标签: Claude

it’s basically impossible for someone to just “show you their prompt” now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I’ve made first, search the web for…

it's basically impossible for someone to just "show you their prompt" now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, search the web for...

开发者 Thariq 提出,如今"把提示词给你看"已无法复制一个人的 AI 使用效果,因为真正起作用的是上下文引用、技能组合和示例库,而不是那几行文字。这揭示出 AI 工作流正从"单条提示词"转向"多资源编排"。

Sonnet 5.5 is here! In Claude Code, users get ~30% more tasks done compared to Sonnet 5. It’s smarter, so it needs fewer tokens for the same work. Here it rakes a yard of leaves using tool calls. 24s faster than Sonne…

Sonnet 5.5 is here! In Claude Code, users get ~30% more tasks done compared to Sonnet 5. It's smarter, so it needs fewer tokens for the same work. Here it rakes a yard of leaves using tool calls. 24s faster than Sonne...

Anthropic 发布 Claude Sonnet 5.5,官方称其运行速度比 Sonnet 5 快 30% 以上,多数工作成本最多降低 30%,在 Claude Code 中用户完成的任务量提升约 30%。这意味着中端主力模型的竞争焦点,正从“谁更聪明”转向“同样聪明的前提下谁更省更稳”。