标签：#an

American Diabetes Association blocked publication of op-ed articles so the authors posted them as a preprint.

Are we living through a small car renaissance? There's the Slate Truck, Amble's dune buggy, and the Fiat Topolino, as well as a whole galaxy of kei cars and trucks from Japan that have their own built-in fan base. While microcar sales in the US are still as tiny as the vehicles themselves, there are […]

I've been using Claude for a long time and mostly ignored Artifacts. Fine for a quick React demo. Not something I reached for. Then I needed to send an analysis to a few people at work, and it clicked. Or I'm just using it in a way nobody intended. Hard to say. The actual case I own the paywall backend at a Czech media house. The subscription offer on our news site is embedded as an iframe, and iframes are a bad neighbourhood: context isolation means the iframe has no access to the parent page's session, so user identity kept breaking and we kept patching it over postMessage. Every iframe is its own page view, so GA4 data was skewed and we had to build server-side tracking and session stitching to make the numbers mean anything. And ad blockers, CSP, and timeouts mean sometimes the thing just doesn't render, so we maintain a fallback UI in parallel. I wanted to propose we drop the iframe and ship a JS embed library instead, distributed through our internal npm registry. That's an architecture change, so it needs a document: what we fixed, why the iframe is still structurally wrong, what the alternative costs, what the numbers say. The numbers part came out of the same agent session, by the way. GA4 said roughly 0.14% of paywalled page views hit an error, about half of them iframe-blocked-by-browser. That's every 700th reader. Small number, real money. The boring problem You get a good answer out of the model. Now what? You paste it into a doc. Reformat it, because chat markdown does not survive the trip. Fix the tables. Decide whether it goes in Confluence or an email. Send it. Then someone asks a follow-up, you go back to the model, get a better answer, and now there are two versions of the truth and one of them is in someone's inbox. I've done the email version of exactly this document before. Outlook ate the markdown. I ended up hand-rolling plain text with unicode bullets and uppercase section headers like it was 1998. Half of that work is transport, not thinkin

David Risher insists that Lyft has lowered its prices and that customers who only check his competitor’s app are “leaving money on the table.”

The recall comes as the top automotive safety regulator in the U.S. has warned AV companies about their vehicles interfering with first responders.

Ben O'Mahony discusses building custom AI-powered Language Server Protocols (LSPs) that go beyond standard rule-based checkers. He explains how to instrument AI agents natively with OpenTelemetry to track concrete user actions (accepting, dismissing, or regenerating code fixes) as implicit labels, creating a continuous data flywheel to distill frontier capabilities into cheaper, local SLMs. By Ben O'Mahony

We consulted preparedness experts and WIRED’s team of testers for the essential gear to keep on hand in case of wildfires, earthquakes, and lord knows what else.

New report says our ability to tie weather damages to climate change is improving.

FCC chair has been gifted at least $63,000 worth of tickets by CBS or its parent company.

Nice PlayStation you got. Bet it could probably run Linux too.

Sarah Friar, CFO of OpenaAI, introduces a practical AI scorecard to measure ROI through useful work, cost per successful task, dependability, and return on compute.

Perimenopause has entered the chat. Perimenopause—and its better-known relative, menopause—used to be considered taboo. Not anymore, thanks at least in part to TV doctors and social media influencers. Perhaps it’s my age, but these days, both my algorithm and my conversations with friends increasingly swing toward perimenopause. Menopause is defined as the life stage that…

OpenAI's July 14 guidance for managing AI investments recommends five moves: improve visibility into usage and spend, evaluate efficiency by outcome ROI, govern advanced workflows before scaling, fund workflows that compound, and match capacity to proven demand. Primary source: OpenAI, “How to manage AI investments in the agentic era” . The hard part is the denominator. “This agent used $800” says little. “This workflow cost $14 per accepted reconciliation, including review and rework” can support a decision. Here is a one-page ledger I would require for an agent pilot. Define one accepted outcome Do not start with tokens, seats, or tasks launched. Define the business state that counts after review. workflow : vendor-invoice-reconciliation accepted_outcome : " invoice matched, exceptions reviewed, result posted" owner : finance-ops pilot_window_days : 21 minimum_sample : 100 invoices quality_gate : false_postings : 0 exception_recall : " >= 0.98" reviewer_minutes_p50 : " <= 3" A generated draft is not an outcome if a person must rebuild it. An agent run is not successful if its result never enters the system of record. Capture the complete cost AI cost + orchestration and observability + human review + rework + incident handling + allocated implementation cost = total workflow cost Use a table with declared variables: Variable Meaning Example only C_model model and tool-call spend $600 C_platform workflow infrastructure $200 H_review reviewer hours 35 R_hour loaded reviewer rate $45 C_build pilot build cost allocated to window $2,000 N_accept accepted outcomes 850 total = C_model + C_platform + H_review * R_hour + C_build cost_per_accepted_outcome = total / N_accept With the illustrative numbers, total cost is $4,375 , or about $5.15 per accepted outcome. These are not benchmark claims; replace every value with measured data. Compare against the real baseline The baseline must use the same unit and quality gate: Metric Manual baseline Agent pilot attempted invoices

