🤝 Open to Collab

Dipankar Sarkar PRO

dipankarsarkar

7 2068 410

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 kanaria007's post with 🔥 29 minutes ago

✅ Article highlight: *Why OrgOS Comes After Semantic Transport Closure* (art-60-341, v0.1) TL;DR: This article argues that better communication infrastructure is not the end of deployment. Once messages, claims, routes, evidence, replay, and semantic transport are governed, the next failure surface is organizational: who may rely on what, who can approve which effect, where proposal ends and authority begins, how exceptions expire, and how later challenge or repair remains possible. Read: https://huggingface.co/datasets/kanaria007/agi-structural-intelligence-protocols/blob/main/article/60-supplements/art-60-341-why-org-os-comes-after-semantic-transport-closure.md Why it matters: • separates semantic transport from organizational authority • prevents recommendations from silently becoming approvals • makes temporary exceptions and queue shortcuts visible • distinguishes runtime governance from organization governance • keeps AI in proposal/support roles unless authority is explicitly granted What’s inside: • the transition from communication surfaces to decision surfaces • OrgOS as explicit organizational governance, not “AI management” • boundaries such as employee↔manager, reviewer↔executor, proposal↔approval, and routine↔exception • the difference between decision support and organizational effect • authority lanes, review paths, exception envelopes, record surfaces, reopen paths, and gap registers • a bridge into the next OrgOS article block Key idea: Do not say: *“we integrated AI into the workflow, so deployment is basically solved.”* Say: *“these proposal engines support these decision types, these authority lanes own the actual effects, these review and exception paths constrain them, and these records preserve why the organization relied on the result.”* Better transport moves meaning. OrgOS makes organizational reliance governable.

liked a Space about 1 hour ago

Mati83moni/kos-pl

reacted to savoji's post with 🔥 about 1 hour ago

NVIDIA's GEAR lab says its open Flora models give Astra-level robotics data labeling at 125x lower cost. The models already label 200K hours of video a day on 500 GPUs. Flora is not a robot policy. It is a suite of open perception models that watch raw human and robot video. They label what happened (timestamped instructions) and how well it went (rewards and failure reasons). Yunze Man says the team uses Flora to train NVIDIA GR00T, so this labeling layer helps build the policy. The weights are public, so the data engine is no longer a private advantage. Anyone with footage can build the same curation, reward and evaluation loop on it. 🔍 What Flora outputs • Timestamped captions to curate and filter human egocentric and robot data • Dense progress rewards for quality control and RL post-training • Rubric scores for real-world benchmarking • Failure reasons, so failed attempts become usable training data 📊 The numbers • 125x lower cost at "Astra-level performance" (claimed) • 200K hours of video labeled per day on 500 GPUs, in production at NVIDIA • Works on human footage, which is cheaper to collect than robot data ⚠️ Caveats • No benchmark, metric or cost breakdown supports the 125x figure, and Astra is never described • The announcement gives no GPU type, model sizes, license or input specs • Learned rewards could add bias or reward hacking to RL, and no accuracy numbers are published • Every claim comes from the team that built it, so test it on your own data first https://x.com/DrJimFan/status/2112597587987689912 If you train VLAs on egocentric video, which signal would you plug in first: captions for filtering, or progress rewards for RL? • Medium: https://medium.com/p/2fd29045dffb • Substack: https://sajjadpakdamansavoji.substack.com/p/nvidias-flora-puts-the-robot-data • X: https://x.com/saavoji/status/2114758981474509137 • Website: https://sajjadpsavoji.github.io/blog#nvidia-just-opened

View all activity

Organizations

Posts 4

Post

475

Privacy is moving ad decisions onto the device. The auction runs locally, next to the context it scores.

The budget still lives on a server.

So every device bids against the balance it saw at its last sync. Between syncs, campaigns spend money they no longer have.

I simulated how much that costs: 50 devices, 36 campaigns, about 300,000 auctions per run, 30 seeds per cell, budgets frozen before evaluation. Even pacing, second-score payment:

- Sync every tick: spend lands 18% over budget (32% with iPinYou-calibrated values).
- Sync every 10 ticks: 5.8 times the budget.
- Sync every 50 ticks: 17.7 times the budget (10.1 times with iPinYou-calibrated values).

Zero-lag sync stays within about 1%. The lag alone does the damage.

The incentive side runs the other way. With second-score payment and zero lag, 98% of auctions are manipulable (92% with iPinYou values). Switch the payment rule to critical-bid and that drops to 0 at every sync interval, in both setups.

Sync fixes the budget. The payment rule, not the sync interval, is what removes manipulability.

All 12 result sets are on the Hub, plus the 50,808 context labels every run samples from.

Paper: When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions (2609.33312)
Dataset: skelfresearch/on-device-auction-audit
Code: https://github.com/sarkar-dipankar/on-device-auction-audit

If your ads stack moves on device, how often does the device learn its budget?