Blog
Field notes for the AI-native company.
Analysis, patterns, and sharp observations from the work of building with AI.
AI Engineering
Kimi K3, explained: how forgetting made the biggest open model possible
K3's answer is selective memory: preserve exact history in some layers and let the rest update a fixed state. That is how forgetting made a model this large practical.
AI Governance
The Citizen SDLC
A six-stage lifecycle that takes what non-technical employees build with AI from personal prototype to production the whole company can rely on.
AI Fundamentals
The Machine That Learned to Pay Attention
Part B of the series: follow one ambiguous word through a transformer, station by station, from tokenizer to attention to the dice roll that picks the next word — plus the remodels and challengers reshaping modern models.
AI Fundamentals
Vectors Are All You Need
Part A of a series that builds modern AI from the ground up: how words become vectors, why the dot product runs everything, and how a machine learns by nudging numbers until it stops being wrong.
2026 Tenex. All rights reserved.
