标签：#AI

I got laid off in March 2026. The day HR handed me the 30-day notice, I had a small panic attack, then opened my laptop and started building things. Here's the deal: I had 30 days before severance ran out, and I wanted to see how much I could ship with AI tools before the money (and motivation) ran dry. I gave myself a single rule — every project gets a 7-day deadline, otherwise I kill it. I built 6 things. One has real users. One broke in production. Two I never opened again. This is what happened, in the order I built them. 1. AI Buddy (Chrome sidebar) — shipped, 15 users A Chrome extension that puts an AI assistant in a sidebar. Select text on any page, hit a keyboard shortcut, it goes to the AI, reply shows up without you leaving the page. Works with GPT-4, Claude, Gemini, DeepSeek. No login, no credit card. Time: 11 days (April 1–11). Status: Live on Chrome Web Store. 15 real users as of June 28, 2026. Rating 4.2. What I used AI for: 90% of the code (500 lines of JavaScript, written in Cursor). The README, the Chrome Web Store description, the marketing tweets — all AI-drafted, then I rewrote the parts that sounded like AI. What went wrong: The first version had a Stripe integration. AI wrote 90% of the webhook signature verification. I had to rewrite it from scratch. Also the model-picker UI went through 5 revisions because AI kept proposing what looked right but didn't work. → Chrome Web Store 2. Weekly report generator — personal use only Every Friday at 4pm, a script grabs my git commits, Slack messages, and Linear ticket changes, throws them at GPT-4, and asks for a "manager-readable" weekly report. I review, tweak, send. Time: 2 days. ~200 lines of Python. Status: Running for 11 weeks. Has 1 user. Me. Cost is $0.12/week. What I used AI for: The prompt. It's surprisingly tricky to get GPT-4 to write a weekly report that doesn't sound like a robot. The single most useful line: "if you don't have data, write 'no progress this week' — don't make things up." T

you've felt it. you type a prompt, hit send, and the response starts streaming in under a second....

The latest update to hermes-memory-installer introduces a focused set of features that directly address production-level concerns: observability, storage management, security, fault tolerance, and performance introspection. If you maintain a message-processing pipeline or job queue, these are the components that often decide whether your system survives peak loads or security audits without manual heroics. Let's break down each addition and how you can integrate them into your workflow. System Metrics Exposing runtime health is no longer an afterthought. The new metrics module taps into the core processing loop and emits standard Prometheus-formatted data: message throughput (count and rate), latency percentiles, queue depths, and goroutine or thread pool utilization. This isn't a simple "up/down" gauge—you get histograms for processing duration and derived metrics like consumer lag. For example, if you run multiple worker instances, you can now directly compare their processing speeds via a Grafana dashboard. The endpoint is configurable, so you can keep it behind a reverse proxy or internal load balancer. Memory pressure triggers a separate gauge for heap usage per queue, which helps with capacity planning before it becomes a midnight incident. Auto-Archive Without auto-archive, old messages accumulate in memory or primary storage, driving up costs and slowing down scans. This feature moves processed or expired messages to a cheaper tier (S3, GCS, or local file system) based on age or queue size. The archive process is a background task that runs on a cron-like schedule; you can define how many messages to retain per queue before archiving kicks in. The compression is transparent—gzip by default, but you can switch to snappy or zstd. A key detail: archived messages retain their metadata and can be restored if needed, though the replay path skips them automatically unless explicitly requested. This is useful for audit trails or multi-region cold replicas. Token Rot

Like most developers, I have a set of tools I use every day. Most of them work great, and I don't...

Abstract Executing autonomous AI agent payloads in Google Workspace via the Apps Script...

China's Zhipu AI (Z.ai) released its open-weight GLM-5.2, and some researchers have claimed that it matches Mythos in certain bug-finding and cybersecurity scenarios. While GLM lags behind models from Anthropic and OpenAI in other, more general tasks, it seems that China has dramatically reduced the gap in the capabilities between its models and those of […]

Streaming ads might be getting a lot quieter.

