Aaron Schneider schneidergithub

DevSecOps & AI research. @commondevops

34 followers · 1.2k following

Highlights

Developer Program Member
Pro

schneidergithub/README.md

Congrats! You found one of my online personas.

Current focus: Terminal-Bench-Science

With CommonDevOps, I’m contributing to a proposed benchmark task that asks AI agents to reconstruct study-level effect sizes from published research on executive function in major depressive disorder.

The challenge: find the right papers, identify eligible comparisons, extract the statistics, and get the math right.

Explore PR #1513 · Watch the task presentation

Website · LinkedIn · CommonDevOps on YouTube

Pinned Loading

google/lmeval google/lmeval Public

Python 241 25
ace-step/ACE-Step-1.5 ace-step/ACE-Step-1.5 Public

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Python 14.7k 1.9k
chess-experiment-claude chess-experiment-claude Public archive

Have LLM build from baseline.

Python 1
chess-experiment-codex chess-experiment-codex Public archive

Have LLM build from baseline.

Python 1
chess-experiment-ghcopilot-opus4.8 chess-experiment-ghcopilot-opus4.8 Public archive

my own benchmarking test

Python 1

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

Uh oh!

There was an error while loading. Please reload this page.