今天新增gemini-4IMAGE
Gemini 4 Carbon 安全基准曝光:漏洞发现 88.2%
Carbon 在 AA 得 59 分领先 Opus 5.5(58)与 GPT-6 Astra(57),漏洞发现 88.2%、利用 54.8%、修补 71%,先向部分网络安全防御者开放。
Choblin
@choblin297 小时前收录原推发布于 2026.10.29

Choblin @choblin29原推发布于 2026.10.29
Holy Moly. Google has announced Gemini 4 Carbon just TWO WEEKS after Argon, claiming the #1 spot on Artificial Analysis with 59 points, ahead of Claude Opus 5.5 (58) and GPT-6 Astra (57). Google says Carbon has run for DAYS on complex engineering tasks. It scores 88.2% on vulnerability discovery, 54.8% on exploitation and 71% on patching benchmarks. Access starts with select cyber defenders as Google participates in voluntary U.S. government pre-release testing.
这条是引用着另一条写的:「Logan Kilpatrick:Gemini 4 Carbon 在编程与对齐上大幅超越 Argon」
x.com/choblin29/status/2115491449789632847采集于 2026.10.29 10:01