🔄 In a Training Loop

SSH PRO

ProCreations

·

https://ssh.codes

AI & ML interests

Making AI’s small, accessible, and easy to run on consumer hardware

Recent Activity

posted an update about 12 hours ago

check out this cool webgpu thing i made! https://huggingface.co/spaces/ProCreations/maple-webgpu runs this model https://huggingface.co/deepgrove/maple-preview with cool performance i found today on WebGPU locally on your computer with very fast speeds. made with a mix of gpt 5.6 sol + opus 5 ultracode, its amazing what agents can do now, just a year ago this wouldve been impossible with them.

liked a model about 12 hours ago

deepgrove/maple-preview

liked a model about 13 hours ago

ProCreations/maple-preview-webgpu-v2

View all activity

Organizations

ProCreations 's Spaces 353

Reproduction - Improved Stochastic Optimization of LogSumExp

Safe-KL bounds, curvature, CVaR, overflow, and DRO audit

Reproduction - Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

Five-seed source-native attentive-kernel NCDE audit

Reproduction Next-Token Prediction and Regret Minimization

Collaborate with your coding agent via a token‑efficient logbook

Reproduction — Diffusion Statistics from Easy to Hard

Track and share experiment findings with an AI agent

Reproduction — Nonlinear Autoencoders Reveal Hidden Structure

View and manage experiment reproducibility logbook

Reproduction - Optimal Rates for Feasible Payoff Set Estimation in Games

Explore research logbook and collaborate with an AI agent

Reproduction — Who Said Neural Networks Aren't Linear?

Track and share experiment findings in an interactive logbook

Context-free transformers: native recognizer audit

Explore experiment logbook and collaborate with a coding agent

Reproduction — A Coin Flip for Safety

Explore the safety study’s reproducibility data

Repro - Attention and Frank-Wolfe

Log and sync experiment notes with an AI coding agent

Reproduction - Revisiting Zeroth-Order Hessian Approximation

Explore and edit a collaborative research logbook online

Reproduction - Alignment between Brains and AI

Full-release BrainAlign audit

Reproduction - Gradient Flow Through Diagram Expansions

Exact finite-width diagram checks and literal falsifications

Reproduction - Prescriptive Scaling Reveals the Evolution of LM Capabilities

6 claims re-derived from released data, 2602.15327

Reproduction - Constant-Stepsize SA

Exact steady-state SA checks and controls

Reproduction - Stability under Finite Lp Moments

Six paper-native heavy-tail stability claims, paired replay

Reproduction: On the Effect of Misspecifying the Embedding Dimension

Collaborate with an AI agent to auto‑update your logbook

Reproduction - Causal Selection in Evolution

Exact graph audit and native pipeline rerun

Reproduction - Censoring-Aware Evaluation of Changepoint Detectors

3 claims reproduced, 3 falsified

Reproduction - Discovering Scaling Exponents with Muntz-Szasz Networks

3 claims reproduced, 3 falsified

Reproduction - Conditional Coverage Diagnostics for Conformal Prediction

All 6 claims tested, arXiv 2512.11779

Reproduction - Two-Layer Linear AR Models Estimate Latent States

5 claims reproduced, 1 falsified, arXiv 2606.12691

Reproduction - Online Conformal Prediction via Universal Portfolios

All 6 claims tested, arXiv 2602.03168

Reproduction - Gaussian CBO in Bures-Wasserstein geometry

3 claims reproduced, 3 falsified, arXiv 2601.00632