标签：#ai

Code generation tools are powerful and can significantly accelerate development work. Their main limitation is not capability, but context. Without access to organizational knowledge, internal conventions, and system-specific patterns, generated output often requires careful verification. This is why generation tools work best when paired with AI code search, as the latter provides immediate visibility into the existing codebase, making it easier to align AI-generated changes with the realities of the system. In regulated environments, the adoption model may look different. Security or compliance constraints can restrict the use of cloud-based code generation. AI code search still improves developer efficiency across implementation, review, and documentation workflows by enabling fast navigation and comprehension of large multi-repository codebases. What is AI code intelligence, and how does it help in practice? Code intelligence tools help developers find and understand existing code. If a search returns a poor result, the developer simply searches again. Nothing changes in your codebase. Code search also integrates without friction. No new review processes, no changes to CI/CD, no new permissions. Generation tools require policies for AI-written code that stall many pilots before they produce data. Clear metrics for measuring AI code intelligence An AI code search assistant only reads your code, which makes it much easier to measure its impact. You can track simple things like: • how long it takes to find the right piece of code • how quickly new developers get up to speed • how many hours the team spends searching each week If your team of 20 developers each spends 5 hours weekly understanding code, that equals 100 hours of engineering time. At $75 per hour, that’s $360,000 per year. Assume 10% reduction recovers $36,000, a realistic input for an AI ROI framework for tech teams. Faster path to Phase 3 expansion Code generation tools face tough questions from secu

The agents were doing exactly what I told them to. That was the problem. I'd built a pipeline where AI agents could take a spec file, implement a feature, run the tests, review the result, and commit — without me writing a line of code. It mostly worked. Dozens of features shipped. But I kept reviewing the output and feeling like something was off. Not broken. Just subtly wrong in a way that was hard to name. I spent a while blaming the models. Then the prompts. Then the validation steps. Eventually I had to sit with the obvious: the agents were implementing exactly what I'd written. My specs were underspecified. The bottleneck was always me, at the planning stage. The thing most people throw away There's something that feels right about vibe coding. You're operating at the level of intent — describing what you want and letting the model handle the mechanics. That part is genuinely useful. But watch what most people do with the output: Traditional development: Source code → Compiler → Binary (keep the source; regenerate binary anytime) Vibe coding done wrong: Prompt → LLM → Generated code (delete the prompt; commit the code) You've shredded the source and carefully version-controlled the binary. The prompt — your structured description of what you wanted, why, and what "correct" meant — is the valuable artifact. The generated code is what compiles from it. When you discard the prompt and commit only the output, you've lost the thing that actually mattered. The practical consequence shows up six months later: you're staring at code you wrote and spending twenty minutes reverse-engineering your own intent. The spec would have been a thirty-second read. What a spec-driven pipeline is I built what I call an SDLC (Software Development Lifecycle) harness — a system where instead of writing code directly, you write a spec describing what needs to be built, and AI agents handle the implementation, testing, review, and documentation. The spec is the source. The code is what

I built a large feature. That's not what this is about. What changed is the baseline — the standards, docs, and automation that exist now and didn't two weeks ago. Everything after this will be built on top of it. Automated tests now ship with new features QA testers were testing. The product was covered. What didn't exist was automation — no E2E suite, no unit tests for new work, no repeatable spec. Now it does. The manual QA cycle stays. The automation catches what humans miss on the tenth pass. Quality leap going forward. Human hours saved. The next feature ships with both. The baseline is set Knowledge lives in the repo. Bug catalog with root causes — so the same thing doesn't get fixed twice. Tech debt inventory with a phased plan. Testing strategy documented, not assumed. GraphQL schema committed and validated against — drift gets caught before it ships. Pre-commit hooks that enforce the standards automatically. The frontend and backend documentation are cross-referenced as single sources of truth. The agent instructions point to the right places. Everything new builds on what's already written. Schema-first development The workflow is now: if the schema accommodates the new field, reuse what exists. If it doesn't, the schema update creates the new structure, the data migrates, and everything stays consistent. No guessing. No drift. One source of truth for what the data looks like. The feature is what you see. The baseline is what you don't — and it matters more.

