标签：#t

Most "AI agent" libraries fall into one of two buckets. Either they're a big framework you spend an afternoon configuring, or they're a tiny toy that drops the one feature you actually need in production: the ability to stop and ask a human before the agent does something you can't undo. I wanted the middle. So I wrote yieldagent : a small agent loop you can read end to end, with human-in-the-loop pause/resume built in, and no runtime dependencies. This post walks through how it works and why it's built the way it is. What an agent loop actually is Strip away the branding and an "agent" is a loop: Send the conversation to the model, along with the tools it's allowed to call. If the model asks to call a tool, run it and append the result. Repeat until the model answers without asking for a tool. That's it. The model decides the control flow at runtime; your job is to run the tools and feed the results back. Here's the core, lightly trimmed: for ( let step = 0 ; step < maxSteps ; step ++ ) { const reply = await call ( messages , toolSpecs ); messages . push ( reply ); if ( ! reply . tool_calls ?. length ) { yield { type : " final " , text : reply . content , messages }; return ; } for ( const tc of reply . tool_calls ) { const args = JSON . parse ( tc . function . arguments ); const result = await tools [ tc . function . name ]. run ( args ); messages . push ({ role : " tool " , tool_call_id : tc . id , content : JSON . stringify ( result ) }); } } Everything else in the library is in service of making this loop observable, testable, and safe to run against the real world. Why an async generator Notice the yield . The loop is an async generator, so the caller drives it: for await ( const step of agent ({ call , tools , messages })) { if ( step . type === " tool-start " ) console . log ( " -> " , step . tool , step . args ); if ( step . type === " final " ) console . log ( step . text ); } Every step (each tool call, each result, and the final answer) is handed back to

For a long time, I believed coding was only for people who studied computer science or worked as professional developers. Whenever I saw a screen filled with code, it looked like a completely different language. There were brackets, symbols, functions, and terms I did not understand. I assumed learning it would require years of study before I could create anything useful. That changed when I encountered a repetitive task at work. I was regularly copying information from a spreadsheet, checking each row, preparing an email, sending it, and updating the status manually. The work was manageable, but completing the same process repeatedly took time and left room for mistakes. I started wondering if the spreadsheet could do some of the work for me. That question led me to Google Apps Script. At first, I did not even know where to begin. I understood the result I wanted, but I did not know how to translate it into code. I could explain the process clearly to another person, but explaining it to a computer felt different. AI became my starting point. I described the task and asked it to create a script. Within seconds, it gave me several lines of code. I copied them, ran the script, and immediately received an error. My first reaction was frustration. I had expected the code to work because it looked complete. But I soon realized that generated code was not automatically working code. I went back and explained the error. AI suggested a change, so I tested it again. Another issue appeared. I repeated the process until the automation finally worked. The moment it worked, something changed in the way I viewed coding. I did not suddenly become a programmer, but I had created something useful. A task that previously required several manual steps could now happen automatically. I became curious about what else I could build. I started experimenting with confirmation emails, timestamps, form submissions, missing-data checks, and automatic reports. Each project introduced me to a

It started with one simple question: Why am I still doing this manually? I was working on a spreadsheet, checking information row by row, sending emails, and updating statuses. The process was not difficult, but it was repetitive. One small mistake could mean sending incorrect information, overlooking a request, or forgetting to update a row. I knew there had to be an easier way. I wanted the spreadsheet to detect when a status changed to Sent , find the email address in the same row, send the correct message, and add a timestamp after the email was sent. The idea sounded simple in my head. The problem was that I did not know how to build it. I was still learning how to code, so I asked AI for help. My first prompt was something like: Create a script that sends an email from Google Sheets. AI immediately generated a script. It looked impressive, but it did not work the way I expected. The script checked the wrong column, used information from the wrong cells, and failed when some required details were missing. That was when I realized the problem was not only the code. My instructions were too vague. I tried again, but this time I described the entire process: When the status in Column G changes to "Sent," get the email address from Column E and send a confirmation email. After the email is sent successfully, add a timestamp to Column H. Do not send the email if any required information is missing. The result was much closer to what I needed. When I changed the status to Sent and received the email automatically, I felt genuinely excited. It was only a small automation, but it removed several manual steps from the process. After building that first workflow, I started noticing repetitive tasks everywhere. A form submission could automatically send a confirmation email. A spreadsheet could detect missing information before processing a request. A completed action could record the date and time. Reports could be organized without manually copying every row. Tasks that

Dead Island 2, Harold Halibut and seven others will be gone soon.

