标签：#AR

How I Cut My Multimodal AI Costs by 97% — A Freelancer's Guide Last month I almost killed a side gig because of a single line item on an invoice. A client wanted me to build a document-processing tool that could read scanned PDFs, pull text out of photos, and answer questions about charts. Easy enough — except I'd quoted the job assuming I'd use GPT-4o for the vision work. When I actually ran the numbers, I realized the API bill would eat my entire margin. I'd be working for free. Maybe worse. So I did what every freelancer does when the big-name vendor gets too expensive: I went hunting. And I landed on Global API, which routes to a bunch of multimodal models I've honestly never heard clients talk about. After a few weeks of testing, I figured out which ones are worth my billable hours and which ones aren't. This is everything I learned, plus the exact code I'm shipping to clients. Why Multimodal Even Matters for Solo Devs Two years ago, "multimodal" was a buzzword you'd hear at conferences. In 2026 it's table stakes. I've personally used vision models to: OCR receipts for an expense-tracking app (boring but pays the rent) Convert screenshots of legacy code into editable source for a Y2K-era company migration Read bar charts from PDF reports for a finance client who hates spreadsheets Analyze medical imaging samples for a startup MVP (this one was scary) Every one of those jobs started as a quick conversation with a prospect and turned into real invoices because I could say yes. The bottleneck was never capability — it was always cost. When GPT-4o charges north of $10/M output tokens, a single 2,000-token response on a tricky chart costs me about two cents. Multiply by 10,000 images per month and you've got a $200 API line item before you've paid yourself. That's a problem when the whole job is worth $400. So I tested every multimodal model I could find on Global API. Here's the lineup I ended up evaluating. The Contenders Nine models, three providers, one freelanc

Even if peace holds up between the US and Iran, oil prices aren’t going back down to where they were any time soon.

Getting the future right is now big business. But at a festival in Berkeley, forecasters worry that sports markets could take the whole industry down.

A new report shows that government agencies failed to communicate and includes recommendations for stronger oversight in a bid to avert future disasters.

This week, I covered the story of Casey Harrell—a man with ALS who is “the first power user” of a brain implant, according to the researchers who worked with him. Harrell is paralyzed and unable to speak coherently without the device. He has now spent almost three years using a brain-computer interface (BCI) that enables…

Azure Functions shipped a serverless agents runtime in public preview at Build 2026. Agents are defined in .agent.md markdown files with YAML triggers, MCP server access, 1,400+ connectors, and sandboxed execution. The Functions team confirmed to InfoQ that the runtime adds no cold start overhead and no billing premium beyond standard Flex Consumption. By Steef-Jan Wiggers

A London clinic owner has claimed he is treating people with stage 4 cancer by sealing them into a plastic bag while they're naked from the waist down and gassing them with chlorine dioxide.

Why Taking Feedback Positively Can Change Your Career As developers, engineers, designers, and professionals, we all want to improve. We spend countless hours learning new technologies, building projects, and gaining experience. Yet many people overlook one of the most powerful tools for growth: feedback. Unfortunately, feedback often feels personal. When someone points out mistakes in our code, resume, communication, or project, our first reaction is sometimes defensive. We feel offended, frustrated, or misunderstood. I've experienced this myself. But over time, I learned that the ability to accept feedback positively is one of the most valuable skills anyone can develop. Feedback Is Not an Attack One of the biggest misconceptions is believing that criticism is an attack on our abilities. When a senior engineer reviews your code and suggests improvements, they are not saying you're a bad developer. When a recruiter rejects your resume, they are not saying you're incapable. When users report problems in your open-source project, they are not trying to discourage you. Most of the time, people are simply showing you where improvements can be made. The sooner we separate our ego from our work, the faster we grow. Every Rejection Contains Information Many professionals view rejection as failure. I view it differently now. A rejection is data. If ten companies reject the same resume, the market is telling you something. If users consistently struggle with a feature, they're revealing a usability problem. If interviewers repeatedly point out the same weakness, they're highlighting a skill gap. The goal isn't to feel bad about the feedback. The goal is to learn from the information hidden inside it. Growth Begins Where Comfort Ends Positive feedback feels good. Constructive feedback creates growth. Nobody enjoys hearing that their architecture can be improved, their communication needs work, or their project has flaws. But those uncomfortable conversations often lead to th

