For creators working on storyboards or brand campaigns, the most impactful new feature is the ability to generate up to eight ...
Images 2.0 introduces advanced reasoning capabilities for complex tasks Advanced thinking features are reserved for Plus, Pro ...
核心升级一: 性能全方位暴涨 40% 。GPT-6 采用全新 "神经符号融合" 架构,训练参数达 12.8 万亿,是 GPT-5.4 的 1.5 倍。在代码生成、逻辑推理、数学计算、智能体任务四大核心领域,全方位碾压 GPT-5.4:数学推理准确率 92.5%、代码生成通过率 96.8%、复杂任务执行效率提升 3 倍,远超行业所有模型。测试显示,GPT-6 ...
OpenAI简直漏风漏得跟筛子一样,关于最新Spud(土豆)模型的消息,又双叒叕来了。 这颗「土豆」,就是万众瞩目的GPT-6。 据爆料,这颗「土豆」已经彻底煮熟了,4月14号就会发布。 知情人士表示,这是个彻底奔着AGI去的模型—— 性能暴涨40% ...
OpenAI's latest image model can accomplish impressive tasks—like making an entire magazine layout or comic book.
The post OpenAI Launches ChatGPT Images 2.0: AI Image Generation Gets Reasoning Boost, Better Text & Pro Design Tools ...
2026年4月,OpenAI即将上线代号Spud的GPT-6,以200万Token上下文窗口(约100万字)、原生多模态Agent与全链路推理升级,彻底改写大模型长文本处理的行业边界,同时与Claude、DeepSeek形成三条截然不同的… ...
OpenAI is releasing a new version of its Codex desktop app today. The latest Codex update adds three key features that expand ...
OpenAI’s updated Agents SDK adds sandboxing, configurable memory, and file/tool workflows for safer, stronger enterprise ...
The package of updates comes as OpenAI’s rivalry with Anthropic intensifies, following the stellar successes of Claude Code ...
OpenAI rolled out their updated Codex app for Mac yesterday and, among other things, they shipped a native computer use tool ...
出于安全考虑,Anthropic 目前仅向包括英伟达、摩根大通、谷歌、苹果和微软在内的部分合作伙伴提供 Claude Mythos Preview。Opus 4.7 作为公开模型,用于测试新的网络安全防护机制,并加入更多安全限制。公司同时推出 Cyber Verification Program,允许安全研究人员在特定条件下使用该模型开展漏洞研究。