In the last essay I played a game with twelve people. Twelve apostles, one teacher, one set of events — and twelve sharply distinct ways of failing and succeeding to understand the same thing. Peter acts before he reflects, Thomas demands the marks in the hands, Matthew counts and structures, Judas asks what you'll give him. I called it pre-cognitive-science cognitive science: the Gospels did the hard work of selecting twelve incompatible human responses to one encounter, and every century since has projected its newest psychology onto that fixed set and found it fits. That essay had a quiet move in it I want to pull on now. The thing that doesn't change, I wrote, is the twelve people. The cognitive vocabularies come and go; the diversity of minds is the invariant. So here is the obvious next question, the one I couldn't stop turning over after I published: what happens when you stop counting people and start counting cultures? Not twelve apostles meeting one teacher, but N civilizations meeting one world. The same exercise, zoomed out A culture is not just a cuisine and a flag. It is a way of thinking that a few million people inherited without choosing it — an implicit operating system for what counts as obvious, what counts as rude, what counts as a good life, what counts as a threat. And like the apostles, each one is an answer to a question . You can describe any of them, I think, with three coordinates. A driver — the deep need the culture is organized around. Survival, honor, harmony, freedom, salvation, mastery, belonging. The thing that, if you threaten it, the culture treats as an attack on existence itself. A provoking question — the founding question the culture exists as a standing answer to. How do we survive the winter together? How do we live rightly before the gods? How do we stay free? How do we keep the harmony so the group doesn't tear itself apart? Cultures are old answers to questions most of their members have forgotten were ever asked. A thin

This is Lowpass by Janko Roettgers, a newsletter on the ever-evolving intersection of tech and entertainment, syndicated just for The Verge subscribers once a week. The 2026 World Cup is breaking streaming records around the world: Brazil's CazéTV YouTube livestream of that country's opening game against Morocco surpassed 12 million concurrent viewers, a new milestone […]

Netris provides software that runs on network switches, and offers a platform that helps neocloud operators reduce the time it takes to go live.

Now that Bungie has moved on from Destiny 2, the game studio is being hit with its latest round of layoffs. In a statement posted on X, the studio said that "we are announcing a reduction in force as we reorganize Bungie." No specific numbers were revealed. But in a separate statement, Hermen Hulst, CEO […]

2 days left to lock in your spot at TechCrunch Founder Summit 2026 and save up to $190 before Early Bird rates expire on June 26 at 11:59 p.m. PT. Register here.

I wasn't surprised when I got the call that my dad was dying, even though we'd been estranged for many years. He'd suffered addiction for decades and eventually ran out of time, which also meant he ran out of time to reconcile with me. About 15 years after we stopped talking, my aunt and uncle […]

Adobe said that it will integrate Topaz Labs' tools across its apps.

Building Rule-Validator: Why I Built a Java Annotation-Based Rule Engine After 3 Years of Fighting Business Rules Let me tell you a story. For three years, I've been fighting the same battle in enterprise Java development: business rule validation . Honestly, every time a new requirement comes in like "this order must be approved if amount > 10000 AND user level > 3 AND discount < 0.1", I'd end up with a 500-line method full of if-else that nobody wants to touch. Sound familiar? I tried every existing solution: Drools: Too heavy, requires learning a new DSL, impossible to debug Spring Validation: Great for basic validation, but can't handle complex business rules nicely Hand-written if-else: Works, but becomes unreadable after 10 rules Expression engines like Aviator: Still externalized, breaks compile-time checking So here's the thing — I learned the hard way that what Java developers actually want is simple, annotation-based, compile-safe rule validation that lives right next to your code. That's why I built rule-validator . What is Rule-Validator? Rule-validator is a lightweight Java library that lets you define business rules using annotations directly on your classes . No DSL, no external files, no magic — just simple, testable, maintainable rules. The core idea is: Each rule is a method annotated with @Rule Rules can be grouped and ordered You get full Java compile-time checking Everything stays in your code, where it belongs Here's a quick example to show you how it works: import com.github.kevinten10.rulevalidator.annotation.Rule ; import com.github.kevinten10.rulevalidator.annotation.RuleGroup ; import com.github.kevinten10.rulevalidator.core.RuleExecutor ; import com.github.kevinten10.rulevalidator.result.RuleResult ; // Define your business object public class Order { private BigDecimal amount ; private Integer userLevel ; private BigDecimal discount ; // getters and setters public BigDecimal getAmount () { return amount ; } public Integer getUserLevel ()

