topic · 2 notes
Inference Cost, as it ships.
Engineering notes on Inference Cost by Samir Sengupta - each one read from primary sources on the day it happened, with what it changes for people building on it.
August 22, 2026 · LLM Serving · Agents · Inference Cost
GPT-5.6 Sol drops 20% per token, and the agent stacks that won't feel it
OpenAI cut GPT-5.6 Sol pricing 20%. The class-level breakdown (cached input, output, reasoning) isn't confirmed, and both agent stacks in the sources bill via Codex seats, not tokens.
August 9, 2026 · Weather Models · Ensemble Inference · Open Source Models
DeepMind open sources WeatherNext Cyclones, a 1,000-member ensemble at 28km
WeatherNext Cyclones runs 1,000-member ensembles at 28x28km, produces a 15-day forecast in under a minute on a TPU, and is now open source. What to verify before you build on it.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.