Would you trust a sci-fi author to program critical AI systems for humanity? No? Yet, that's what we've been doing. Years ago, I remember hearing the argument: "Why don't we just prompt LLMs with Asimov's three laws of robotics ?" It sounds elegant. The laws were designed to constrain artificial minds. Why not use them? Because the model has already read every story where they fail. LLMs are statistical engines designed to autocomplete text. Imagine a story that starts like this: Once upon a time, there was a good little robot who followed the 3 laws of robotics to the letter. Now take human literature and complete the story. Does it end well? ‹ › (function() { var container = document.currentScript.closest('.ltag-slides--carousel'); var track = container.querySelector('.ltag-slides__track'); var slides = track.querySelectorAll('.ltag-slide'); var prevBtn = container.querySelector('.ltag-slides__nav--prev'); var nextBtn = container.querySelector('.ltag-slides__nav--next'); var dotsContainer = container.querySelector('.ltag-slides__dots'); var current = 0; var total = slides.length; for (var i = 0; i < total; i++) { var dot = document.createElement('button'); dot.className = 'ltag-slides__dot' + (i === 0 ? ' ltag-slides__dot--active' : ''); dot.setAttribute('aria-label', 'Go to slide ' + (i + 1)); dot.dataset.index = i; dot.addEventListener('click', function() { goTo(parseInt(this.dataset.index)); }); dotsContainer.appendChild(dot); } function goTo(index) { current = ((index % total) + total) % total; track.style.transform = 'translateX(-' + (current * 100) + '%)'; var dots = dotsContainer.querySelectorAll('.ltag-slides__dot'); for (var i = 0; i < dots.length; i++) { dots[i].classList.toggle('ltag-slides__dot--active', i === current); } } prevBtn.addEventListener('click', function() { goTo(current - 1); }); nextBtn.addEventListener('click', function() { goTo(current + 1); }); })(); It doesn't. Because the entire body of fiction built around those laws exists to explo

Your AI coding agent writes something that looks right. It compiles in your head. Then you notice it called user.getProfileById() — a method that doesn't exist anywhere in your codebase. You didn't ask it to make that up. It invented it confidently, in the middle of otherwise-fine code. And that's the worst kind of wrong: not obviously broken, just quietly incorrect in a way you have to catch. If you've run Claude Code, Cursor, or any agent on a real repo, you know this one. Here's why it happens — and why the obvious fix doesn't work. The fix everyone tries first (and why it fails) You reword the prompt. You add "Don't make up functions." It behaves… for one file. Then it does it again. So you add "Only use methods that exist in the provided code." Better for a bit. Then two more sentences — and now your prompt is fifteen rules long and it still invents a method the moment the task gets complex. Here's the part nobody tells you: rewording treats a structural problem as a vocabulary problem. A prompt isn't a contract the model reads once and obeys. It's something the model has to hold in working memory while it reasons about your actual task. A flat list of fifteen rules is unholdable. As the work gets harder, the model spends its attention on the code and quietly drops whichever rule wasn't front-of-mind. "Don't invent methods" is usually rule #11. Under load, it falls out. You can't out-word that. A sixteenth rule just gives it one more thing to drop. The actual cause: shape, not wording The agent invents a method because nothing in the prompt's structure requires it to check. You told it what not to do. You never changed what it actually does, step by step. So stop forbidding the bad thing. Remove the opportunity for it. Instead of a rule it has to remember, make grounding a required step it has to perform. Before — a pile of rules:You are an expert engineer. Write clean code. Follow our conventions. Don't make up functions. Only use methods that exist. Handle er

Last night I was deep in a build session with an AI assistant. We picked it back up tonight. At some point I mentioned it had been a day and a half since we last spoke — and the model had no idea. None. As far as it knew, it was still the previous session. The gap was invisible to it. That tiny moment is one of the most underrated problems in AI systems right now. So let's talk about it. The model doesn't know what time it is An LLM gets a rough sense of "now" at the start of a conversation — a single timestamp, handed to it once. That's why it can greet you with "good morning." But that stamp is frozen. It doesn't update as the conversation runs, and it definitely doesn't travel into the next conversation. Each session starts cold. On its own, that's a curiosity. It becomes a real problem the moment the model reasons over retrieved context — search results, documents, database rows, another agent's output. Staleness is invisible Here's the dangerous part. When a model reads a retrieved document, that document usually carries no trustworthy signal about when it was true . So the model treats it as present-tense. It produces a confident answer from six-month-old data with nothing flagging that the data is old. A few places this bites: Pricing — quoting a number that changed last quarter. Availability — "in stock" from a cached page. Compliance — citing a policy that was superseded. People — stating someone's job title from two years ago. For a human reader, a slightly stale search result is fine — you see the date and judge for yourself. For an LLM, the staleness is silent. The wrong answer looks exactly like a right one. Why "just add a clock" doesn't fix it The instinct is: give the model the current time. But knowing it's 9 PM doesn't help if the document you're citing went stale in 2023 and nothing told you. The missing piece isn't the model's clock — it's the context's freshness . Two different things: What time is it now? — easy, a now() call solves it. How old

Performance optimization has always been one of the hardest parts of web development. You run...

