Sleeping
Agents
SentinelLLM Safety & Alignment Harness
🛡
Jailbreak, bias & format guardrails for LLMs — live demo
Abhishek Mittal
abhimittal
·
AI & ML interests
None yet
Organizations
Sleeping
Agents
AI Steering
🧭
Simulate AI steering: reasoning, context, guardrails, routing
Sleeping
Agents
VERITAS — Hallucination-Reduction RAG
🔬
Claim-verified RAG that measurably reduces hallucination
Sleeping
Swarm Parameter Server
🐝
Generate text samples from a distributed training model
Running
Live Latent-Space Navigator
🧭
Walk a diffusion model's latent space in real time
Running
Agentic Skill-Composition Benchmark
⚖
Token cost of skill-based agents vs monolithic prompts
Running
Quantization Error Propagation Viewer
🔬
Explore quantization error across model layers
Running
KV Cache Budget Simulator
📐
KV cache bytes, OOM walls, PagedAttention, Pareto frontier
Running
Speculative Decoding Trace
🎯
Watch rejection sampling accept/reject every draft token
Paused
Agents
Caliper — LLM Measurement Lab
🔬
Adaptive IRT evals, bias-audited judging, contamination