wshobson

Prepare, format, and validate datasets for supervised fine-tuning and preference training.

Build scalable design systems with design tokens, theming infrastructure, and component architecture patterns.

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model…

PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas.

Design and implement event stores for event-sourced systems.

Convert files between formats — PDF to Word, HEIC to JPG, MP4 to MP3, CSV to JSON, EPUB to MOBI, and 999 total routes across images…

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model.

Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR).

Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format…

Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated…

Design and implement microinteractions, motion design, transitions, and user feedback patterns.