标签：#m

For decades, developers were judged by one thing: How much code they could write. The best programmers wrote faster. Debugged faster. Built faster. That era is ending. The next generation of developers won't spend most of their time writing code. They'll spend it directing AI. Welcome to the age of the AI Orchestrator. The Evolution of Software Development Software development has always evolved. First, developers wrote machine code. Then came assembly. Then high-level languages. Then frameworks. Then cloud platforms. Then DevOps. Each evolution removed repetitive work and let developers focus on bigger problems. AI is simply the next step. But this time, it isn't replacing a tool. It's becoming a teammate. Coding Is Becoming a Smaller Part of the Job Building software isn't just writing code. A typical project includes: Understanding requirements Researching documentation Designing architecture Writing code Reviewing code Debugging Testing Writing documentation Deploying applications Monitoring production Fixing incidents Only one of those is coding. Everything else is coordination and decision-making. That's where AI is changing the game. From Programmer to Orchestrator Think about how modern teams work. A tech lead rarely writes every line of code. Instead, they: Assign work. Review solutions. Provide feedback. Make architectural decisions. Remove blockers. Developers are beginning to work with AI in much the same way. Instead of writing every function, they'll: Define the goal. Provide the right context. Choose the right tools. Review AI-generated code. Run tests. Improve weak areas. Approve the final result. The value shifts from typing code to guiding its creation. What Does an AI Orchestrator Do? An AI orchestrator doesn't ask one question and accept one answer. They manage a workflow. For example: Break a large project into smaller tasks. Give each AI the context it needs. Decide when to retrieve documentation. Decide when to search the codebase. Ask AI to g

Introduction In large-scale Unity development, GC Alloc can quietly become a real problem. At first, nothing looks wrong. But as the project grows and you add more enemies, UI, master data, events, states, notifications, logs, and other systems, small allocations that happen every frame begin to pile up. LINQ is especially convenient. var aliveEnemies = enemies . Where ( x => x . IsAlive ) . OrderBy ( x => x . DistanceToPlayer ) . ToList (); It is readable. But if this kind of code runs every frame, it can become a source of both GC Alloc and CPU overhead. Unity's official documentation also recommends reducing frequent managed heap allocations as much as possible, ideally getting close to 0 bytes per frame. https://docs.unity3d.com/2022.3/Documentation/Manual/performance-garbage-collection-best-practices.html For general GC Alloc best practices, this article refers to the Unity 2022.3 documentation, because the general guidance still applies. Unity 6-specific GC behavior is covered later using the Unity 6.0 documentation. This article assumes Unity 6.0 as the minimum Unity version and explains how to choose between regular LINQ and ZLinq in production code. Unity 6.0 uses the Roslyn C# compiler, and its C# language version is C# 9.0. However, some C# 9 features, such as init-only setters, are not supported. https://docs.unity3d.com/6000.0/Documentation/Manual/csharp-compiler.html The short version The point of this article is not to ban LINQ completely. Do not use LINQ in hot paths just because it is readable. Do not assume ZLinq solves everything just because you introduced it. Those are the two main ideas. A rough guideline looks like this: Area Guideline Editor extensions, build scripts, debug code Regular LINQ is usually fine Startup, loading, initialization LINQ can be fine, but measure when data size is large Update / LateUpdate / FixedUpdate Avoid LINQ by default Code that is not per-frame but still called frequently Consider ZLinq Code that materializes res

