[Work & Writing](/work) # AI 16 entries ## 2026 - [View case study](/work/the-city) ### [The City](/work/the-city) I saw [AI Office](https://sael.net/ai-office) showing Claude Code agents as robots at desks, and wanted something that fitted the way I work. In The City, each project folder is a building and each team has a floor of robots, so I can see which ones need me. - AI - Architecture - UX design [Source code](https://github.com/Slaymish/theCity) - [View case study](/work/typed-diff-questions) ### [Typed Diff Questions](/work/typed-diff-questions) A narrow question about a diff can be scored, where a whole code review can't. This was a test of whether a bank of typed questions gives a usable signal. - AI - Developer tools - Research - [View case study](/work/otto) ### [Otto](/work/otto) Otto is a voice and text assistant for the Mac, built as a Swift app on top of the voice-os project. - AI - macOS - Swift - Voice [Source code](https://github.com/Slaymish/Otto) - [View case study](/work/lumen) ### [Lumen](/work/lumen) Lumen connects an Obsidian vault to a local research backend, so related notes surface while you write and reports come out of what's already there. - AI - Obsidian - Python [Source code](https://github.com/Slaymish/Lumen) - [View case study](/work/synod) ### [Synod](/work/synod) Synod reads your journal through a set of value agents and writes their disagreements back into the vault as a bulletin. - AI - Obsidian - TypeScript [Source code](https://github.com/Slaymish/Synod) - - [26 March 2026 Writing](/posts/splitting-the-stack-and-making-setup-actually-work) ### [Splitting GPUShare into two services](/posts/splitting-the-stack-and-making-setup-actually-work) [I split GPUShare’s accounts from the hardware services, then found the installer still pointed at a service I’d removed.](/posts/splitting-the-stack-and-making-setup-actually-work) [- AI- Architecture- Economics- Self-hosted](/posts/splitting-the-stack-and-making-setup-actually-work) - [Read the story](/work/gpu-share) ### [GPUShare](/work/gpu-share) My desktop GPU sits idle most of the day. I built a way for friends to share it for local AI and rendering, with the limits of a home machine visible. - AI - Architecture - Economics - Front-end development - Self-hosted - UX design [Source code](https://github.com/Slaymish/GPUShare) - - [21 March 2026 Writing](/posts/building-a-private-ai-server-for-friends) ### [Sharing my GPU with friends](/posts/building-a-private-ai-server-for-friends) [I built GPUShare around my desktop GPU. The accounts, routing and cost estimates ended up needing as much explanation as the hardware.](/posts/building-a-private-ai-server-for-friends) [- AI- Architecture- Economics- Self-hosted](/posts/building-a-private-ai-server-for-friends) - - [8 February 2026 Writing Report](/reports/grid-diffusion-anomaly-detection) ### [Anomaly (Out-of-Distribution) Detection for Electrical Distribution Networks using Discrete Diffusion Methods](/reports/grid-diffusion-anomaly-detection) [The paper behind Grid Diffusion AD: discrete diffusion over quantised magnetic-field windows, trained on normal data only, scored against a false-alarm budget. The best configuration separated faults from normal weakly, and the paper reports that instead of rounding it up.](/reports/grid-diffusion-anomaly-detection) [- AI- Machine learning- Research- Time series](/reports/grid-diffusion-anomaly-detection) - - [20 January 2026 Writing](/posts/healthagent-apple-health-data-ingestion-and-insights) ### [Putting my Apple Health data in one place](/posts/healthagent-apple-health-data-ingestion-and-insights) [I brought my nutrition and activity data out of Apple Health and into Postgres, so I could compare the daily and weekly trends.](/posts/healthagent-apple-health-data-ingestion-and-insights) [- AI- Architecture- Data pipelines](/posts/healthagent-apple-health-data-ingestion-and-insights) - [View case study](/work/health-agent) ### [HealthAgent](/work/health-agent) My nutrition and activity lived in different apps. I brought their Apple Health exports together so I could see the trends in one place. - AI - Architecture - Data pipelines - Front-end development [Source code](https://github.com/Slaymish/HealthAgent) ## 2025 - [View case study](/work/grid-diffusion-ad) ### [Grid Diffusion AD](/work/grid-diffusion-ad) Diffusion models trained on normal magnetic-field signals, scored on whether they notice a fault they've never seen. - AI - Machine learning - Research - Time series - [View case study](/work/pinterest-aesthetic-analysis) ### [Pinterest Aesthetic Analysis](/work/pinterest-aesthetic-analysis) I used CLIP embeddings to group the images on a Pinterest board, then kept the snapshots so one month's themes could be compared with the next. - AI - Computer vision - Python [Source code](https://github.com/Slaymish/PinterestBoardEmbedding) - - [9 June 2025 Writing Report](/reports/wildfire-analysis-with-pyspark) ### [Wildfire Analysis with PySpark](/reports/wildfire-analysis-with-pyspark) [I used PySpark to train and compare models on 1.88 million US wildfire records. The report covers the features, training runs and what happened when I weighted the rare classes.](/reports/wildfire-analysis-with-pyspark) [- AI- Data pipelines](/reports/wildfire-analysis-with-pyspark) - [View case study](/work/wildfire-pyspark) ### [Wildfire PySpark](/work/wildfire-pyspark) I worked with 1.88 million US wildfire records for a university project, and got into how a model could look accurate while missing the larger fires. - AI - Data pipelines ## 2023 - [View case study](/work/articulate-ai) ### [ArticulateAI](/work/articulate-ai) One of my early voice experiments: record a clip, transcribe it with Whisper, send the transcript to GPT with a prompt, and optionally speak the reply. - AI - Python - Voice [Source code](https://github.com/Slaymish/ArticulateAI)