Day 1 · by Kunal Hore ( @KunalOnTech ) Quick Jump Why I'm Learning This Publicly Today's Map 1. State 2. Nodes 3. Edges 4. Build & Run — The Full Exercise Kunal's Interview Corner Today's Takeaway Most code runs top to bottom, once, with no memory of where it's been. Real decisions don't move in a straight line — sometimes you loop back, sometimes you branch depending on what just happened. A script can't pause mid-run and reconsider. A graph can. That single difference — code that can stop, decide, and circle back instead of just executing — is the entire reason LangGraph exists. Over the next few days I'll cover all the topics to make you familiar with LangGraph. This is my first day of learning, and I'll share whatever I learn along the way. Today it's the three basics — what a graph remembers ( state ), what counts as one step (a node ), and how those steps connect (an edge ). We won't just talk about them — we'll build a small hands-on exercise with real code, because I've always believed you learn by building, not by theory alone. Kunal's one-liner: "Code that only moves forward can't think. Code that can loop back, can." That's the whole pitch for today. Everything else — TypedDict, function signatures, edge syntax — is just the mechanics of making that one idea real in Python. Why I'm Learning This Publicly I'm learning LangGraph from zero — one concept a day. No shortcuts, no pretending I already know it. Whatever I learn each day, I share the same day: the wins, the confusion, the "oh THAT'S what it means" moments, all of it. My goal is simple: One concept per day, explained with everyday analogies — no jargon walls Real code every single day, because you learn by building, not by theory alone Write it the way I wish someone had explained it to me Your goal, if you learn alongside me: by the end of this series, we'll both be able to design and build stateful AI agents — the kind of systems that can decide, branch, retry, and loop, not just respond once. An

Your agent feels fast during a demo. Then a real session reaches twenty turns, several tools have returned large payloads, and every response starts taking longer and costing more. This pattern is often called token drift : the effective input context grows as an agent carries more conversation history, tool output, retrieved documents, and state into each model call. The model itself is not gradually becoming less efficient. The application is asking it to process more material on every turn. Token drift is manageable, but only if context is treated as a budgeted system resource rather than an unlimited transcript. What Token Drift Actually Means Most conversational agents build each request from several sources: a system prompt, tool definitions, recent messages, retrieved context, durable memory, and sometimes a summary of older work. Whether the application sends that state on every request or a provider manages part of it, the model still has an effective context to process. Consider an illustrative session: Turn Effective input What changed 1 1,200 tokens System prompt, tools, and one user message 8 6,900 tokens Conversation history and two tool results 20 18,400 tokens More history, retrieved documents, and accumulated state The exact price and latency depend on the model, provider, cache behavior, and workload. The important signal is the trend: later calls repeatedly process a larger context. Why Agents Accumulate Tokens So Quickly Conversation history is only one source of growth. Production agents often accumulate tokens in several places at once: Repeated transcripts: Every prior user and assistant message remains in context. Tool schemas: Large tool descriptions and JSON schemas may be attached to every model call. Tool results: Search results, stack traces, database rows, and API responses can be much larger than the user's request. Retrieved documents: RAG pipelines sometimes add too many chunks or keep stale retrieval results across turns. Retries an

1. Introduction In 2026, many teams still default to WordPress when building blogs or marketing sites, often without fully considering the architectural alternatives. The classic WordPress setup PHP on shared hosting or managed WordPress platforms, coupled with a MySQL database and a plugin ecosystem works reliably but comes with inherent performance trade-offs. Modern visitors now expect lightning-fast page loads and perfect Core Web Vitals a bar that traditional WordPress setups struggle to meet without extensive optimization and caching strategies. This article examines why, for many developer-managed websites, Astro + Cloudflare Pages delivers superior results in performance, SEO, security, and maintainability compared to traditional WordPress deployments. We'll explore the technical trade-offs and help you make an informed decision for your next blog or business website. 2. What is Astro + Cloudflare Pages? Astro is a modern web framework that prioritizes delivering fast, lightweight content by default. Instead of running client-side JavaScript on every page load, Astro generates complete HTML during build time. Only interactive elements—dubbed "islands of interactivity"—run JavaScript, and only when needed. Cloudflare Pages is a globally distributed static hosting platform that leverages Cloudflare's edge network for content delivery. Think of it as Git combined with Cloudflare's CDN and security stack with integrated CI/CD, zero-downtime deployments, and automatic edge caching. How they work together: You write your content and components using Astro's Markdown, MDX, or frameworks Astro builds your site to static HTML during your CI/CD pipeline Cloudflare Pages takes the built static assets and deploys them to edge locations worldwide Every request hits the nearest edge location , serving cache-optimized HTML directly This contrasts sharply with WordPress, which typically involves: PHP processing on every request Database queries to fetch content Server-side

In the wake of a massive hours-long gridlock event, San Francisco mayor Daniel Lurie has told state regulators it's time to put more requirements on robotaxi operators like Waymo.

The company didn't immediately say what went wrong. SpaceX's stock plunged more than 4% in after-hours trading before paring losses.

Both nominees flailed in their own unique ways as senators sought answers.

On today’s Uncanny Valley, we unpack OpenAI’s ongoing drama, both legal and reputational, and whether these developments could further hurt the company—particularly in its fight against Anthropic.