Goodfire builds cybersecurity monitors for Kimi K3 and GLM 5.3, 50x faster and cheaper
CatAstro_Piyush · x · 2026-10-09
Goodfire AI built cybersecurity monitors for Kimi K3 and GLM 5.3 that are more accurate, 50x faster, and 50x cheaper than an optimized LLM judge. External red-teaming by Far AI found the monitors greatly reduce universal jailbreaks.
More from Models
- Gemini 4 Argon appears in Google's own model picker ahead of keynote — vedantmisra · 2026-10-09
- LightOnOCR-3 Training Data Revealed: MinHash Dedup, Weighted Formula/Table Sampling, Muon — IgorCarron · 2026-10-09
- LightOnOCR-3 uses multi-objective RLVR to jointly train grounding, OCR and empty-page handling — IgorCarron · 2026-10-09
- LightOn built an OCR-and-layout-detector annotation pipeline to train document grounding — IgorCarron · 2026-10-09
- Compact inline markers cut grounding output tokens 9-14% vs HTML-style rivals — IgorCarron · 2026-10-09
- Same Qwen3.5-4B backbone, but LightOnOCR-3 is 19% faster per page than Chandra 2 — IgorCarron · 2026-10-09