标签：#disc

TL;DR Welcome back to Dev Opportunity Radar. This is a weekly series where I share opportunities,...

Over the past year, AI has become part of many developers' daily workflow. It can generate code, explain unfamiliar frameworks, review pull requests, and even suggest architectural patterns. But I've noticed that the biggest impact isn't on writing code faster. It's on how we think about software architecture. With AI handling repetitive implementation tasks, it feels like architects and senior engineers are spending more time on system design, scalability, security, integrations, and long-term maintainability rather than syntax and boilerplate. At the same time, AI-generated code isn't always production-ready. It still requires strong engineering judgment, careful reviews, and a solid understanding of the underlying architecture. I'm curious how other developers are experiencing this shift. Has AI changed the way you design software systems? Do you trust AI when making architectural decisions? Which parts of software architecture do you think should always remain human-led? Have AI tools improved your team's productivity, or introduced new challenges? I'd love to hear real-world experiences, lessons learned, and different perspectives from the community.

The trust problem nobody scopes correctly When companies talk about trust in AI, they almost always mean trust in the model. Is the output accurate? Is it hallucinating? Can we rely on what it says? Those are valid questions but they're the wrong starting point. The trust that actually determines whether AI gets adopted or quietly abandoned inside an organization isn't about the model. It's about the system surrounding it. The four questions that determine Every team evaluating AI in a production workflow eventually runs into the same four questions. Not about model quality. About operational control. Can we understand the outputs? Not just "does the answer look right" but can someone on the team explain why this output was produced and whether it's appropriate for this specific context. An AI that generates correct-looking code or recommendations that nobody can verify is a system that runs on hope. Hope doesn't survive the first incident. Can we validate the decisions? When the AI recommends an action or generates an output that feeds into a business process, is there a way to check it against the actual requirement? Or does the team just trust the output because questioning it is harder than accepting it? The second one is more common than anyone admits. Can we intervene when needed? When something goes wrong, how fast can a human step in? Is there a kill switch? Is there a fallback path? Or does the AI output flow directly into downstream systems with no circuit breaker? The teams that skip this question are the ones that discover the answer during an incident. Can we trace what happened afterward? When an AI-generated decision produces a bad outcome, can you reconstruct the chain? What input went in, what output came out, what context was available, what wasn't? Without traceability, post-mortems hit a dead end, and the same failure happens again. Why opaque systems don't survive real operations There's a tempting argument that opacity is fine as long as the sy

When I started learning iOS development, I thought the hardest part would be writing Swift code. I...

We have all been riding the massive vibe coding wave lately. It feels like pure magic to sit back, tell an AI assistant what to build, and watch a full application appear out of thin air. But if you have ever tried to take that exact same web workflow and deploy a smooth, native app onto an iPhone or Android, you know exactly where the frustration sets in. Are you a vibecoder who loves to build applications and you have built many websites? You have built and deployed many websites. Now you really want to make a mobile application that could disrupt the market and go really viral. Have you heard of FlutterFlow ? Have you tried using it? If the answer is no, then I will tell you about FlutterFlow and then you can decide whether you want to check it out and vibe code mobile applications. I will share the app that I created as well. What is FlutterFlow anyway? Have you ever tried building mobile applications and heard of Flutter and Dart? If you haven't, you should definitely check them out. When I was in college looking for a path to choose whether to pursue app development or web development. I explored both options. While exploring app development, I used and built applications using Flutter, an open-source framework created by Google, which uses a programming language called Dart. While Flutter itself is built by Google, FlutterFlow is an independent, visual low-code platform founded by ex-Google engineers. Today, many of us are familiar with AI vibe-coding tools like Cursor and Claude, which allow us to generate code for websites using conversational prompts. FlutterFlow, however, operates differently than vibe-coding: instead of writing code through chat prompts, it provides a visual, drag-and-drop canvas where you can build and design native mobile applications visually while it automatically generates clean Flutter code in the background. I recently had the opportunity to attend a workshop held by the FlutterFlow team and there, I was blown away by the magic of

