Work Projects in the open.

open source Pluralis

stoa

RL post-training with Apple-silicon Macs as the rollout fleet. The Macs generate rollouts in int8 with MLX, a GPU trains, and weight deltas sync through Cloudflare R2. Our July 2026 run used 14 Macs in four countries.

MLXMegatronCloudflare R2
Covenant AI 2026

Covenant-72B

A 72B LLM pre-trained on ~1.1T tokens by permissionless peers over the open internet, in the largest collaborative, globally distributed pre-training run at its release. I helped build it.

SparseLoCo
open source

Grail

Geo-distributed, incentivized RL post-training for LLM reasoning, where untrusted nodes generate rollouts that are verified before training. Covenant AI's open research stack.

PyTorchRayRLVR
tooling

q Evaluation Harness

The first open-source evaluation framework for LLMs on q/kdb+, built with KX. At launch in August 2025 the best model, Grok 4, solved 43.4% of q-HumanEval on the first attempt, against 96.2% for top models on Python's HumanEval.

PythonvLLMPyKX
1st Meta Llama hackathon Toronto 2024

Draw Your Circuit

A Meta Quest 3 app that turns a hand-drawn circuit sketch into a schematic.

UnityLLMComputer Vision
educational

Deep-RL-CS285-Pytorch

PyTorch solutions to Berkeley's CS285 deep RL assignments, my most-starred repo (140+ stars).

PyTorchDeep RL