🧠 Most AI bug-catching tools review your code the way a human reviewer would, only faster. What if the AI wrote a test that proved the bug instead? That’s Catching Just-in-Time Tests (JiTTests) — a novel approach where LLMs generate executable tests designed to fail, surfacing behavioral changes in a code change before it lands. After a year of research, it’s now part of Meta’s infrastructure. ✅ 589 engineers have engaged with it, reporting a 60% true-positive rate 📈 In the first half of 2026, it helped catch 74 privacy SEVs at the diff stage, lowering overall privacy SEV occurrence by 20% 🔗 Read how it works: 📄 Read our FSE 2026 paper, “Just-in-Time Catching Test Generation at Meta”: #AI# #SoftwareEngineering# #SoftwareTesting# #DeveloperTools# #Engineering#

Which Claude model should you build with? Our new guide breaks down when to use Fable 5.2, Opus 5.5, Sonnet or Haiku. It also covers when to adjust effort instead of switching models, and how to save cost by putting subagents on smaller models.

What if you could get frontier-level AI classification at 1% of the cost? Airbnb engineers fine-tuned a small language model to deliver comparable accuracy in under 100ms. Here’s how. 👇

Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

Why PMs are suddenly valuable again with Tulsee Doshi (@tulseedoshi)—Head of Product for @Google’s frontier AI models, including @Gemini, Nano Banana, Genie, Veo, and more. We discuss: 🔸 The rising value of great PMs 🔸 Google’s full-stack frontier AI strategy 🔸 Why model development is like Snape’s potions class 🔸 Why the PM role has shifted from writing requirements to creating something with “heft 🔸 How to write your first eval Listen now 👇

这段时间集中面试，公司的阶段、人数、行业、组织和问题千差万别，也想借这次机会更多接触不同的企业来补充自己对于不行业和团队的理解。 我也想把面试中遇到的一些典型问题记录下来，当然会脱敏，意图不是曝光或八卦，主要还是在具象问题中抽象出更合理的解决办法，希望对各位在职场中的朋友有所启发，也希望对在看机会的朋友面试有一些心里准备，哪些是痛点、哪些是雷点，能分清。 我都记录在这篇内容下吧，先来第一个： 一家硬件和 SaaS 软件公司，HR 前置沟通一再强调，团队目前遇到了很深的技术难题，希望有 tl 来带队攻坚！ 但我初步了解了产品形态后，感觉不太对，他们遇到的肯定不是单纯的技术难题，是业务不断发展累加、不断复杂化但又缺少技术架构梳理和重构而欠下的技术债。 后来实际面试中 CEO 和几位技术负责人都参加了，轮到技术负责人提问时，他们提的也确实都是那类问题：业务不能停、个例用户也要支持、业务牵引而缺少技术决策主导等等。 实际上是非常典型的问题，就是业务快速发展的阶段，由于经验能力和时间分配等，忽略了技术架构和工程。当然有一个好的前提是，公司发展很好，且团队意识到了技术上的问题。接下来就来到技术负责人要做的工作：梳理业务痛点、以最痛点的几个问题切入专项解决、先把业务稳住再把专项解决的方案落到各个端。在这个阶段，同步梳理哪些功能可以抽离解耦、各端口协议如何做归一化、数据埋点和日志补全降低排查难度、提升功能使用情况监控。 同时在团队内落地和规范 AI Coding，边解决问题，边渗透 AI Coding 边加速，让研发团队的小的成果不断对业务产生价值，提升信任感和团队的成就感，再内部挖掘可以提供业务附加价值和创新点的方向，部分人和精力投入预研，拿出能打的东西来！ 这样有 2-3 个月时间，就能看到研发团队的变化，也差不多到了技术负责人试用期考核中期了，这份答卷，应该不会差。

最近同事看到手机上自己做的一个记录APP，也想要一个给她家小朋友学习打开的APP。 设计了一版手机APP的UI，手机版的设计出来之后，想着也做个网页版本的吧。 小蜜蜂学习看板原来是按手机排的，进度卡在上，任务清单在下。我想试个电脑版，打开就能一起看今天要做什么、这周做了多少。 我把手机稿发给 Ling Studio 里的 Ling-3.2-flash，打了这么一句。 “帮我根据这个设计的图，制作成网页” 它给了我一份 HTML，打开就是图一，就是在电脑上套了个手机壳。 网页是做出来了，四个入口也都在，内容还是挤在屏幕中间那一条里。 我那句确实只说了做网页，就是把手机的设计稿复刻了一下，不是真正的网页版本。 第二轮我没再传图，就补了一句。 “能不能适配一下，pc端的网页，而不是模拟的手机端页面” 这次把「今日、练习、资料、成长」挪到了左边，任务清单摊在中间，原来叠在清单上面的进度卡也摆到了旁边。 这是算是真正的网页端了。 如果说第一版是一句话复刻的设计稿，那么第二版是有加入了想法的感觉，理解力更强了， 总的来说不管第一次还是第二次的版本都是能给你需求来完成任务。 在线体验入口： API体验：

