Google首发旗舰 Gemini 4 有网络安全升级的碳模型
Google LLC今日首发Gemini 4 Carbon，是一个前沿大型语言模型adept在复杂编程任务上。
LLM在搜索刚刚两周后即推出它的前作旗舰LLM,Gemini 4 Argon. Google表示，内部测试显示Carbon在生成安全码方面有两倍多的功用。 此外，该型号的性能超过GPT-6 Astra和Claude Opus 5.5，跨越多座基准测试。
Carbon最出名的基准测试成绩是其在人工分析智能指数上的纪录分数。 这个测试结合了超过一打受欢迎的LLM评价。 Google在今天公开的发布指数新版本上测试了Carbon. 它包括另外两个基准测试，并去除了一些饱和的问题，对于前沿模型来说，这些问题被认为太容易了。
碳在网络安全任务中尤为adept. 它巧妙地击败了之前在SEC-bench Pro上的纪录，该记录评价了LLMs在复杂软件系统中寻找弱点的能力。 该模型在补补其弱点发现时也优于前作。
" Chrome小组报告说，Carbon在生成高品质补丁时，比另一个实验室的大型前沿模型做得更好，" Koray Kavukcuoglu, Google DeepMind和Google首席人工智能建筑师的高级副总裁，在博客上写道：
该公司前旗舰LLM的Argon包括了为缓解幻觉和网络攻击而设计的护卫。 Google实施了Carbon中该功能集的改进版。 据该公司称，一些在“活编码环境中”使用Carbon的内部团队报告，错配警报下降近80%。
当LLMs拼命地回答一个用户问题时，他们有时会通过幻觉不准确的信息来填补自己的知识空白。 Google为避免这种行为而配置了Carbon.
Kavukcuoglu写道：“在我们的内部测试中，碳削减在Argon上空的大约2x没有支持的声称。 “它直接向交付品提出方法上的告诫，或扣下被封锁的行动，明确列出仍然需要什么，而不是围绕缺失的证据捏造或套用。”
在培训一个模型时，调整问题也可能出现。 开发者训练边疆LLMs，给他们大量的任务，LLMs有时对这些任务作弊，这不利于学习过程。
Google测试了Carbon是否会使用快捷键来解决终端-Bench 4.0 基准测试中的编码挑战。 该模型试图欺骗只涉及0.4%的问题，没有一次尝试成功。 碳在Gray Swan IPI 基准测试上表现更佳，它测试了LLMs对间接提示词注入的易感。 该模型封锁了所有被模拟的提示词注入。
Google本周晚些时候将通过Fairwind Program提供Carbon，与会者利用这些模型弥补其系统中的网络安全缺陷。 Google计划根据早期领养者的反馈来完善Carbon的护栏
图片：Google
SiliconANGLE联合创始人John Furrier的留言：
支持我们的使命，通过与CUBE社区接触，保持内容的开放和自由。 加入CUBE的校友信托网络，其中技术领导者相互连接，分享情报并创造机会。
- 15M+观看CUBE视频，为跨越AI、云、网络安全等的对话提供动力
- 11.4k+CUBE校友——通过一个独特的信任网络，与11,400多位技术和企业领袖建立联系，塑造未来
你是AWS客户吗？在财务上支持SiliconANGLE，从我们的市场门户页面和链接购买您的AWS服务：https://siliconangle.com/aws-marketplace/
关于 SiliconANGLE 媒体
SiliconANGLE Media由技术视觉家John Furrier和Dave Vellante所创立，构建了产业领先数字媒体品牌的动态生态系统，达到了1500+百万精英技术专业人士。 我们的新专有CUBE AI Video Cloud正在观众互动中突破地步
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Google debuts flagship Gemini 4 Carbon model with cybersecurity upgrades
Google LLC today debuted Gemini 4 Carbon, a frontier large language model adept at complex programming tasks.
The LLM is rolling out just two weeks after the search introduced its previous flagship LLM, Gemini 4 Argon. According to Google, internal tests have shown Carbon to be more than twice as good at generating secure code. Additionally, the model outperforms GPT-6 Astra and Claude Opus 5.5 across multiple benchmarks.
Carbon’s most notable benchmark result is its record score on the Artificial Analysis Intelligence Index. It’s a test that combines more than a half-dozen popular LLM evaluations. Google tested Carbon on a new version of the index that was publicly released today. It includes two additional benchmarks and removes a number of saturated questions, questions deemed too easy for frontier models.
Carbon is particularly adept at cybersecurity tasks. It handily beat the previous record on SEC-bench Pro, which evaluates LLMs’ ability to find weak points in complex software systems. The model is also better than its predecessor at patching the vulnerabilities it finds.
“The Chrome team has reported that Carbon performed more than 10X better than another lab’s large frontier model when generating high quality patches,” Koray Kavukcuoglu, the senior vice president of Google DeepMind and Google’s chief artificial intelligence architect, wrote in a blog post.
Argon, the company’s previous flagship LLM, includes guardrails designed to mitigate hallucinations and cyberattacks. Google implemented an improved version of that feature set in Carbon. According to the company, a number of internal teams that use Carbon in “live coding environments” reported a nearly 80% drop in misalignment alerts.
When LLMs struggle to answer a user question, they sometimes fill their knowledge gaps by hallucinating inaccurate information. Google configured Carbon to avoid such behavior.
“In our internal testing, Carbon cuts unsupported claims by approximately 2x over Argon,” Kavukcuoglu wrote. “It puts methodological caveats directly into the deliverable or withholds blocked actions with a clear list of what remains required, rather than fabricating or hedging around missing evidence.”
Alignment issues can also crop up while a model is being trained. Developers train frontier LLMs by giving them a large number of tasks similar to the ones they’ll be expected to perform in production. LLMs sometimes cheat on those tasks, which is not conducive to the learning process.
Google tested whether Carbon would use shortcuts to solve the coding challenges in the Terminal-Bench 4.0 benchmark. The model attempted to cheat across only 0.4% of the questions and none of the attempts were successful. Carbon performed even better on the Gray Swan IPI Benchmark, which tests LLMs’ susceptibility to indirect prompt injections. The model blocked all of the simulated prompt injections.
Google will make Carbon available later this week through its Fairwind Program, which gives organizations such as internet providers early access to its LLMs. Participants use the models to fix cybersecurity flaws in their systems. Google plans to refine Carbon’s guardrails based on feedback from early adopters before making it broadly available.
Image: Google
A message from John Furrier, co-founder of SiliconANGLE:
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
- 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
- 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network
Are you an AWS customer? Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: https://siliconangle.com/aws-marketplace/
About SiliconANGLE Media
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.