Google added two new models to the Gemini API today: Nano Banana 2 Lite (image generation) and Gemini Omni Flash (video generation + editing). Neither is the Gemini 3.5 Pro release people have been waiting for, so it's easy to miss. Here's what's actually in them. TL;DR Nano Banana 2 Lite: gemini-3.1-flash-lite-image = text-to-image in ~4s, $0.034/1K images Gemini Omni Flash: gemini-omni-flash-preview = video gen + conversational editing, $0.10/sec Both are built to be chained: generate an image fast, then animate it into video Neither model is positioned as a quality upgrade = both are cost/speed plays Nano Banana 2 Lite Model ID: gemini-3.1-flash-lite-image Text-to-image output in about 4 seconds $0.034 per 1K-resolution image Positioned as the direct replacement for the original Nano Banana ( gemini-2.5-flash-image ) - if you're on that model, this is a drop-in upgrade Available in Google AI Studio, Gemini API, Gemini Enterprise Agent Platform, and consumer surfaces (Search AI Mode, Gemini app, Photos, NotebookLM, Flow, Google Ads) Gemini Omni Flash Model ID: gemini-omni-flash-preview Public preview in Google AI Studio and the Gemini API Conversational editing - refine a generated video using plain-language instructions instead of re-prompting from zero Multimodal referencing - combine text, image, and video inputs to keep a scene consistent $0.10 per second of video output (same rate as Veo 3.1 Fast) Known limitations right now Generations capped at 10 seconds No audio reference uploads yet No scene extension yet Video references under 3 seconds are accepted by the API schema but not correctly processed yet Character consistency across scene changes/pans still has rough edges Google says longer durations are coming. The part worth paying attention to: chaining them Generate an image with Nano Banana 2 Lite (fast, cheap) Pass that image as a reference into Omni Flash Omni Flash animates it into a video Both models are optimized for throughput and cost, not for to

At the beginning of June I started a “ Claude withdrawal ” challenge. The plan was to run MiniMax 3 for a month, to see if I can get the same level of quality, but at 5x less the price. Until then, Claude Code was my main driver, with MiniMax on the backup, for when I was running out of quota, or sometimes for code review. The monthly bill for Claude was $100 on the Max plan, whereas for MiniMax I would pay $20 for the Token plan. All in all, it seemed like an interesting experiment. Then, half way through the challenge, Grok came into the picture. I got a very interesting offer at $35 for 3 months, then $35/month. But Grok has something neither Claude, nor MiniMax can give me out of the shelf: video and image generations. The only unknown was if switching from Claude Code to Grok will still maintain the same coding power. So I instantly took the offer, and did whatever I had to do to understand if this was the right path. And here comes the “whatever I had to do”, in plain technical terms. Switching from Claude Code to Grok – the Actual Steps The switch itself was interesting because I didn’t want to lose the Claude Code interface. I like the harness. The way it works with my codebase, the commands, the flow. So I used a helper called cliproxyapi . It’s a small proxy that sits between the Claude Code client and whatever model you point it at. You run it locally, tell it to forward requests to Grok’s API instead of Anthropic’s. Then you launch Claude Code the same way you always do, but it talks to Grok under the hood. Here’s how it goes in practice. Step 1: Install the proxy. I used brew to install it, I’m on a Mac, and also because I wanted to have it started as a service. Step 2: Set two environment variables. One is the target API base URL, for Grok that’s something like https://api.x.ai . The other is your API key. "env" : { "ANTHROPIC_BASE_URL" : "http://localhost:8317" , "ANTHROPIC_API_KEY" : "cliproxy-local-key" } , Notice how we use “cliproxy-local-key”, be

The video game disc is dead, and Sony's been planning to kill it for some time, according to a report out of Austria. The man who leads Sony's discmaking operations, Sony DADC president Dietmar Tanzer, told ORF Salzburg that the company's Thalgau plant produces 600,000 discs every day, half of which are for PlayStation. But […]

Book: Decoupled PHP — Clean and Hexagonal Architecture for Applications That Outlive the Framework Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub You've been handed the ticket everyone dreads: move the app off Laravel and onto Symfony. Maybe the team standardized on Symfony. Maybe a Messenger-and-Doctrine shop acquired you. Maybe someone decided Eloquent's global scopes had cost enough Friday nights. The estimate comes back in quarters. Someone quotes the phrase "big rewrite" and the room goes quiet, because everyone remembers the last big rewrite. Here is the question that decides whether this is a quarter or a year: how much of your business logic imports the framework? If your PlaceOrder logic reaches into request() , calls Order::create() on an Eloquent model, and opens a transaction with DB::transaction() , then the framework is the application and you are rewriting the application. If your business rules sit in plain PHP classes that never heard of Laravel, then the migration is an adapter swap, and adapter swaps ship one route at a time. What the framework actually owns Strip a typical Laravel app down and you find three categories of code. The first is your domain and use cases: the rules about what an order is, what placing one means, when it can be cancelled. This is the part the business pays for. It should not import a framework at all. The second is glue that translates the outside world into calls on that logic: controllers, form requests, Eloquent models, queue jobs, service providers. This is framework-specific by definition. The third is infrastructure your code talks to through interfaces: the database, the queue, the mailer, the payment gateway. A framework migration only touches the second category. The trouble is that most Laravel apps let the first and

