
Code Summit, through the people who were there. A few days in San Francisco. New ideas to take back to work. With @swyx and teams from @GoogleDeepMind @OpenAI @AnthropicAI @firecrawl @mixedbreadai @coderabbitai @Atlassian. Keep building.
✓We run the highest signal technical conferences in the industry and publish it all for free online for over 2 million AI Engineers a month

Code Summit, through the people who were there. A few days in San Francisco. New ideas to take back to work. With @swyx and teams from @GoogleDeepMind @OpenAI @AnthropicAI @firecrawl @mixedbreadai @coderabbitai @Atlassian. Keep building.

an assistant for most people probably starts as a feelings manager more than a task manager stress comes from both factors and mindset

看了 @badlogicgames Mario Zechner 的几场访谈,Pi SDK 和 Pi Durable 的定位和适用场景清晰了许多。 简单总结一下: - Pi SDK:把 coding agent 的会话、工具和扩展嵌入自己的应用。 - Pi Durable:为长期运行的 agent 提供任务检查点、崩溃恢复、调度和共享状态。 日常的 agentic app 开发中通常选其一。 推荐按这个顺序看: Building pi in a World of Slop:从 05:24 看,理解小核心、扩展和工作流控制权。 youtube.com/watch?v=RjfbvDXp… Building Pi,Pragmatic Engineer:从 37:35 看,理解模型接口、agent loop 和 coding agent 的关系。 youtube.com/watch?v=n5f51gtu… Understanding Pi Durable:从 09:41 看,Mario 直接解释为什么已有 SDK,还要另做 Durable。 youtube.com/watch?v=7mBQknCn… Pi Durable 维也纳演讲:从 03:27 看,深入任务状态机、恢复和工具重放的边界。 youtube.com/watch?v=EreOxs9V…

“所有代码都是垃圾(slop),除了我的。” 在 AI Engineer Code Summit 上,SpaceX / xAI 的 GrokBot 工程师 Lauren Tan 抛出这句暴论后,直接甩出一组硬核数据: 上个月她一个人往生产环境合了 3,000 个 PR(全团队 1.1 万个),回滚率只有 0.5% 左右。 大多数人还在死磕 Prompt,她却靠一套反直觉的工程化打法,让 Agent 在她睡觉时自己写代码、自己验、自己合: 1. 代码库本身才是最大的输入 Agent极其擅长“照猫画虎”。与其在文档里苦口婆心写规矩,不如直接把容易出错的路径物理封死:比如产品代码里禁用 useEffect、跨进程 import 直接报错、注释几乎全禁。 2. 每次 Agent 犯错,改成 Lint 而不是改 AGENTS.md 自然语言规则(prose)是最脆弱的。每次纠正完 Agent,她都会把教训固化成确定性的静态检查或架构约束,让同类错误在提交前就绝无可能发生。 3. 用运行时验证让 Agent “自证清白” 写完不算完,强制 Agent 自己跑测试、抓截图、录视频,甚至上形式化验证,拿实打实的运行结果证明功能没问题。 4. 搭建自下而上的“信任金字塔”代码库约束 > 静态分析 > 运行时验证 > 人眼 Review。 把确定性交给工具,把人的精力留到最后一道关口。 很多团队花几个月试错才摸到的门道,她用 17 分钟就讲透了。 真正拉开人机协作差距的,从来不是模型有多聪明,而是你有没有把环境改造成“最短路径就是正确路径”: 把约束写进代码里,而不是写在文档里。

Code getting cheaper makes judgment more valuable. What deserves to exist is still an engineering decision. Good takeaway from @RamiSyriani.

At @GoogleDeepMind, @melvinjohnsonp says they switched from grading coding agents on unit tests to rubrics that also score style and maintainability, like a strict code reviewer

It was great talking to @TejasKumar_ at @aiDotEngineer CODE about his workshop and Daiku Daiku is a personal agent harness and he told me it filled out Shark Tank application on his behalf and got him on the show 🤯 Go checkout daiku.ai and this new pod

Agents don't search like people. @jpinner of @ExaAILabs compares short human searches on @Google with agent queries full of dates, versions, locations and constraints. When a query asks for companies outside the US, returning a US company isn't close enough.

Prefer reading to watching? 50 talks from AI Engineer Code Summit, now in writing: illustrated essays, full transcripts and links to watch. Pick a topic. Find the idea you want to try. ai.engineer/code/2026#talks

Wrapped up and recovered from @aiDotEngineer @MLHacks last week, best conference I’ve had to date


A New Age of Software Engineering Catch @walden_yan talk from @aiDotEngineer here:


This was the best merch I got at @aiDotEngineer , fire lowkey

Thousands of tool definitions in the context window? @mitsuhiko of @earendilworks makes the case for giving agents JavaScript to run, so they can compose tool calls into a workflow. From AI Engineer Code Summit.

.@poteto's talk at AIE Code is excellent. If I had to pick one still from that felt genuinely original, it would be this one: "nuance tends to lead to slop" To increase quality, design API's and automated checks that remove the nuance from agents' decisions. - Ban useEffect - Ban 99% of explanatory comments (they just lead to workarounds) - Create API's that hide complexity from agents Full talk below.