parkinsons law maximizer
逆水行舟,不進則退
parkinsons law maximizer
逆水行舟,不進則退
Evaluate LLMs the right way — confidence intervals, unbiased pass@k, significance testing, bias-controlled LLM-as-judge, contamination checks. A drop-in agent skill with a numpy stats core validate…
Python
Ask your coding agent WHY a language model made a prediction — mechanistic interpretability (logit lens, activation patching, SAE features, steering) as a drop-in agent skill. Validated against pub…
Python
Forked from RyanRana/nomos
rl traffic coordination for autonomous vechicles
Python
Forked from TransformerLensOrg/TransformerLens
Fork for PR #1369 (merged): Direct Logit Attribution tool
Python
Differentiable deep-brain-stimulation field solver on NVIDIA Warp — CG Poisson solver in Warp kernels (CPU-verified, CUDA-ready) with wp.Tape gradients steering contact currents under a Shannon cha…
Python