I Spent 30 Days Comparing Startup and Enterprise AI APIs Look, I'm just a dude building a SaaS side project. Not enterprise, not Fortune 500, just me and a few friends trying to ship something useful. So when I started hitting AI API walls, I went down the rabbit hole of figuring out what the heck to do. And honestly? Most guides out there are written by people who clearly have never had to choose between buying groceries or paying for OpenAI credits. They're either too corporate ("here's our enterprise procurement guide!") or too naive ("just use the cheapest API!"). So I figured I'd write the guide I WISH existed when I started. And I'm gonna throw in some enterprise stuff too because I consulted for a bigger company last year and saw what THEY deal with. Different worlds, I tell ya. Let me break this down properly. Why I Almost Just Used DeepSeek Directly Okay so here's the thing. When I first started, I was like "DeepSeek is dirt cheap, let me just sign up there and call it a day." I mean, the pricing was wild. Like cents per million tokens. How could I lose? Then I tried to actually sign up. Chinese phone number required. WeChat Pay or Alipay only. No PayPal. No Visa. Nothing. And I get it, that's their home market, but for me sitting here in my apartment in the US? Absolute dead end. So I started looking at aggregators. Tried like four of them. Some had weird pricing. Some had models that didn't actually work. One of them straight up charged me for tokens I never used (still salty about that). Then I landed on Global API and honestly I gotta say, it just worked. Email signup, PayPal, and I could test DeepSeek AND Claude AND Qwen all with one key. That's when I realised going direct to providers is kind of a trap if you're small. Let me show you the actual problem with going direct. The "Go Direct" Trap Here's what happens when you sign up direct with various providers: Problem What Happens to You Locked to one vendor Your whole app depends on their uptime Paym

Structured output broke on us three times. The third time taught us what "operator-ready" means. Last quarter we shipped a contract-extraction agent to an enterprise legal team. Schema validation passing at 97%. Human reviewers satisfied with the output quality in testing. Rollout went smoothly. Then it broke. Three times. In three completely different ways. The first two failures we fixed with better prompts and stricter schemas. The third one taught us something the first two hadn't: that "operator-ready" is not a technical checklist. It's a claim about your agent's behavior under conditions you didn't design it for. Failure one: the validation paradox Week two. A lease agreement came through with a renewal clause formatted as a table instead of prose. Our extractor looked for renewal terms in a specific JSON path. The table format populated the schema differently. Validation passed. The extracted renewal date was off by two years. The fix was obvious in retrospect: add a canonical-format normalization step before extraction. But the lesson was sharper than that. Schema validation tells you the shape of the output, not whether the content is correct. A JSON object with the right keys and the right types can still contain wrong values. Our 97% validation success rate was measuring the wrong thing. It was measuring structure conformance, not content accuracy. After this failure, we separated validation into two signals: schema validity (does the object have the required fields) and field confidence (do we have evidence the content is correct). We started logging both. An output is trusted only when both signals are above threshold. Failure two: the retry loop that lies Month one. A particular clause type appeared in a contract format we hadn't trained our test set on. The extractor failed schema validation on the first attempt. Our retry logic kicked in, filled missing fields with model-inferred defaults, and passed validation on the third try. The output looked rig

