← Back to home
Systems
Technical experimentation and applied AI engineering.
For: Developers, engineers, researchers.
What we cover
Local AIApple Silicon AIInference systemsAgent architecturesRAG systemsVector databasesEvaluation & benchmarkingToken analytics
From this domain
Lab report · May 22, 2026
Running a 70B model on Apple Silicon, end to end
A reproducible local inference setup with quantization, KV-cache tuning, and honest token-throughput numbers.
Read moreLab report · May 4, 2026
Evaluating RAG retrieval with adversarial questions
What happens to answer quality when the right chunk is present but buried under near-duplicates.
Read moreLab report · Apr 15, 2026
Embedding model shootout: accuracy vs. speed on CPU
A head-to-head comparison of six open embedding models on retrieval accuracy, latency, and memory footprint — all measured on the same CPU-only machine.
Read moreLab report · Mar 28, 2026
Five failure modes in production agent loops
An observational study of 200 real agent runs — cataloguing the repeating failure patterns that kill multi-step tasks before the finish line.
Read moreStay close to the work
Get new systems pieces in The Signal.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.