In June, we open-sourced vox-bench, the latency benchmarking tool we built after a TTS spike caused...
4 Months of vox-bench in Production — What 14,000 Benchmark Runs Taught Us About Voice AI Latency
Related
What app code should assume about an LLM call
See how next-token prediction, pre-training, post-training, and temperature should change validation, freshness, and sampling in your app.
The other half of the software factory
Event storming, vertical slicing and event sourcing, shown on one small book club in Erlang, with the five Ds and what runs today.
Building Ribbonlab, a 3D Animated Background Generator
Originally published on ayurchenko.xyz. The image above opens the live editor. Ribbonlab is a free...