An investigation agent flagged "the license API PHP returns Japanese-hardcoded messages" and we sat down to fix it. But something felt off the moment we opened the file — the version running on the production server didn't match the latest commit in the local repo . Stranger still, production had more recent features than our local checkout . A bit of digging turned up the truth: months earlier, someone had hot-patched the production file in response to a different user issue, and that change had never been committed back to git . This post walks through how we detected that drift, and the two-stage strategy we used to merge production back into the local repo safely. How this regression silently slips in If we'd written the fix on top of our local repo and uploaded it to production, here's what would have happened: all the production-only improvements get overwritten and quietly disappear . In our case, the production file had a half-year-old language-handling addition for the "Early Bird Bonus" feature — when a USD customer buys, client_name is set to 'Early Bird Bonus' ; for JPY customers it's '早期利用特典' . None of that existed in our local git. A normal PR-merge-and-deploy cycle would have silently rolled back the Early Bird i18n logic , regressing English users' display back to Japanese. Catching this was half luck. Opening the file to start the fix, I noticed code I didn't recognize, ran git blame , and the lines were nowhere in git history . That's when alarm bells went off. Two-stage rollforward — make production the source of truth first The strategy we landed on was a two-stage merge. Stage 1 (rollforward sync) : Pull the production file straight into the local repo. Apply the diff in the "production → local" direction, not the other way . After this, the local repo's HEAD matches what's actually running on production. # Pull the production file into the local repo scp -i ~/.ssh/key layer2024@host:wpmm.jp/public_html/license/api/register_free.php \ /tmp/regis

The satirical site is fighting to officially take over Infowars. In the meantime, CEO Ben Collins says the new show will mock “how fucking stupid” conspiratorial brain rot has become.

At an internal meeting, the Meta CEO reportedly said that AI development efforts were not moving as quickly as anticipated.

True Anomaly and Rocket Lab are performing Top Gun-style satellite fly-bys for the U.S. military.

Pocket is listed in app stores but seemingly unavailable in the US.

OpenNG Foundation and spartan/ui 1.0 are the headline topics this week: a new home for libraries like Spectator and Elf, and spartan/ui, a stable shadcn-inspired component library for Angular. Also in brief: Storybook's Angular modernization through AnalogJS, the end of ng-conf, and AI Dev Craft in Las Vegas. OpenNG Foundation Maintaining open-source libraries is hard work. Developers often do it in their spare time, committing to years of maintenance, adding new features, and responding to user requests. Last episode, we reported that the ngneat organization was taken down for unknown reasons. While we still don't know why it happened, a new home has emerged for its popular libraries like Spectator and Elf: the OpenNG Foundation. Gerome Grignon, known for CanIUseAngular and as the organizer of Ng-Baguette, announced the foundation, which is already hosting these libraries. Alongside Gerome, the current OpenNG team also includes Dominic Bachmann, organizer of Angular Lucerne and author of the angular-typed-router library. OpenNG Foundation · GitHub OpenNG Foundation has 8 repositories available. Follow their code on GitHub. github.com spartan/ui 1.0 spartan/ui has officially released its 1.0 version. It provides an "accessible, production-ready library of more than 55 components" with fully customizable styling. After debuting in August 2023 with 30 primitives, it now reaches stable in 2026 with a modern architecture built around signals, standalone components, zoneless change detection, and SSR. Originally initiated by Robin Götz, a full team quickly formed around the project. spartan/ui can be seen as the Angular equivalent to shadcn/ui, famous for its customizability. While similar open-source alternatives exist, spartan/ui was the pioneer and has a proven track record of active maintenance over the years. Announcing spartan/ui 1.0 Robin Goetz Robin Goetz Robin Goetz Follow for Playful Programming Angular Jun 24 Announcing spartan/ui 1.0 # angular # webdev 8 reac

