Sakana AI updates Fugu-Cyber, claiming SOTA on real-world security benchmarks
hardmaru · x · 2026-07-21
Sakana AI says its updated Fugu-Cyber orchestration model reaches state-of-the-art results on real-world security benchmarks.
The key point is that it does not train a cyber model from scratch. Instead, it orchestrates existing frontier models and claims performance on par with cyber-focused systems such as GPT-5.5-Cyber and Mythos Preview.
More from Models
- Anthropic's Terra returns with better writing and 2X usage vs 6.1 Sol — weswinder · 2026-10-27
- User catches model failing to parse 400-paper file, citing stale news sources instead — jungofthewon · 2026-10-27
- Odd eval result: Gemini 4.1 Flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Gemini fails at listing unread emails, tells user to search Gmail manually — gethackteam · 2026-10-27