crypto cat ( i , i)

59,674 lines of code and tests in 5 days. Here's what they bought. With offline packs, on a phone with 4 GB of RAM, BOAR answers at 48% of the quality of Opus with web search. A blind judge scored 61 real research questions (the travel guides pack we tested ships in the next update). Vegan places in 20 cities: 85% right (Opus with web: 90%). First words in under 5 seconds. Offline packs mean you download only what you need: each city in 1–4 MB, crypto in 36 MB, emergency guides in 16 MB. Travel guides are next. v1.1.0 is out for Android. One command audits exactly what the APK can reach. iOS is built too. Download coming soon. github.com/rferrari/boar-app…

Doing a bit of a self-experiment. Goal: use my personal health and travel data to provide personalized diet and exercise recommendations for me, using frontier models but in a way that avoids leaking to them any private information. Strategy: use a local model (Qwen 3.8 Flash Next) to orchestrate, and use powerful remote models as a tool call to benefit from higher-level thinking and knowledge that the local model does not have. Three-layer approach to privacy: Avoid leaking personally identifiable information, or leaking my identity through writing style -> local model writes the queries to the frontier model, not me Avoid leaking who I am through the payment channel -> zkAPI Avoid leaking who I am through networking / IP -> Tor You need all three (and finally we have all three, at least to some extent) A skill file teaches the local model when and how to construct minimally-data-revealing requests to remote models. Use zkAPI-wrapped-with-Tor as a CLI tool. And everything works! I got the recommendations back, info from frontier models helped to improve them. Main deficiencies: * Tor is really not optimized for request-by-request de-linking, which is the only form of network-layer privacy that really makes sense in today's world (long-running identifiers are too fragile). Probably not private enough, and latency 10-100x higher than it could be, at the same time. * The skill file's request construction strategies are definitely far from optimal. * Qwen 3.8 Flash Next is still too slow for comfort. It's comfortably running at 20-30 TPS, but it would only really start to feel fast at 100+ * There is a tradeoff: the more careful you are about what data you give to a remote model, the less it can help you github.com/ethereum/zkapi/pu…