Last Tuesday at 3am, a multi-agent loop hit 12K KV writes/minute and froze. The loop was a one-line counter bug. That part was fixable. What I found while tracing it was worse. I had --dangerously-skip-permissions enabled on a Claude Code session that was running D1 migrations. I thought it was pointing at staging. It wasn't — I'd misconfigured my env file reference, loading .env.production instead of .dev.vars . Claude didn't ask. The flag told it not to. The migration was ADD COLUMN , not DROP COLUMN , so no data loss. Survivable. But only barely. The thing I got wrong: I treated --dangerously-skip-permissions as "skip the annoying confirmation popups." It's actually "remove the only moment a human sees what command is about to run." Those are very different things. Turning the flag back off helps, but it doesn't constrain what Claude attempts — it just adds a prompt you'll click through anyway at 3am. What actually worked was adding a deny rule in .claude/settings.json : { "permissions" : { "allow" : [ "Bash(wrangler d1 execute * --local*)" ], "deny" : [ "Bash(wrangler d1 execute *)" ] } } The allow rule is more specific than the deny, so --local calls go through and everything else is blocked before execution. Over 2 weeks post-fix, Claude attempted zero production DB commands. Three deny events were logged — all from ambiguous prompts I wrote during fast context-switches, not from Claude going rogue. I ended up running three layers: the settings.json allowlist, a separate git worktree for migration work that physically contains only staging credentials, and a CLAUDE.md that instructs Claude to ask before anything touching production. The CLAUDE.md approach has a real caveat though — in long sessions the instructions lose weight as context grows. Anything critical needs to be restated in the prompt itself. I wrote up the full breakdown — including the worktree setup, the exact CLAUDE.md wording, and why MCP tool permissions behave inconsistently with the deny ru

Use these verified Chirp coupon codes and shopping tips to score up to 67% off wheels, up to 50% off refurbished products, and more.

Students can get a Hulu plan for $1.99 per month. Get more details on this and other great deals below.

Find the best L.L.Bean promo codes and coupons for 10% off your first order, major sale discounts, free shipping on $75+, and extra savings for select groups.

Save on bulk groceries, household essentials, and electronics with a verified Sam's Club promo code or membership discount.

DeductiveAI, a startup that uses AI to catch and resolve bugs in software, was founded just three years ago.

Your repo is already your agents' context, whether you designed it on purpose or not That sentence took me a while to understand. In this post I'll save you the trip. It was October 2025, working in Skyward's monorepo with AI agents every day. And every day the same routine: I'd tell the agent in the prompt "don't use this", "don't do it this way", "reuse the component that already exists". I wrote it down. I repeated it. The agent did exactly what I told it not to do. It wasn't that it didn't listen to me. It was that it read the code and saw something else there. The agent believes the code, not your prompt An agent follows the patterns it sees in the repo, not the ones you tell it in the prompt. And subagents are worse, because they start without the conversation's context. The whole fight you put up earlier in the chat, for them it never happened. So this is what kept happening. It created a new component even though one already existed that solved exactly that problem. It didn't respect the design rules or use the design tokens. It followed stale docs because they were still there, alive, with nothing flagging them as outdated. My first instinct was everyone's instinct, cram more context into the prompt. More rules, more "please don't do this", more examples pasted in by hand. It half worked, and for the next task you had to add it all again. Until the next subagent showed up and started from scratch. At some point, tired of repeating myself, I understood the obvious thing. The agent wasn't disobeying me. It was reading the repo and listening to what the repo said about itself. If the good component lives alongside three old versions, it has no way to know which one is the official one. If the docs say one thing and the code does another, it'll believe whichever is closest at hand. It's doing exactly what I asked. The repo itself is the context agents use. If it's badly structured, the answers won't be good. Period. No prompt fixes a repo that contradicts itsel