by Peter Yang, Behind the Craft Today, I want to share 18 hot takes on where I think the AI market is headed. AI is in a weird place right now. The government is restricting access to frontier models, enterprises are becoming conscious of token costs, and everyone’s trying to rebuild their product for agents first instead of humans. I’ve interviewed dozens of AI leaders and spent far too much time following these topics on X/Twitter. Here are 18 hot takes on where I think AI is headed next: The frontier-only AI stack is collapsing The AI super app era is here Traditional software risks becoming a dumb pipe for agents Cloud agents and collaboration are the next wave The Frontier-Only AI Stack Is Collapsing Tokenmaxxing at frontier API prices makes no sense. Uber burned through its entire 2026 AI budget in 4 months, Microsoft moved engineers off Claude Code due to cost, and companies are realizing that running everything on frontier models can get expensive fast. Tokenmaxxing makes sense when you’re on a subsidized $200/month plan but is unsustainable at API rates. Companies will rely on a portfolio of models. Coinbase recently cut its AI spend nearly in half by switching engineers to Chinese open-source models like GLM and Kimi. Airbnb and Pinterest have done the same with Alibaba’s Qwen models. I believe that this will be the default path forward — using frontier for high-stakes work and cheaper models for everything else. China’s open-source strategy is working. Chinese models are taking market share from frontier models at US companies. China is also building the full AI stack — from energy (e.g., solar, nuclear) to data centers to domestic chips. The Chinese government is planning a $295B investment in AI data centers with at least 80% of the chips built domestically. Frontier labs are in a catch-22 situation. If they release great open-source models, they might undercut their own frontier API revenue. If they gate the best models behind a trusted list, companies

When the enemy is in distress, exploit the opportunity to seize advantage. — The 36 Stratagems, Loot a Burning House Who's Leo — In the last story , he was CoreStack's backend lead — the guy who built the core system alone over five years with zero P0 incidents. Then a new CTO named James showed up, spent $8M on his old employer's product, and laid off Leo's entire team. Thirteen days later, that $8M AI system collapsed — three agents fighting over context, OOM taking down six GPU servers, a 37% order duplication rate, and 2,300 customer complaints. Leo pulled the old system off his laptop, flipped one line of Nginx config, and restored service in thirty seconds. The CEO called him at 3 AM begging him to come back. He came back. Three conditions: kill the paid AI product, AI assists only — never touches the primary pipeline — and engineers decide the architecture, not the guy writing checks. The CEO agreed to all of it. So who's Leo now: CoreStack's CTO. Technically confident to the point of arrogance. Zero talent for upward management. No idea how many people he pissed off on the board with those conditions. Doesn't care. He only knows one thing — the system he built is still running. That's all the proof he needs. Then a Slack message cut him off. The Signal 12:47 AM. CoreStack's CTO gets a Slack notification. The account has no profile picture, no display name, no status. Account creation timestamp at the bottom — 00:43. Four minutes old. Seven characters: Check CodeForge's status page. Leo taps it open. CodeForge's status page is all red. Payment Routing — Major Outage. Investigating. All customers affected. Status has been active for approximately 3 hours. He pulls up CoreStack's CRM. The sales team's prospect list has ShopStream at #2 — a potential whale, with "Current Provider" reading CodeForge. E-commerce platform doing 470,000 transactions a day . An hour of downtime costs them $210,000 . If this drags on until morning? He doesn't want to do the math. Core

I used to waste hours tweaking and re-tweaking my AI model prompts. It was like trying to find a needle in a haystack—I'd make a change, run the code, wait for the results, and then... nothing. The output would be inconsistent, unhelpful, or just plain wrong. I'd try again with tiny modifications, rinse and repeat, until I was about to pull my hair out. It wasn't until I stumbled upon the concept of reusable prompt templates that everything changed. It was like a switch had flipped—my code started producing consistent results, and I finally understood why. No more guesswork, no more frustration. Just good old-fashioned productivity. A simple shift from writing one-off prompt strings to using reusable templates is the key to reducing prompt overhead, increasing consistency, and getting back to doing what we love—building amazing, AI-driven applications. From Chaos to Control: A Simple Example Let's make this tangible. Imagine you're building a feature to generate a short story, but for different characters. Before: The Inconsistent, One-Off Way Without a template, you'd likely write a new prompt each time, introducing small, unintentional differences that lead to wildly different results. Two separate prompts = inconsistent, unpredictable output prompt_for_alex = "Write a short story about a character named Alex who is trying to get to work on time, but keeps getting delayed in a busy city." prompt_for_jordan = "Generate a story about someone named Jordan. They're late for work and stuck in traffic in a big city." See the problem? The tone, wording, and details are different. You have no control over the consistency of the output. After: The Clean, Templated Way Now, let's use a single template. We define the core structure once and simply pass in the parts that change. Now, let's use a single template. We define the core structure once and simply pass in the parts that change. One template = consistent, predictable output story_template = "Write a short story about