I wanted to tell my girlfriend 'I missed you today' in Farsi and have it sound like something a person would actually say, not a phrase pulled from a travel guide. Every tool I tried — Google Translate, DeepL — gave me one answer. No register. No note on whether it was too formal for a text message or too casual for a letter. Just a string of words and the implication that language has one correct answer per sentence. So I built konid: it returns three options for anything you want to say, ordered casual to formal, each with the register explained and the cultural nuance between them described. It also plays audio pronunciation through your speakers directly, using node-edge-tts — no API key, no copy-pasting into a separate tab. The interesting engineering constraint was deployment target. I wanted this to live where I already work, not in a separate browser tab I forget to use. That meant MCP. A single MCP server running at https://konid.fly.dev/mcp now serves four clients without any client-specific code: # Claude Code claude mcp add konid-ai -- npx -y konid-ai # ChatGPT (Developer mode, Actions) # endpoint: https://konid.fly.dev/mcp Cursor, VS Code Copilot, Windsurf, Zed, JetBrains, and Claude Cowork all connect the same way. The server doesn't know or care which client called it. The output structure for a query like 'I missed you today' in Japanese looks roughly like this: Option 1 (casual): 今日会いたかった Register: intimate, fine for close friends or a partner Note: dropping the subject is natural here; adding あなたに would feel stiff Option 2 (neutral): 今日、あなたのことが恋しかったです Register: polite, appropriate for someone you're close to but addressing respectfully Option 3 (formal): 本日はお会いできず、寂しく思っておりました Register: formal written Japanese; would be unusual in a personal context The nuance comparison is the part I couldn't get anywhere else. Knowing that option 3 exists and that you would almost never use it for a personal message is actually load-bearing information if you're l

AI Dev Weekly is a Thursday series where I cover the week's most important AI developer news, with my take as someone who actually uses these tools daily. OCR had a week. Mistral dropped OCR 4 with bounding boxes. Baidu open-sourced a model that beats DeepSeek-OCR. Claude got a permanent home inside Slack. And the Fable 5 ban fallout keeps getting uglier: Alibaba was apparently stealing Claude's capabilities, and even the NSA lost access to Mythos. Meanwhile, GPT-5.6 is delayed to mid-July. Let's go. 1. Mistral OCR 4: document AI gets serious Mistral launched OCR 4 this week. It's not just another OCR model. It's a full document understanding system with paragraph-level bounding boxes, confidence scores, and support for 170 languages. The specs: $4 per 1,000 pages (standard), $2 per 1,000 pages (batch) Paragraph-level bounding boxes with coordinates 72% win rate in blind tests against competitors Available on la Plateforme, Microsoft Foundry, and self-hosted for enterprise Top score on OlmOCRBench Why this matters for developers: Bounding boxes change everything. Previous OCR models gave you text. Mistral gives you text + where it is on the page. That unlocks document search, compliance systems, and any workflow where page structure matters. My take: At $4/1000 pages, this is competitive with Google Document AI ($5) and significantly cheaper than building your own pipeline. For enterprise document processing, this is probably the best option right now. For budget-conscious developers, Baidu's free alternative (see below) is worth considering. Full comparison in our Mistral vs DeepSeek vs Baidu breakdown. 2. Baidu open-sources Unlimited-OCR While Mistral went commercial, Baidu went open. Unlimited-OCR is a 3B-parameter MIT-licensed model that processes multi-page PDFs in a single inference pass. Key features: Built on DeepSeek-OCR architecture (SAM+CLIP + DeepSeek-V2 MoE decoder) Reference Sliding Window Attention for memory efficiency on long documents Tables to HTM

For a decade, "what's your frontend stack?" was a loaded question. jQuery vs. Backbone. Angular vs. React. Webpack vs. everything. The churn was exhausting, and a non-trivial chunk of our job was just keeping up. That era is quietly ending — not because we won the framework wars, but because the questions moved up a layer. The interesting problems in frontend today aren't about which library renders a list. They're about how rendering, data, and increasingly generation fit together. And AI is sitting right in the middle of that shift. The stack consolidated more than we admit Look at what most new production apps actually reach for in 2026: React or Svelte/Vue for the component model, with the framework wars settling into "pick one, they're all fine." A meta-framework — Next, Remix/React Router, SvelteKit, Nuxt — because nobody hand-rolls routing, data loading, and SSR anymore. TypeScript by default. Not a debate. The plain-JS greenfield project is now the exception. Server-first rendering (RSC, islands, streaming) as the baseline, with the client bundle treated as a cost to minimize rather than the center of the universe. The center of gravity moved back toward the server — but a smarter server that streams HTML, hydrates selectively, and treats the network boundary as a first-class design concern. The pendulum didn't swing back to 2010; it spiraled forward. What AI actually changed (and what it didn't) The hype says "AI writes the frontend now." The reality on the ground is more specific and more interesting. It collapsed the cost of the first 80%. Scaffolding a component, wiring a form, translating a Figma frame into JSX, writing the Tailwind for a layout — these used to be hours of work and are now minutes. That's real, and it's already changed how teams estimate. It did not collapse the last 20%. Accessibility edge cases, focus management, race conditions in async state, the weird Safari bug, the design-system invariant that isn't written down anywhere — this i