Tu repo ya es el contexto de tus agentes, lo hayas diseñado a propósito o no Esa frase me costó entenderla. En este post te ahorro el camino. Era Octubre del 2025, trabajando en el monorepo de Skyward con agentes de IA todos los días. Y todos los días la misma rutina: le decía en el prompt al agente "no uses esto", "no hagas esto así", "reutiliza el componente que ya existe". Lo escribía. Lo repetía. El agente hacía exactamente lo que le dije que no hiciera. No era que no me escuchara. Era que leía el código y ahí veía otra cosa. El agente le cree al código, no a tu prompt Un agente sigue los patrones que ve en el repo, no los que tú le dices en el prompt. Y los subagentes son peores, porque arrancan sin el contexto de la conversación. Toda la pelea que tú diste arriba en el chat, para ellos no existió nunca. Entonces pasaba esto. Creaba un componente nuevo aunque ya había uno que resolvía exactamente el problema. No respetaba las normas de diseño ni usaba los design tokens. Seguía documentación obsoleta porque seguía ahí, viva, sin nada que la marcara como obsoleta. Mi primer instinto fue el de todos, meter más contexto en el prompt. Más reglas, más "por favor no hagas esto", más ejemplos pegados a mano. Funcionaba a medias, y para la siguiente tarea había que volver a agregarlo todo. Hasta que llegaba el siguiente subagente y empezaba de cero. En algún momento, cansado de repetirme, entendí lo obvio. El agente no me estaba desobedeciendo. Estaba leyendo el repo y haciendo caso a lo que el repo decía de sí mismo. Si conviven el componente bueno y tres versiones viejas, no tiene cómo saber cuál es el oficial. Si la doc dice una cosa y el código hace otra, le va a creer al que esté más a mano. Está haciendo justo lo que le pedí. El mismo repo es el contexto que usan los agentes. Si está mal estructurado, las respuestas no van a ser buenas. Punto. No hay prompt que arregle un repo que se contradice a sí mismo. Screaming Architecture me llevó hasta media cancha Lo prim

Every startup idea looks perfect... until you start building. The first version of PixoraCloud looked amazing on paper. Then reality hit. We discovered: Some features weren't necessary Some APIs were too complicated Some ideas solved our problem, not the user's problem So we changed them. A lot. That's where we are today. Not chasing perfection. Chasing simplicity. Building in public means admitting your first idea isn't always your best one. What's one thing you've completely changed after starting a project?

Architecture Overview Clioloop's Agentic Fusion is not just "run the same prompt 5 times and pick the best." It's a structured pipeline where different models play different roles, with strict security boundaries between them. The Pipeline Step 1: Planning Phase When you run /fusion , up to 5 planner models are dispatched in parallel. Each planner: Receives your original prompt and context Has read-only tool access — they can search the web, read files, but never modify anything Proposes an approach (not an answer — an approach) The planners might suggest different strategies: Planner A: "Search the web for similar problems, then write a script" Planner B: "Read the existing codebase first, then modify in place" Planner C: "Break it into subtasks and use the Kanban system" Step 2: Execution Phase Your main model takes the planners' proposals and does the actual work: Full tool access (file editing, shell, web, browser, image gen, etc.) Fully visible — you watch every file edit, every command, every web search in real time Not a black box — you can intervene at any time This is the key difference from "ensemble" approaches: the main model does real work with real tools, not just text generation. Step 3: Review Phase Up to 5 reviewer models critique the draft: Read-only access — they can see what the main model produced, including generated images They check for errors, suggest improvements, flag problems Each reviewer works independently Step 4: Verdict Loop The draft is revised based on reviewer feedback: If reviewers find issues, the main model gets the feedback and revises The loop continues until reviewers approve You get the final, reviewed answer Step 5: Fusion Everything combines into one answer that has already passed independent review. Security Model The safety comes from schema-level restrictions : Role Can Read Can Write Can Execute Planners ✅ Files, web, images ❌ Nothing ❌ Nothing Main Model ✅ Everything ✅ Files ✅ Commands Reviewers ✅ Draft, files, image