I sat down to work for 2 hours. I actually worked for 45 minutes. Sound familiar? You open your...

co-written with UnitBuilds, who built most of this out loud in the comments of my last piece. I...

Exhaust the enemy's strength without fighting. Weaken the strong by nurturing the soft. — The 36 Stratagems, " Wait at Leisure While the Enemy Labors " P flipped the business card over and wrote one letter on the back: P . Then P walked into the conference room. P didn't do opening lines. P doesn't have a name — not yet, not in this series anyway. But if you've read the earlier stories, you'd recognize the signature. The first story — P's own article got flagged as "low quality" by the company's AI moderation system. P dug into the internal API, pulled 347 flagged records — effective accuracy came out to 38%. More false positives than correct identifications. The second story — an AI payment gateway processing $2.8 billion. The CTO backed it with formal verification, claimed it was "mathematically bulletproof." P spent eight months quietly building an adversarial testing pipeline, and proved the gateway would approve illegal transactions. P won both times. P left zero fingerprints both times. After those two jobs, P stopped working for other people. This time, P got brought in as an independent evaluator. Two Companies, One Customer, Zero Questions The customer was a mid-sized industrial IoT firm called FirmCore . Their production-line gear had been running for almost a decade. The monitoring system was going down once a month, and management had finally had enough. They decided to bring in an AI monitoring platform. A good call — right up until they decided to run two vendors through POC at the same time and pick a winner. "We want to see who can actually cover our failure modes," the VP said in the meeting. "We've also brought in an independent evaluator." P was that evaluator. The two AI monitoring companies were MonitorAI and SentryWave . MonitorAI's pre-sales team went first, slides blazing with "99.3% fault coverage, validated across 3 manufacturing customers." SentryWave followed right behind: "99.7% coverage, 7-day deployment" — bigger numbers, bolder font.

I'm curious... What's the one feature that instantly makes you stop using a resume builder? For me, it was simple: You spend time creating your resume, everything looks great, and then the site asks you to pay just to download it. That experience inspired me to build Resumship, a resume builder where downloading your resume is completely free. Now I'm thinking about the next features to add, and I'd love to hear from the community. If you were building the ideal resume builder, what features would you include? AI-powered resume suggestions? Better ATS optimization? More templates? Portfolio integration? Cover letter generation? Something completely different? If you have a minute, I'd also love for you to try Resumship and share your honest feedback. 🌐 https://resumship.com Your feedback will directly influence what gets built next. Every suggestion, bug report, or feature request helps make the platform better for everyone. Looking forward to hearing your ideas! 🚀

An agent opened a pull request on our service last week. Six hundred lines. It rewrote how we handle webhook retries and deduplication, an area that is fiddly and easy to get subtly wrong. The diff was clean. The tests were green. The commit messages were better than mine usually are. And I felt the specific dread that I think a lot of engineers are starting to feel in 2026. I was the reviewer. I had not written any of this. I had no idea why it was shaped the way it was. To review it properly, the way I would want my own code reviewed, I was looking at the better part of an hour of carefully reconstructing intent from the code itself. I did not have that hour. So I did what almost everyone does in that situation, which is skim it, decide it looked reasonable, and approve. That moment is the actual problem with AI-written code, and it is not the one people argue about. The bottleneck moved, and most teams have not adjusted The tired debate is whether agents write good code. In 2026 that argument is mostly over. They do. They plan, they read the codebase, they run the tests, they back out of dead ends, they open pull requests that clear most review bars. If you are still litigating whether the code is any good, you have not used a current agent in a while. But here is what follows from that, and it is the part teams have not absorbed: if writing the code is no longer the slow step, then reviewing it is. And review does not scale the way generation does. An agent can produce five well-tested pull requests before lunch. Your senior engineers cannot deeply review five pull requests before lunch, not on top of their own work. The volume went up and the review capacity did not, and something has to give. What gives is the depth of review. It degrades, quietly, into a skim. People approve fluent diffs they have not truly read, because reading them properly costs more time than anyone has. The green check still appears. It just means less than it used to. That is a governan

Crossword puzzles are easy. But what if you had to solve one while running inside the hardware constraints of a Large Language Model?