AI harnesses are the new vendor lock-in. To swap across harnesses easily without rewriting your app, LiteLLM launched the Lite-Harness SDK . Run your prompt across different harnesses: from lite_harness import query , AgentOptions prompt = " Fix the failing test " # Claude Code harness async for message in query ( prompt = prompt , options = AgentOptions ( harness = " claude-code " , model = " claude-opus-4-8 " ), ): print ( message ) # Codex harness async for message in query ( prompt = prompt , options = AgentOptions ( harness = " codex " , model = " gpt-5.5 " ), ): print ( message ) To enable cost controls, fallbacks, and logging, point it to your LiteLLM AI Gateway: export LITELLM_API_BASE = https://litellm.your-company.com/v1 export LITELLM_API_KEY = sk-litellm-... Engineer's Takeaway: This SDK unifies how you invoke the agents, not how they run internally. Each harness keeps its native loop and tool-calling semantics. It is perfect for A/B testing agent performance and centralizing costs, but remember it is in public beta, so custom tool injection might require extra work! The Problem I Had My team was building an internal bot to fix failing CI/CD tests. We had three engineers advocating for three different harnesses: one wanted Claude Code, another Codex, and another Pi AI. Without an abstraction layer, we would have had to maintain three forks of the same bot , with three different SDKs, three logging systems, and three ways to track costs. It would have been an impossible maintenance burden. How Lite-Harness Helped The SDK solved that exact pain point in three concrete dimensions : 1. Unified Invocation (Time Savings) Instead of maintaining three separate implementations, I had a single query() that routed to whichever harness I wanted. Switching from Claude Code to Codex was literally just changing a string in the options. This allowed us to do real A/B testing in production for two weeks without rewriting any core logic. 2. Cost Observability (The Killer

Here's a thing that surprises people the first time: an email sent through the API does not carry the signature the user set up in Gmail or Outlook. Provider signatures live in the provider's compose UI, and a programmatic send bypasses that entirely, so a message your app sends goes out with no signature at all unless you add one. The Nylas Signatures API is how you add it: store an HTML signature once, then attach it to a send by ID, and the signature gets appended to the message for you. This post covers signatures from two angles: the HTTP API your backend calls, and the nylas CLI for creating and testing one from the terminal. I work on the CLI, so the terminal commands below are the ones I reach for when I'm setting a signature up. Nylas signatures are separate from provider signatures The first thing to get straight is that these are not the user's existing signature. Nylas doesn't sync the signature configured in Gmail, Outlook, or any other provider, and that provider signature is never applied to mail sent through the API. If a message your app sends needs a sign-off, you create that signature with this API and attach it explicitly; there's no inheriting it from the connected account. That separation is deliberate, because a programmatic send is a different context from a person typing in their webmail. It does mean the responsibility is yours: a user who connects their mailbox expecting their familiar signature to appear on app-sent mail won't get it automatically. Stored signatures are grant-scoped, living at /v3/grants/{grant_id}/signatures , so each connected account has its own set, and they're HTML, so a branded sign-off with a logo and links works the same as a plain one. Create a signature Creating a signature is a POST /v3/grants/{grant_id}/signatures with a name and an HTML body . The name is for you, a label to find it by later; the body is the markup that gets appended to outbound mail. The response returns the signature with its ID, which is w

Amazon’s latest India investment comes as global tech companies race to expand AI infrastructure in the country.

To celebrate its new status as No. 1 in JD Power's initial quality ranking among mainstream automakers, Ford is opening up about the challenges it has faced in recent years, especially around its reliance on automated systems in production and design. It turns out that those automated systems were not as robust as previously assumed, […]

Your QA team built 50 automated tests in the first quarter. Leadership was thrilled. Coverage was...

IBM’s nanostack transistors could boost chip performance or energy efficiency.