Are you tired of wrestling with raw cURL requests, parsing Server-Sent Events (SSE) by hand, and building complex polling loops just to interact with trading APIs? If you are a PHP developer or a Laravel enthusiast looking to dive into algorithmic trading, your life is about to get a whole lot easier. Meet coinquant-php , the official PHP and Laravel SDK for the CoinQuant Public API. CoinQuant is revolutionizing the way we approach algorithmic trading. It takes a trading idea described in plain English and turns it into a backtestable strategy using advanced AI. However, integrating such powerful tools into your own applications can often be a daunting task. That is where coinquant-php steps in. This robust SDK wraps the public API, providing a seamless, developer-friendly experience that lets you focus on what really matters: building profitable trading strategies. In this comprehensive guide, we will explore why coinquant-php is a game-changer for PHP developers, delve into its standout features, and show you how to get started in minutes. Why Choose CoinQuant PHP? The landscape of algorithmic trading is often dominated by Python, but PHP remains a powerhouse for web development, especially with frameworks like Laravel. coinquant-php bridges the gap, allowing PHP developers to leverage the cutting-edge AI capabilities of CoinQuant without leaving their preferred ecosystem. 1. Built for Modern PHP The library is designed for the modern era of PHP. It requires PHP 8.1+ and embraces strict typing, ensuring your code is robust and free from legacy baggage. Whether you are building a standalone script or a complex enterprise application, the SDK provides a solid foundation. 2. First-Class Laravel Integration If you are using Laravel 10, 11, 12, or 13, you are in for a treat. The package auto-registers its ServiceProvider and Facade , meaning there is absolutely zero manual wiring required. You can simply install the package and start using the CoinQuant facade anywhere

The bug reports all sounded the same. "It disconnected again." No error, no warning, nothing on screen to explain it. Someone would open a GitHub issue, start a planning-poker vote, then stop to actually read the thing they were estimating. Thirty seconds later they'd look back and the room had quietly gone still. Other people's votes weren't showing up, and their own weren't reaching the room. It had simply stopped, without a word. If you've ever built anything real on Chrome's Manifest V3, you can probably guess where this is going. The socket didn't drop because the network hiccupped. It dropped because Chrome reached over and killed the process it was living in. This is the story of that bug, and what it actually takes to keep a WebSocket alive inside a Manifest V3 extension. TL;DR: Manifest V3 runs your background code in a service worker that Chrome terminates after ~30s idle. If your WebSocket lives there, it dies with it, silently. The fix is three parts: a heartbeat so extension activity keeps the worker awake, auto-reconnect that pulls a fresh snapshot so drops are invisible, and a try/catch around every port message because the worker can die between your null-check and the call. Why the socket doesn't live where you'd expect First, some context on how the extension is wired, because it explains why this bug was even possible. It puts a button on GitHub issues and boards. Click it, and a live planning-poker room opens right there in the page. Votes flow over a WebSocket to a Cloudflare Durable Object that owns the room's state. Standard real-time stuff. The obvious place to open that socket is the content script, the code injected into the GitHub page. That's where the UI lives, so why not open the socket right next to it? Firefox is why not. A content script runs in the page's world, which means it inherits the page's Content Security Policy. GitHub ships a strict connect-src , and Firefox enforces it against content scripts. Try to open wss://… from the