"AI agent" is one of those terms that's everywhere right now, and it's thrown around loosely enough...

One of the things I love most about the tech community is that there isn't a single path to becoming...

TL;DR Anthropic recently published When AI Builds Itself, an essay explaining how AI is...

Welcome to this week's Top 7, where the DEV editorial team handpicks their favorite posts from the...

AI เขียนโค้ดแทนเราได้แล้ว — แล้วเราจะเหลืออะไรให้ทำ? มีประโยคที่ได้ยินบ่อยขึ้นทุกวัน: "เดี๋ยวนี้ใครยังไม่ใช้ AI ช่วยเขียนโค้ดบ้าง?" คำตอบคือ — แทบไม่มีแล้วครับ ตั้งแต่ GitHub Copilot, Cursor, Claude, ChatGPT ไปจนถึง agent ที่เขียนโค้ดเองได้ทั้ง project — เราใช้ AI ใน level ที่ต่างกัน: Level หน้าตา ตัวอย่าง 🎵 Vibe Coding พิมพ์สิ่งที่อยากได้ กด accept อย่างเดียว "เขียนหน้า login ให้หน่อย" → กด tab tab tab 🧩 Prompt-Guided คิดก่อน ถามทีละส่วน ตรวจทุกอย่าง "สร้าง UserService ที่ใช้ bcrypt hash password" 🛠️ Skill/Lint-Guided ใช้ AI เป็น editor ชั้นสูง — lint, refactor, test "refactor function นี้ให้เป็น table-driven test" 🏗️ Agent-Based ให้ AI run ทั้ง project — spawn subagent, PR, deploy "พอร์ต microservice นี้จาก Express ไป Fastify" แล้วคำถามคือ — ถ้า AI ทำทั้งหมดนี้ได้ แล้วมนุษย์อย่างเราเหลืออะไร? Unit Test — ตัวอย่างที่เห็นชัดที่สุด ลองดู unit test ที่ AI เขียนให้: // 🤖 AI-generated test func TestCalculateDiscount ( t * testing . T ) { tests := [] struct { name string input float64 expected float64 }{ { "zero" , 0 , 0 }, { "normal" , 100 , 90 }, // 10% discount { "max" , 1000 , 800 }, // 20% discount } for _ , tt := range tests { t . Run ( tt . name , func ( t * testing . T ) { result := CalculateDiscount ( tt . input ) if result != tt . expected { t . Errorf ( "got %v, want %v" , result , tt . expected ) } }) } } ดูเผิน ๆ — สวย, table-driven, ถูกต้องตาม Go convention 1 แต่ถามหน่อย — test นี้บอกอะไรเกี่ยวกับ business? "ส่วนลด 10% สำหรับยอด 100 บาท" — ทำไมต้อง 100? เป็นกฎจากที่ไหน? "ส่วนลด 20% เมื่อยอดถึง 1000" — แล้วถ้าลูกค้าเป็น member ได้เพิ่มอีก 5% ล่ะ? input: 0, expected: 0 — test นี้ cover edge case หรือแค่ cover บรรทัด? AI test ได้ถูกต้องตาม function — แต่มัน ไม่รู้ว่า business จริง ๆ คืออะไร AI ไม่รู้ Business Context — และจะไม่มีวันรู้ นึกภาพระบบ e-commerce: ลูกค้าซื้อสินค้า → ระบบตัดสต็อก → คำนวณส่วนลด → คิดค่าส่ง → ออกใบเสร็จ AI แยก test ทีละ function ได้: ✅ TestDeductStock — "ตัดสต็อก 1 ชิ้น" ✅ TestCalculateDiscount — "ส่วนลด 10%" ✅ TestCalculateShipping —

you probably didn't think about this when you signed up. you entered your card details, verified...