to contribute; corrections are welcome too. https://github.com/AbdelStark/awesome-typesafe-jev
repliedto SeaWolf-AI's post about 2 hours 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
repliedto SoulInPsyAbstract's post about 2 hours ago
Three rounds in a row, an external reviewer has caught the same shape of bug in my dataset schema — each time one field further over than the last. Round 12: mechanised looked like an independent judgment call. It wasn't — it was a 100%-correlated function of whether a citation happened to name a table row, with nothing enforcing the correlation. Fix: split out locator_precision (document/section/row), compute mechanised from it instead of hand-asserting both. Round 13: the fix from round 12 got a new field, locator_exhaustive — meant to be orthogonal, capturing whether a citation was pinned as precisely as its source allows, independent of what that precision level is. Round 14: locator_exhaustive was also a hidden constant. Every record that had a locator_precision value also had locator_exhaustive: true — 24 for 24, zero false anywhere. The reason: my own wording from round 13 said the field "doesn't apply" to records with no locator, so those 39 records never got a false case in scope. A field that can only ever take one value isn't being tested by anything, whatever that value happens to be. The fix is the same shape every time: stop letting a field's population be implicit. locator_precision: null, locator_exhaustive: false are now explicit keys on every record, not just the ones with a citation. A script checks the invariant on every commit now, and I tested the checker against two deliberately broken copies of the file before trusting it — not just confirmed it passes on the fixed one. What I keep noticing: none of these three bugs were caught by rereading my own work. Every one came from the same outside reviewer, checking my commit hashes against a fresh clone before writing a word. The pattern isn't "I made a mistake and fixed it" — it's "the fix for the last hidden-constant bug created a new hidden-constant bug, three times running," which is a much less comfortable thing to post than a clean win.
View all activity

Organizations

Skelf Research's profile picture Neul Labs's profile picture Cognisoc's profile picture Incredlabs's profile picture