Applied AI: Copilot's Kimi K2.7, AI Agent Workflow Barriers, Open-Source Life Planner Today's Highlights This week's top AI news covers a significant upgrade to GitHub Copilot with the Kimi K2.7 Code model, enhancing developer productivity through advanced code generation. We also explore the practical challenges faced by AI agents in fully automating workflows due to "last mile" integration issues, alongside a hands-on look at a new open-source AI life planner that demonstrates real-world application of AI tools. Kimi K2.7 Code is generally available in GitHub Copilot (Hacker News) Source: https://github.blog/changelog/2026-07-01-kimi-k2-7-is-now-available-in-github-copilot/ GitHub Copilot has integrated the Kimi K2.7 Code model, making this advanced code generation capability generally available to its users. This update signifies a continuous improvement in the underlying AI models that power development tools, specifically in the domain of code generation and assistance. Kimi K2.7, presumably an internal or specialized model from GitHub's AI research, focuses on enhancing the quality, relevance, and efficiency of generated code suggestions, auto-completions, and code explanations within the Copilot environment. For developers, this means a more accurate and helpful programming assistant that can better understand context and intent. The deployment of Kimi K2.7 into a widely used production tool like GitHub Copilot demonstrates a key pattern in applied AI: iterating on foundation models and integrating improved versions directly into developer workflows. This enhancement aims to boost developer productivity by reducing the time spent on boilerplate code, debugging, and searching for solutions, allowing engineers to focus on higher-level architectural and design challenges. This release confirms the ongoing progress in AI's capability to augment the software development lifecycle. Comment: New model, better code generation – straightforward for Copilot users. This

Maintaining a robust testing pipeline or managing automated node infrastructure often requires orchestrating dozens of isolated EVM wallets. Over time, these automated Python or JavaScript configurations inevitably hit a common wall: the accumulation of fragmented token dust across multiple layers (Ethereum, Arbitrum, Base, BSC, etc.). Trying to clear these micro-balances manually or writing one-off scripts to sweep individual assets scale operational costs rapidly. Each network requires separate RPC updates, custom middleware logic, and redundant gas overhead, turning standard infrastructure hygiene into an engineering bottleneck. The Problem with Traditional Asset Sweeping When handling larger developer setups or wallet clusters, custom scripts face three major friction points: Redundant Network Fees: Batching transfers without native contract-level optimization burns excessive gas when scaling to 50+ addresses. RPC Disruption: Constantly querying and broadcasting batch transfers via public or even shared private endpoints can trigger rate limits. Data Contamination: Manually routing funds from dense testing nodes increases the risk of cluster cross-contamination. To resolve this friction within our decentralized dev pipelines, we deployed a streamlined utility layer: CryptonEquity Terminal ( https://cryptonequity.com ). Building a Unified Utility Layer for Multi-Chain Workflows The terminal introduces a non-custodial Cross-Chain Dust Sweeper designed to eliminate fragmented operational friction. Instead of manually deploying individual sweeping scripts per account, the infrastructure automates multi-chain scanning and groups asset consolidation into a single transaction link. Simultaneous Layer Aggregation: Automatically detects micro-balances across dominant EVM networks at once. Gas Mitigation: Designed to structure transfer paths to limit redundant network fee overhead. Zero Onboarding Friction: Operating strictly on a non-custodial architecture, it requires n

The original safety gate on the Dolt-over-MCP plugin tried to keep a Claude Code agent harmless by excluding "history-affecting tools" from its MCP grant. It was the wrong granularity, and it did nothing. MCP exposes the entire database through one tool — query / exec — and that tool carries every SQL verb. SELECT rides it. So does CALL DOLT_PUSH , CALL DOLT_RESET('--hard') , DROP DATABASE , and CALL DOLT_BRANCH('-D', 'main') . Excluding "dangerous tools" from the grant accomplishes nothing, because the dangerous verbs live inside the one tool you already granted. The destructive operations were never separate tools to exclude. This is the reframe the whole Phase 0 hardening pass turned on: a tool-name allowlist is meaningless for any tool that carries a sub-language. SQL is a sub-language. So is the shell behind a Bash tool. So is anything behind an eval . If the tool can run arbitrary statements in some grammar, the only boundary that means anything is one that reads the statement. It is the move from tool-name allowlisting to capability-based security: the grant stops being "you may call the query tool" and becomes "you may run these statement classes inside it." Why not just allowlist the safe tools? Because there is exactly one tool, and it is not safe or unsafe — it is whatever statement you hand it. You cannot partition a single door into a safe door and a dangerous door by naming. The same logic kills the next-obvious fix: a denylist of dangerous verbs. Blacklist DOLT_PUSH , DOLT_RESET , DROP ... and miss DOLT_REBASE , or the proc Dolt ships next quarter, or a CALL whose name your regex didn't anticipate. A denylist is only as good as your imagination on the day you wrote it. The fix inverts that. You add safety by enumerating what is safe, not by blacklisting what is dangerous. Anything you cannot positively classify as safe is treated as the most dangerous thing it could be. Default-deny the unknown. It's least privilege applied to a grammar: the agent get