这段时间集中面试，公司的阶段、人数、行业、组织和问题千差万别，也想借这次机会更多接触不同的企业来补充自己对于不行业和团队的理解。 我也想把面试中遇到的一些典型问题记录下来，当然会脱敏，意图不是曝光或八卦，主要还是在具象问题中抽象出更合理的解决办法，希望对各位在职场中的朋友有所启发，也希望对在看机会的朋友面试有一些心里准备，哪些是痛点、哪些是雷点，能分清。 我都记录在这篇内容下吧，先来第一个： 一家硬件和 SaaS 软件公司，HR 前置沟通一再强调，团队目前遇到了很深的技术难题，希望有 tl 来带队攻坚！ 但我初步了解了产品形态后，感觉不太对，他们遇到的肯定不是单纯的技术难题，是业务不断发展累加、不断复杂化但又缺少技术架构梳理和重构而欠下的技术债。 后来实际面试中 CEO 和几位技术负责人都参加了，轮到技术负责人提问时，他们提的也确实都是那类问题：业务不能停、个例用户也要支持、业务牵引而缺少技术决策主导等等。 实际上是非常典型的问题，就是业务快速发展的阶段，由于经验能力和时间分配等，忽略了技术架构和工程。当然有一个好的前提是，公司发展很好，且团队意识到了技术上的问题。接下来就来到技术负责人要做的工作：梳理业务痛点、以最痛点的几个问题切入专项解决、先把业务稳住再把专项解决的方案落到各个端。在这个阶段，同步梳理哪些功能可以抽离解耦、各端口协议如何做归一化、数据埋点和日志补全降低排查难度、提升功能使用情况监控。 同时在团队内落地和规范 AI Coding，边解决问题，边渗透 AI Coding 边加速，让研发团队的小的成果不断对业务产生价值，提升信任感和团队的成就感，再内部挖掘可以提供业务附加价值和创新点的方向，部分人和精力投入预研，拿出能打的东西来！ 这样有 2-3 个月时间，就能看到研发团队的变化，也差不多到了技术负责人试用期考核中期了，这份答卷，应该不会差。

最近同事看到手机上自己做的一个记录APP，也想要一个给她家小朋友学习打开的APP。 设计了一版手机APP的UI，手机版的设计出来之后，想着也做个网页版本的吧。 小蜜蜂学习看板原来是按手机排的，进度卡在上，任务清单在下。我想试个电脑版，打开就能一起看今天要做什么、这周做了多少。 我把手机稿发给 Ling Studio 里的 Ling-3.2-flash，打了这么一句。 “帮我根据这个设计的图，制作成网页” 它给了我一份 HTML，打开就是图一，就是在电脑上套了个手机壳。 网页是做出来了，四个入口也都在，内容还是挤在屏幕中间那一条里。 我那句确实只说了做网页，就是把手机的设计稿复刻了一下，不是真正的网页版本。 第二轮我没再传图，就补了一句。 “能不能适配一下，pc端的网页，而不是模拟的手机端页面” 这次把「今日、练习、资料、成长」挪到了左边，任务清单摊在中间，原来叠在清单上面的进度卡也摆到了旁边。 这是算是真正的网页端了。 如果说第一版是一句话复刻的设计稿，那么第二版是有加入了想法的感觉，理解力更强了， 总的来说不管第一次还是第二次的版本都是能给你需求来完成任务。 在线体验入口： API体验：

Why PMs are suddenly valuable again with Tulsee Doshi (@tulseedoshi)—Head of Product for @Google’s frontier AI models, including @Gemini, Nano Banana, Genie, Veo, and more. We discuss: 🔸 The rising value of great PMs 🔸 Google’s full-stack frontier AI strategy 🔸 Why model development is like Snape’s potions class 🔸 Why the PM role has shifted from writing requirements to creating something with “heft 🔸 How to write your first eval Listen now 👇

Whether agents feel like liberation or loss depends on which joy of engineering you lean on most: making, knowing, or mattering. I've seen engineers say many conflicting things about agents: some are bubbling with excitement and for the first time ever, they feel like they're in an all-star lineup, while others mourn for the death of their craft, leaving them feeling hollow. I'm someone who works with agents every day, so I understand these sentiments. Rather than take sides, my hope is that I help you understand this in a more nuanced way. Too often we see two camps: people who love the joy of coding and people who love the joy of shipping. I think this is a gross oversimplification. Rather than asking you to pick a side, I want to ask you to reflect on the elements of your work that are the most nourishing to you. I think most of us have three sources of joy in our work, which we interweave in multiple ways: - The joy of making (or "flow"): the joy of molding things in our hand and feeling that sweet moment when it all clicks into place. - The joy of knowing: the joy of having such a strong mental model of our systems that we sense where a bug will be just by glancing at files. - The joy of mattering: the joy of knowing that you are the expert that it all relied on. Agents affect each of these elements in subtly different ways, which is why this discussion can be so complicated (we're mourning for different losses, and we're arguing from different places). The joy of making is easy to maintain. it just moves up a level. You're not shaping every line anymore. You're shaping the system or factory, in a loop fast enough that flow still happens. And when you miss the old flow, nothing stops you from writing the code yourself. The joy of knowing is especially at risk of erosion, so it's important to pay attention to it. Sometimes you'll realize you're reaching for a design you should be able to conjure automatically, but your intuition comes up with nothing. Picking an option from an agent's suggestions is a different skill than conjuring an idea in the first place. If you always pick and never conjure, the ability to conjure will erode. You can't direct something you don't even loosely understand. If you don't understand your own codebase, you're not directing an agent to do something, the agent is directing you. You matter. Obsolescence does affect you, but, you, your judgment, and especially your need for judgment, has never been more important. You get to decide what problems to solve, and you get to bring your taste and judgment to the work you do. You get to take ownership of it, all of it, whatever ships. That feeling of sadness isn't a sign of failure to adapt. Grief means that you're attached to something, and that it's natural to feel grief when you see your work changing in ways that feel unfamiliar. Lean into the things that make your work yours, and work on them more.