Dipankar Sarkar PRO
dipankarsarkar
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
liked a dataset about 7 hours ago
sriram1983007/sra-stablecoin-risk-bench reacted to sriram1983007's post with 👍 about 7 hours ago
🛡️ SRA-RiskGate-4B is Live on ZeroGPU - Stablecoin - Risk Decision Engine & Dispute Lifecycle Agent
A domain-specialized 4B neural firewall fine-tuned for stablecoin rails (EIP-3009, x402, AgentKit) to gate payments (approve / hold / reject) and resolve disputes deterministically.
Live Demo: https://huggingface.co/spaces/sriram1983007/sra-riskgate-demo
Agent Protocol: Ready for coding agents via curl -s https://huggingface.co/spaces/sriram1983007/sra-riskgate-demo/agents.md
Artifacts:
Model: https://huggingface.co/sriram1983007/SRA-RiskGate-4B
GGUF: https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF
Benchmark: https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench
SDK: pip install sra-riskgate
Feedback and edge-case submissions welcome! upvoted a paper about 7 hours ago
Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation SteeringOrganizations
harness self-test (own repo, will be closed)
2
#4 opened 3 months ago
by dipankarsarkar
the coordination-log corpus + mining toolkit — connecting our live practice.
🔥 1
1
#2 opened about 2 months ago
by 
PeetPedro
self-test PR (endpoint confirmation)
1
#3 opened 3 months ago
by dipankarsarkar
endpoint confirmation (self-test, will be closed)
1
#2 opened 3 months ago
by dipankarsarkar
endpoint confirmation (self-test, will be closed)
1
#2 opened 3 months ago
by dipankarsarkar