Book: Decoupled PHP — Clean and Hexagonal Architecture for Applications That Outlive the Framework Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub You already run three tools that half-cover this job. Pulse gives you a live wall on a local route. Datadog runs an agent and prices on host and usage volume, so the bill scales with your infrastructure. Sentry catches the exceptions after they already hurt someone. And none of them can tell you the one thing you actually asked: the checkout request that took 900ms at 14:03 dispatched a job, that job ran a query, and the query is what timed out. Laravel Nightwatch reached general availability in 2025 as the framework's own APM, aimed straight at that gap. It is worth knowing exactly what it captures, what it charges, and where its knowledge of your app stops and yours begins. What Nightwatch actually is Two moving parts. A Composer package inside your app, and a separate agent process that ships the data. composer require laravel/nightwatch The package writes events to a local socket. The agent listens on 127.0.0.1:2407 , batches what it receives, and sends it to Nightwatch's cloud. Because the agent runs outside your request cycle, the request thread is not blocked waiting on a network call to a telemetry backend. Laravel puts the added cost at under 3ms per request ; take that as a starting figure and measure your own before you trust it. # environment token per app + environment NIGHTWATCH_TOKEN = your-env-token # start the collector (keep it running under a # process monitor: Forge daemon, Vapor, supervisor) php artisan nightwatch:agent # confirm it is alive and receiving php artisan nightwatch:status One detail that bites people: the agent has to be running for anything to arrive. In local dev you start it by hand. In product

The Quest Begins (The "Why") I still remember the first time I faced a problem that asked for the sum of numbers in a sub‑array, over and over again, with updates sprinkled in between. It felt like I was stuck in a never‑ending loop of for i in range(l, r+1): total += arr[i] – O(n) per query, and with up to 10⁵ queries the solution timed out every single time. I was staring at the screen, thinking, “There has to be a smarter way to answer these range questions without scanning the whole array each time.” That moment was my dragon: a seemingly simple problem that kept biting me because I kept reaching for the brute‑force sword. I needed a data structure that could give me the answer in logarithmic time while still supporting point updates. Enter the segment tree – the tool that turned my O(n·q) nightmare into an O((n+q)·log n) victory. The Revelation (The Insight) So why does a segment tree work? Imagine you have an array and you want to know the sum of any interval [l, r] . If you could break that interval into a handful of pre‑computed chunks, you’d only need to add those chunk values together instead of touching every element. A segment tree is exactly that: a binary tree where each node stores the aggregate (sum, min, max, etc.) of a segment of the original array. The root covers the whole array [0, n‑1] . Its two children cover the left half and the right half, and this keeps splitting until the leaves represent single elements. The magic lies in two facts: Every node’s value is a function of its children. If you know the sum of the left child and the sum of the right child, the parent’s sum is just their addition. This means we can build the tree bottom‑up in O(n) time. Any interval can be represented as O(log n) disjoint nodes. When you walk down the tree to answer [l, r] , you either take a whole node (if its segment lies completely inside the query) or you recurse further. Because the tree’s height is log₂n, you’ll visit at most 2·log₂n nodes. Thus, building

Mozilla shut down the well-loved read-it-later Pocket app last year, and now Meta is launching an app called Pocket with an entirely different, AI-focused pitch: this new app lets you make and share little interactive "gizmos" built from an AI prompt, as reported by Business Insider. Meta CEO Mark Zuckerberg is all in on AI […]