开启时会模糊预览图，关闭后正常显示
We invited Khoa to our Hacker Resident for a weekend, so cool to have someone so young yet with so much hustle energy joining us! The most talented 17-year-old I've met for sure.
Building software I love to use. https://t.co/p4T2vFZoJ1, https://t.co/y0Lq4RQRsu, https://t.co/KfFdieGrVf. Learn to build and learn to sell, you will be unstoppable.
## Lists outside, Detail inside. one fun discovery i've had using Cursor 2.0 is that the Agents view and the Editor view are not actually that different if you happen to be #rightsidebar gang I've been #rightsidebar since @shanselman first talked about it many moons ago and just realized my natural koding layout looks a bit like this now. I encourage people to think about AI UX in terms of literal screen real estate dedicated to agents. with Cursor 1.0 it was ~25%, with Cursor 2.0 it's now ~50-100% depending how you use it. I like being able to inspect my filesystem (which also doubles as logs) so I'm at 50%. but its interesting to see how LHS = Agent and RHS = Manual and have the karpathy "autonomy slider" visually manifest as the VSCode pane splitters.
achieve ambition with intentionality, intensity, & integrity - @dxtipshq - @sveltesociety - @aidotengineer - @latentspacepod - @cognition + @smol_ai
.@jjen_abel's top advice for closing tier-1 logos: 1. Make sure the founder is involved 2. Sell the vision. Don't sell to a problem.
Deeply researched product, growth, and career advice
AI FOR GOOD (@elevenlabsio’s Impact Program) Intellectually knew the difficulties for people with ALS, but seeing Eleven Labs bring back voices for people like Yvonne, it hit different and ended up tearing up. Happy 25th wedding anniversary Yvonne!
AI Apps investing @a16z | Investor in @elevenlabsio, @function, @cluely, @trymirage, @slingshotai_inc, @partiful & more | Growth @Snap & CFO @livebungalow
Powerful to hear from Yvonne Johnson on her experience losing her voice from ALS and how @elevenlabsio brought it back.
Human.
使用 Google AI Studio 和 Gemini 进行开发的 9 条实用编码提示 1. 注重细节（Be specific）：提供越多的具体信息（如参数、约束或预期结果），就能更好地控制 AI 生成的输出，避免模糊或意外结果。这有助于提升精确性和效率。 2. 逐步分解（Break it down）：建议将复杂任务拆分成小步，从一个功能或步骤开始逐步推进。这种增量式方法能减少错误，并便于调试。 3. 迭代优化（Iterate & refine）：初次提示往往不完美，将其视为对话过程，不断调整和完善。通过多次互动，逐步接近理想输出。 4. 利用参考资料（Use references）：向 AI 提供草图、图像或其他视觉参考，能提升生成质量。例如，指定字体名称和样式，能让输出更符合设计需求。 5. 借助模型能力（Lean on the model）：AI 不仅用于编码，还可协助脑暴想法或优化提示本身。这体现了 AI 作为辅助工具的多功能性。 6. 重置或重启（You can revert or restart）：如果代码助手的响应出现幻觉或不准确，使用聊天重置选项来清除上下文，重新开始。这能恢复对话的可靠性。 7. 保持耐心（Patience is key）：开发过程可能遇到故障、意外或需多次调整。强调坚持和灵活性是成功的关键。 8. 非确定性（It is not deterministic）：AI 输出受随机性影响，即使相同提示，在不同会话中也可能产生变异结果（如打开多个标签测试）。这提醒开发者需评估多个选项。 9. 享受过程（Have fun）：将 AI 视为创意伙伴，享受协作的乐趣。这种心态能激发创新，并缓解潜在挫败。
邵猛，中年失业程序员 😂 专注 - Context Engineering, AI Agents. 分享 - AI papers, apps and OSS. ex Microsoft MVP 合作 - 私信/邮箱：shaomeng@outlook.com 📢 公众号/小红书: AI 启蒙小伙伴
