Writing Dispatches from the deep.
Technical posts and essays.
2026 · 07 · 14
RL Post-Training on Macs
Multi-turn RL of an 8B mixture-of-experts model with 14 Macs in four countries generating rollouts and one B200 training it. Held-out pass@1 on PaperSearchQA went from 29% to 63%.
technical 30 min Pluralis blog
2026 · 01 · 05
The Act of Creation
On moving from passive absorption to active curation, and finding the self through creation.
essay 12 min Substack Liminal
2025 · 08 · 14
Introducing q Evaluation Harness
The first open-source evaluation framework for LLMs on q/kdb+. At launch 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.
technical 7 min KX Systems on Medium