System card
32 min
Kerrfield One system card
How Kerrfield One was trained, what 11,400 hours of red-teaming found, and every mitigation we shipped before launch.
Paper
18 min
Thinking longer, not bigger
A 70B model given four minutes to think beats a model ten times its size answering at once. Here is why, and where it stops working.
Paper
14 min
Calibration you can check
When Kerrfield One says it is 80% sure, it is right about 80% of the time. How we trained for honest confidence, and how to verify it yourself.
Release
9 min
Kerrfield One Distill: an open 8B model
A small reasoning model you can run on one GPU, released under Apache 2.0 with its training recipe.
Engineering
12 min
Two million tokens, one question
How we made a two-million-token context window useful rather than just long: retrieval inside the model, and tests that catch forgetting.
Paper
16 min
Checking your own work
Self-verification at scale: why running the code, re-deriving the maths and arguing the other side catches most mistakes.