When a learner finishes a course they want a certificate that behaves like a document: something they can print at full quality, attach to a job application and that an employer can check is genuine. In this tutorial you'll build exactly that in Laravel: a Blade-designed certificate rendered as a vector PDF, with a QR code that resolves to a verification page and an email that delivers it automatically. This post originally appeared on Accreditly as How to generate verifiable PDF certificates in Laravel . Keep the design in Blade The certificate is an ordinary Blade view. Everything lives in one file, styles inline, so the markup you preview in the browser is exactly what gets rendered. If you want a designed starting point rather than a blank page, the certificate of completion template is a good base to adapt. {{-- resources/views/certificates/template.blade.php --}} <!doctype html> <html> <head> <meta charset="utf-8"> <style> body { font-family: Georgia, serif; color: #1a2233; margin: 0; } .certificate { padding: 60px; border: 6px double #b28a2f; margin: 24px; text-align: center; } .heading { font-size: 15px; letter-spacing: 4px; text-transform: uppercase; color: #b28a2f; } h1 { font-size: 44px; margin: 24px 0 8px; } .course { font-size: 22px; margin: 4px 0 28px; } .issued { font-size: 15px; color: #5a6478; } .qr { margin-top: 36px; } .verify-url { font-size: 12px; color: #5a6478; } </style> </head> <body> <div class="certificate"> <p class="heading">Certificate of Completion</p> <h1>{{ $certificate->user->name }}</h1> <p class="course">has completed {{ $certificate->course }}</p> <p class="issued">Issued {{ $certificate->issued_at->format('j F Y') }}</p> <div class="qr"> {!! QrCode::size(110)->generate(route('certificates.verify', $certificate)) !!} </div> <p class="verify-url">{{ route('certificates.verify', $certificate) }}</p> </div> </body> </html> Two things are doing quiet work here. The design flows like a document rather than being pinned to fixed pixel

NatGeo's Pompeii: Out of Time fuses historical fact and imagination to bring city's last 24 hours to life.

Parental Supervision is coming to Meta's Threads.

Everyone is arguing about AI ROI right now. Boards want a number. Consultants are selling frameworks. And the headlines look brutal: an MIT report claimed 95% of enterprise GenAI pilots showed no measurable return, and a Forbes piece this January says 56% of CEOs see zero ROI from AI. So AI is a bust, right? Here is the thing. Ask any of those same companies to turn off email for a week. Just try it. Nobody ever ran a six month ROI study on email. Nobody had to. It became the way work happens, and the return stopped being a line item because it was everywhere. I think AI is following the same path, and the data backs it up. The gap between the pilot and the person That same MIT report has a stat that got way less coverage than the 95% number: 90% of employees regularly use personal AI tools for work, while only 40% of companies have an official LLM subscription. Workers adopted it at more than twice the rate of their own employers. The report even found that 70% of workers prefer AI over a colleague for quick stuff like drafting emails and basic analysis. So the official pilot fails its KPI review while the people inside the building are quietly using AI multiple times a day. That is not a failed technology. That is a measurement problem. Worth noting: the 95% figure itself has been heavily criticized. It came from 52 interviews and a narrow definition of success. I would not build a strategy on that number in either direction. Why the ROI is invisible The value seems to be landing in the same place email's value landed: the unglamorous middle of the workday. Drafting the reply. Summarizing the thread. Turning messy notes into something you can send. None of that shows up as a new revenue line. It shows up as an hour you got back and immediately spent on something else. You cannot easily measure that, but you can feel it. Take the tools away from a developer who has been using them for a year and watch what happens. People cannot imagine working without it anymore.

I am a very clumsy man. So clumsy, that I have AirTags hanging off practically every camera I own. Have I left my camera in an Uber? Yes. Have I left it on an airplane? Also yes. For me, finder tags are essential for my cameras. The problem is, strapping a finder tag to a […]

Your resume tells people what you’ve done. Your GitHub shows what you’ve built. But your personal website tells people who you are. When I started learning web development, I believed that a good resume and a few GitHub repositories were enough. Like many students, I spent countless hours building projects, solving coding problems, and learning new technologies. Every new project felt like a milestone, yet all of them remained scattered across different platforms. A recruiter would have to open my resume, visit my GitHub, search for my LinkedIn profile, and perhaps never even discover the articles I had written or the experiments I had built. That made me realise something important. Developers need a place on the internet that they truly own. Not another profile. Not another social media account. A place that represents their identity, work, and journey. That’s what a personal website becomes. More Than Just a Portfolio Many people hear the words personal website and immediately think of a portfolio with a few screenshots and a contact form. A great developer website goes much further. It answers questions before anyone has to ask them. Who are you? What technologies do you enjoy working with? What problems have you solved? What kind of developer are you becoming? What have you learned recently? How can someone reach you? Instead of forcing visitors to jump across five different platforms, everything exists in one carefully designed experience. Your Name Deserves a Home Every developer works hard to build projects. Very few work equally hard to build their own identity. When someone searches your name, what should they find? Ideally, the very first result should be something you completely control. A website with your own domain isn’t just another webpage. It’s your digital home. Unlike social platforms, algorithms cannot redesign your identity overnight. You decide what visitors see first. You decide which projects matter. You decide how your story is told. Resume

