千呼万唤，Claude Opus 4.8 正式发布了。 北京时间 5 月 29 日凌晨，Anthropic 正式发布 Claude Opus 4.8，如果只看名字，Opus 4.8 很容易被理解成 Opus 4.7 后面的一次小版本更新，其实从官方释出的性能表来说，也确实如此。比如 Terminal-Bench 2.1 上，GPT-5.5 的 78.2% 仍然高于 Opus ...
XDA Developers on MSN
4 Claude Code settings I always change depending on the project I'm working on
Claude Code runs great on defaults, right up until it doesn't ...
Anthropic近日宣布对桌面端Claude Code进行全面升级，此次更新引入了多项突破性功能，为开发者带来前所未有的工作效率提升。新版本最引人注目的特性是支持在同一窗口内并行运行多个Claude实例，用户可以同时处理多个任务，例如让一个实例修复代码漏洞，另 ...
Dynamic workflows in Claude Opus 4.8.8 offer a structured way to handle complex tasks by dividing them into smaller, independent components. These workflows enable parallel task execution, where ...
Read our full review of Claude Sonnet 5 vs Opus 4.8 to see which AI model provides the best balance of quality and ...
机器之心编辑部刚刚，Anthropic 正式发布了全新的模型 Claude Sonnet 5，称其为「迄今为止最具 Agent 属性的 Sonnet 模型」，可以制定计划，使用浏览器、终端等工具，并以数月前还需要更大、更昂贵模型才能达到的水平自主运行。Sonnet 5 在推理、工具使用、编程和知识工作方面，相比 Sonnet 4.6 性能有显著提升，更接近 ...
Anthropic (ANTHRO) unveiled its latest artificial intelligence model on Thursday, known as Claude Opus 4.8. “Opus 4.8 launches alongside several new features,” Anthropic said on its website. “Users on ...
Claude Code’s five-hour rate limits double across Pro, Max, Team, and seat-based Enterprise plans from Tuesday, with peak-hours throttling removed for Pro and Max. The capacity behind the change is a ...
On benchmarks, Opus 4.8 is a step up rather than a leap. It scores 88.6% on SWE-bench Verified (vs. 87.6% for Opus 4.7), 69.2% on the harder SWE-bench Pro (vs. 64.3%), and 74.6% on Terminal-Bench 2.1 ...
Anthropic on June 30, 2026, launched Claude Sonnet 5 as the new default AI model for its Free and Pro subscription tiers — replacing Sonnet 4.6 with a model the company says narrows the performance ...
Fable 5 restored globally July 1 after 19 days under US export controls. Anthropic deployed a new cybersecurity classifier ...
当前正在显示可能无法访问的结果。
隐藏无法访问的结果