News
Goodfire built cybersecurity monitors for Kimi K3 and GLM 5.3 that beat an LLM judge at a cost 50 times lower.
A probe reads the model's internal activations and sends only suspicious exchanges to an LLM judge.
At the chosen operating point, the cascade reaches 93% recall for 5.5% false positives.
The cost is under 200 dollars per million exchanges, about 50 times less than the judge alone.
Universal jailbreaks fall to 0% on the static attack battery of an independent evaluator's red teaming.