Exam Guide: Developer - Associate Technologies And Concepts Cheat Sheet 📘 Cheat Sheet 1 | Services Compute Service What It Does Key Points Lambda Serverless Functions 15 min timeout, 10240 MB memory max, 1000 default concurrency EC2 Virtual Servers Instance profiles for IAM roles, user data for bootstrap ECS/Fargate Container Orchestration Task roles for IAM, Fargate = serverless containers Elastic Beanstalk PaaS Deployment .ebextensions for config, supports rolling/immutable/blue-green Storage & Databases Service What It Does Key Points DynamoDB NoSQL key-value Partition keys, GSI/LSI, query vs scan, DAX for caching S3 Object Storage SSE-S3/SSE-KMS/SSE-C, lifecycle policies, presigned URLs ElastiCache In-memory Cache Redis (complex types, persistence) vs Memcached (simple, multi-threaded) RDS Relational Database RDS Proxy for Lambda connection pooling, read replicas OpenSearch Search & Analytics Full-text search, log analytics API & Integration Service What It Does Key Points API Gateway REST/HTTP/WebSocket APIs Stages, authorizers, caching, request validation, throttling SQS Message Queue Standard (at-least-once) vs FIFO (exactly-once), visibility timeout, DLQ SNS Pub/sub messaging Fanout, filter policies, message attributes EventBridge Event Bus Pattern matching, content-based filtering, multiple targets Kinesis Real-time Streaming Shards, partition keys, parallelization factor Step Functions Workflow Orchestration Standard (long-running) vs Express (high-volume, short) Security Service What It Does Key Points IAM Access Management Policies, roles, least privilege, STS AssumeRole Cognito User Auth User Pools (tokens) vs Identity Pools (AWS credentials) KMS Key Management Envelope encryption, 4 KB limit, key rotation, cross-account Secrets Manager Secret Storage Auto-rotation, $0.40/secret/month SSM Parameter Store Config Storage Standard (free) vs Advanced , SecureString type ACM SSL/TLS Certificates Free public certs, auto-renewal, can't export CI/CD Service Wha

A practical framework for test planning, hardware scheduling, artifact traceability, failure classification, and evidence-based quality gates Disclaimer: The views expressed in this article are my own. The architecture, examples, terminology, and code snippets are generalized for educational purposes and do not describe or disclose any employer’s proprietary systems, confidential information, or internal implementation details. A software change can compile successfully, pass unit tests, and still introduce a serious GPU regression. The failure may appear only on one GPU generation. It may depend on a particular driver, firmware revision, operating system, graphics API, or workload. A change may preserve functional correctness while quietly reducing performance. It may also cause an intermittent failure that disappears when the test is rerun. This is why GPU validation cannot be treated as conventional CI/CD with a GPU runner attached to the end of the pipeline. A dependable GPU validation platform must coordinate: Software and firmware artifacts Hardware configurations Test coverage GPU resource scheduling Failure classification Performance baselines Engineering evidence It must do all of this while operating under an important constraint: compatible GPU capacity is limited and expensive. The objective is not simply to run more tests. It is to produce reliable evidence quickly enough to support engineering decisions. Why conventional CI/CD is not enough A conventional application pipeline often resembles: Commit ↓ Build ↓ Unit tests ↓ Integration tests ↓ Deployment A GPU validation pipeline is more multidimensional: Code or configuration change ↓ Build software and firmware artifacts ↓ Determine affected GPU configurations ↓ Reserve compatible hardware ↓ Prepare the driver and runtime environment ↓ Run functional, stability, and performance tests ↓ Collect logs, traces, metrics, and crash artifacts ↓ Classify failures and compare results with baselines ↓ Make a mer

New data centers built through 2033 could consume as much electricity as India uses today.

The company didn't say how many are in each city and has taken a far more cautious approach to scaling the network than CEO Elon Musk had promised.

A single chemical made by mole-rat queens enforces the social order.

A developer credential that proves what you built Discussion | Link

Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber Discussion | Link

Amazon greenlit a Robocop pilot. Now it has committed to a full TV show.