This is a submission for the June Solstice Game Jam This installment brings a Firebase build to Midsommer Madness via Antigravity CLI. The Midsommer Madness web app is deployed to Firebase Web Hosting and the Maypole was saved! What I Built When it comes to Summar Solstace — the place to be is Sweden. It is one of the highlights of the calendar. This project aimed to recreate some of the mystique around the event- just in time for some fresh surestromming! Now you can get it with Firebase enhancements! FireBase Console The full project was imported to the Firebase Console: Just show me the Code!!! GitHub Repo is here: GitHub - xbill9/midsommer-firebase Midsommer Madness with Firebase So how can we use Firebase to enhance the project? Github and Skills! The GitHub repository has been successfully linked to your Firebase project midsommer-madness . ### What was configured: 1. GitHub Secrets: A service account ( github-action-1273534909 ) with Firebase Hosting admin permissions was created, and its credentials were uploaded to your GitHub repository secrets as FIREBASE_SERVICE_ACCOUNT_MIDSOMMER_MADNESS . 2. GitHub Actions Workflows: Two workflow files were generated and pushed to your GitHub repository: • firebase-hosting-pull-request.yml: Deploys a preview channel of the game whenever a PR is created against the master branch. • firebase-hosting-merge.yml: Automatically deploys the latest version to the live Firebase Hosting site whenever a PR is merged (or a commit is pushed) to the master branch. 3. Agent Skills: Installed Firebase Agent Skills in the repository to make it easier for agents to help you with Firebase configurations in the future. > /skills ⎿ Exited /skills command What else? > how is firebase enhancing the project ● Read(/home/xbill/midsommer-firebase/lib/main.dart) (ctrl+o to expand) Firebase enhances the Midsommer Madness project in four primary ways, turning it from a simple local game into a connected, production-ready mobile application: ### 1.

Build-in-public. This is the real architecture behind running ~50 local AI agents on 6GB of VRAM — one GPU lock, an eviction watchdog, a resource governor, and a model router. Originally posted on my blog. The question I get most often is some version of "there's no way you run that many agents on a 6GB laptop GPU." The honest answer: not the way you're picturing it. I don't run 50 models at once. I run one model at a time, very deliberately — and most of the engineering is about scheduling, not inference. Here's the actual architecture. The hard constraint: 6GB of VRAM A single consumer GPU with 6GB of VRAM holds roughly one 7B-parameter model at a usable quantization. Two at once? It thrashes — the GPU starts swapping, latency explodes, and eventually a driver out-of-memory can take the whole machine down. I've had the desktop freeze from exactly that. So the first design rule wrote itself: only one heavy model is allowed on the GPU at any moment. That sounds limiting. It isn't — because almost nothing I run is latency-sensitive. A blog post that publishes at 7am doesn't care if it was generated at 6:52 or 6:58. Once you accept that your AI workforce is a batch system, not a chat window, the whole problem changes shape. A lock, not a crowd Every agent that needs the GPU has to take a lock first. It's a simple file-based queue with: FIFO ordering PID-based ownership Stale-lock detection, so a crashed job can't wedge the line forever If an agent can't get the lock within its timeout, it skips gracefully and tries again on its next scheduled run instead of piling up. So at 50 agents, what's really happening is: dozens of cron-scheduled Python workers wake up throughout the day, and the ones that need the model form an orderly line for it. The fleet is huge; the GPU contention is always exactly one. That's the trick. It's less "50 models" and more "50 employees sharing one very busy workstation, politely." Eviction and a VRAM watchdog Even with the lock, idle models l