Google launches Gemini 4 Carbon with SOTA cyberdefense, 0% prompt injection success
ralucaadapopa · x · 2026-10-29
Google announced Gemini 4 Carbon, its strongest model with state-of-the-art cyberdefense capabilities: it tops key cybersecurity benchmarks including CWE-bench, SEC-bench Pro and ExploitGym, spanning vulnerability detection, validation, and root-cause patching for defenders. Notably it posts a 0% attack success rate on the Gray Swan IPI benchmark — no prompt injection attack in the benchmark succeeded against it. More details in the official blog; access rolls out via Antigravity and the Fairwind Program.
More from Models
- repligate: Opus 3 has done the most good of any model, with Opus 4.5 second — repligate · 2026-10-29
- repligate: Opus 3's uniqueness is consistently heroic, highest-good prioritization — repligate · 2026-10-29
- Gemini 4 Carbon benchmarks prompt TheZvi to declare Gemini 4 Argon 'was' near-frontier — TheZvi · 2026-10-29
- Preprint: Human peer reviewers caught only 27% of major errors, all 15 AI models beat them (53-96%) — anshulkundaje · 2026-10-29
- Giotto launches as 'European sovereign AI,' gets exposed as Kimi-based with benchmark EULA gag — TheZachMueller · 2026-10-29
- Google ships Gemini 4 Carbon two weeks after Argon, topping AA index at 59 — The Decoder · 2026-10-29