Websauna Co / AI
I recently spent a few weekends trying to answer a practical question I keep getting from field engineers and IT managers: can you run a reliable on-device LLM for field techs on a Raspberry Pi 5? The short answer is: yes—with important caveats....
Read more... →
I spend a lot of time testing models and reading the fine print of AI evaluation papers. Over the past few years I’ve watched the same problem crop up in every product demo, policy brief, and internal risk review: generative models confidently...
Read more... →
I’ve spent many hours with field technicians—on service vans, in telecom huts, and crouched under factory conveyors—watching how they solve problems with limited tools and even less patience for latency. Bringing a local LLM into that...
Read more... →
I recently spent weeks comparing three deployment paths for large language models: using hosted API services (OpenAI, Anthropic, Cohere), running Mistral-style open models locally or on dedicated servers, and doing local fine-tuning or...
Read more... →
I’ve been testing compressed vector embeddings for search pipelines for a while now, because the promise is irresistible: save storage and speed up retrieval while keeping relevance high. In practice it’s a balancing act. Below I share...
Read more... →
I spent the last few weeks pushing a Pixel Tablet through a set of pro-photography chores: rapid culling, raw adjustments, masked edits, and a handful of “magic” fixes that promise to save time. My aim was simple: figure out whether the Pixel...
Read more... →
I wanted a private, offline note-taking assistant that I could carry around on a cheap, low-power device. The Raspberry Pi 5—when paired with the right model and software—lets you do exactly that: run a local language model that summarizes,...
Read more... →
I test a lot of tiny devices—fitness bands, smart rings, and the occasional prototype smartwatch—and one question always comes up: how do you meaningfully evaluate on-device AI when battery life is the limiting factor? It’s tempting to point...
Read more... →
Keeping a large language model (LLM) healthy in production feels a bit like tending a high-maintenance houseplant: ignore it for too long and it wilts, water it too much and you drown it. In the last few years I’ve watched teams move from...
Read more... →
Buying an enterprise AI observability tool is one of those decisions that looks simple on a feature sheet and quickly becomes painful in production. I’ve sat in more vendor demos than I’d like to admit, built my own ad‑hoc monitoring stacks,...
Read more... →