Have you ever wondered how apps like university portals know which courses a student is enrolled in, or how they pull up an instructor's full schedule in seconds? The answer lies in database relationships - one of the most important concepts in backend development. In this article, we'll explore: What database relationships are and why they matter The three types of relationships: One-to-One, One-to-Many, and Many-to-Many How relationship schemas work (primary keys, foreign keys) How SQL Joins let you pull connected data from multiple tables To keep things grounded, we'll use one running example throughout: a University Management System . By the end, you won't just understand the theory, you'll see exactly how these concepts connect in a real-world scenario. What Are Database Relationships? A database relationship defines how data in one table connects to data in another. Instead of storing the same information repeatedly, relational databases organize data into separate tables and link them using keys . Think about our university system. We have a table for students and another for courses . A student can enroll in multiple courses, and each course can have many students. Rather than storing a student's full details on every course record, we store the student's info once and create a relationship between the two tables. This keeps data clean, reduces duplication, and makes updates easy. If a student's email changes? Update it in one place - done. Here's a simple visual of what that looks like: +------------------+ +------------------+ | Students | | Courses | +------------------+ +------------------+ | student_id (PK) | | course_id (PK) | | name | | title | | email | | credits | +------------------+ +------------------+ \ / \ / \ / Enrollments (links students ↔ courses) Now let's look at the three types of relationships you'll encounter. Types of Database Relationships 1. One-to-One (1:1) Each record in Table A matches exactly one record in Table B and vice versa

What happens when thousands of people decide they're hungry at the exact same time? The Quiet Before the Storm 10:00 PM. The numbers are gentle tonight. One hundred eighty-nine requests trickle in. Someone in Lagos is ordering late-night suya. A rider in Ibadan is wrapping up his last delivery. In Bangladesh, someone is just discovering us for the first time. By 11:00 PM , things get quiet. Just 8 requests. The platform takes a breath. 2:00 AM. A mystery. 151 requests spike out of nowhere. We check the logs. Nothing unusual. Just a group of night owls ordering food, maybe shift workers, maybe students pulling an all-nighter. The beauty of a platform is we're always on, always ready. 7:00 AM. Good morning, Nigeria. Fifty-five requests. People waking up, checking their wallets, planning their day. The coffee hasn't even brewed yet, but the platform is already humming. The Morning Rush 9:00 AM. 315 requests. The workday begins. Offices buzz with conversations about lunch plans. If someone searches "foodmat site" for the third time this week, they're getting closer to finding us. A corporate client logs in to set up their employee meal program for the first time. By 10:00 AM , the traffic settles to 50 requests. A calm before the real storm. 11:00 AM. 173 requests. The hunger is building. People are making decisions about what to eat, where to order, and which vendor to choose. Our World Cup campaign notifications ping. Someone shares their referral code. The viral loop begins. The Lunch Explosion 12:00 PM. 321 requests. It's happening. The platform comes alive. 1:00 PM. 339 requests. The peak is building. Our servers are handling it smoothly. This is where the magic happens when thousands of people decide they're hungry at the exact same time. 2:00 PM. 289 requests. Still going strong. Vendor dashboards refresh. Riders accept orders. Laundry bookings come in alongside food deliveries. If someone cancels an order with a reason, we take note. Every interaction teaches us

I created Agentis Lux for the purposes of entering H0 Hackathon (Vercel + AWS Databases). #H0Hackathon See Agentis Lux's Devpost.com entry . It started with a comment at a hackathon. A you.com employee said the thing out loud: the web has a second audience now. When you ask ChatGPT or Perplexity a question, a retrieval agent fetches a page and reads its HTML to answer you. Not the laid-out site with the buttons and the hero image. The markup underneath. These agents arrive by the million, and many of them rely on the raw or minimally rendered HTML rather than running your JavaScript, so they often see far less of your page than a person does. That comment sent me to build. My first answer to it was Hermes Clew , for the GitLab Duo Agent Platform Challenge. Hermes lived inside GitLab Duo Chat, no frontend, no database: a Python engine that scanned the HTML, JSX, and TSX files in a repo, scored them across six categories, and let an LLM reason over the findings. It proved the core idea. It also told developers how to fix things, lived inside one vendor's chat, and only worked on files in a repo. Agentis Lux is what happened when I took that idea to the open web and rebuilt it with a different stance. Any live URL, not just repo files. Its own product on a real cloud architecture, not a chat window. And no fix suggestions, on purpose, where Hermes used to hand them out. Same six-category bones, a new body, a sharper philosophy. It scans your site and shows you what that second audience experiences when it tries to read it. What it does You paste a URL to Agentis Lux . You get a report. The report is written from the agent's point of view. Not "this is broken." More like: "an agent landing on this page can't tell which element starts checkout, because it's a styled div and not a button." It reports findings. It does not suggest fixes, and that is on purpose. I know what the agent sees, not what you should change. That is the whole value: visibility, and you decide what

I've been building with AI for a while now. I can get these tools to do what I want, but I want to go a level deeper, past "it works" into actually understanding why. So I'm sharpening the fundamentals and the applied side, and writing it down here as I go. Expect short, honest posts on what I'm learning and building.

Suno has ambitions to be more than just a toy to churn out AI slop, it also wants to be a streaming destination and to break new artists. Spark is their new incubator program for independent artists that provides grants, mentorship, and marketing support. To apply, artists need to be an unsigned singer, songwriter, or […]

"Mistakenly we thought that by just introducing artificial intelligence ... that would produce a high-quality product.”

TL;DR — Claude Code sends its requests wherever one environment variable points. Aim that at a small local translator and it runs on the Kiro plan you already pay for. Full setup below, plus the two snags worth knowing about. Claude Code and Kiro have something funny in common: underneath, they're powered by the same Claude models. Same brain. They just grew up speaking different dialects, so out of the box they can't hold a conversation. I noticed this right as I was about to start a second subscription for Claude Code. My Kiro plan was already renewing every month, already serving the exact models Claude Code wanted to charge me for again. Paying twice to talk to the same thing felt absurd. So instead of buying a second seat, I hired an interpreter. One small program that sits between them, listens to Claude Code, and relays everything to Kiro in a dialect it understands. Here's how to set it up, and what I learned doing it. Why they can't just talk Claude Code is more open-minded than people assume. It doesn't hard-code where it sends requests. It reads one environment variable, ANTHROPIC_BASE_URL , and ships everything to that address. Normally that's the official endpoint, but it'll happily send its requests anywhere you tell it to. That's the opening. Point it somewhere local and the whole thing becomes possible. Meet the interpreter The catch is that Claude Code and Kiro phrase things differently. You can't just redirect one at the other and expect them to understand each other. You need a translator fluent in both. That's kiro-gateway-next : a tiny proxy that runs on your own machine. A request arrives phrased one way and leaves phrased another: Claude Code (phrases it for Anthropic) ──▶ kiro-gateway (rephrases it for Kiro) ──▶ your Kiro account Claude Code gets a reply in the format it expects. Kiro receives a request it recognizes. The interpreter does the rephrasing in the middle, and the conversation just flows. Setting it up, step by step Six steps. Abo

The biggest challenge wasn't choosing a language model or designing prompts—it was managing context over time. Once an application grows beyond isolated conversations, memory becomes just as important as reasoning. An assistant that remembers previous architectural decisions, coding preferences, and project history can contribute much more effectively than one that starts from scratch every session. Runtime intelligence proved to be equally important. Not every request deserves the same computational resources. Routing tasks based on complexity, enforcing execution budgets, and maintaining an audit trail make AI systems more predictable and practical for real-world development. DevPilot AI brings these ideas together by combining Google Gemini for reasoning, Hindsight for persistent memory, and cascadeflow for runtime intelligence. While the project will continue to evolve, building it reinforced one idea above all else: the future of AI applications isn't just about generating better responses. It's about building systems that can remember, adapt, and make better decisions over time. If you're interested in the architecture or would like to explore the project further, you can find the source code here: GitHub: https://github.com/siddharthg-7/DevPilot-Ai- I'm always interested in feedback and discussions around persistent memory, runtime intelligence, and AI engineering. If you've explored similar ideas or approached these challenges differently, I'd love to hear your perspective.

For the last 3 months I recorded every session I had with Claude Code. Not screenshots, not memory. Every prompt I typed and everything it did, saved to a small database I own. I did it because I kept losing my own work. I would finish a week, someone would ask what I shipped, and I genuinely could not remember. The work was real. It just lived in terminal scrollback I would never scroll through again. So I set up a chain of small agents to remember it for me. Every night, while I sleep, one agent reads that day's raw sessions and writes a single clear note: what I built, the decisions I made, what is still open. Plain language, the way I would write it in a journal, not a wall of logs. Once a week, a second agent reads all seven daily notes and updates a profile of me: the projects I am moving, the skills I have actually used, the things I learned. After a few months this turned into a more honest picture of my work than my resume. Then a third agent reads all of that and drafts posts for LinkedIn and X about what I actually worked on that week. Building in public, without me having to remember or sit down and write. The part I like most: none of it runs on my machine. It is all scheduled cloud routines. My laptop can be off. I wake up and the notes, the profile, and the draft posts are already waiting. I have started open-sourcing this as Pulse. The capture and the nightly daily-note agent are out now. You point it at your own database and your own notes repo, and it writes your day for you, in plain English, in files you own. The weekly profile agent and the post-writer are the pieces I am extracting next. It is early and rough in places. The honest caveat: the writing is only as good as the model behind it, and a quiet day still makes a quiet note. But after 3 months, I no longer guess what I did. I just open the vault. The graph at the top is 3 months of my own notes, each day linked to the projects it touched. Repo: https://github.com/muhammademanaftab/pulse