标签：#t

TL;DR — When the spec is good, implementation needs less model. I started using a top-tier model to write the spec and a cheaper, faster one to implement it — still using the strong model, just spending it on the spec instead of the implementation. The gain isn't some magic prompt phrasing; it's the context: explicit business rules, audited project constraints, a defined output contract. That's systems engineering — the discipline of anyone who's kept real software alive, whatever their stack. Every backend dev knows the scene: the Swagger is out of date, the last hotfix shipped without a unit test, and the README.md documents a command nobody's used in six months. The code works. The docs lie. And the gap between the two is exactly where AI — and we — start to go wrong. I've spent the last few months developing with AI for real inside production projects, not tutorial greenfield. My takeaway was less about which model to use and more about a shift that already has a name: the move from prompt engineering to context engineering . The difference isn't semantic. Prompt engineering treats the problem as writing — finding the magic phrase. Context engineering treats it as what it always was: a systems engineering problem . And it's where my backend background applied most directly — though anyone who's kept a real system alive has the same instinct. The experiment that convinced me Let me start with the evidence, because that's what made me take this seriously. My reflex, for a long time, was to reach for the strongest model for everything — more expensive, smarter, fewer errors. Makes sense on paper. In practice, I saw something else. When the task's specification is well done — explicit business rules, audited project constraints, a defined output format — the model capability needed for implementation drops sharply. Enough to split the work by stage: I started using a top-tier model (currently Opus) to write the spec , and a cheaper, faster model (Sonnet) to implemen

Your code has CI/CD. Your docs don't. Every modern engineering team has automated builds, tests, and deployments for their code. But documentation? That's still someone manually exporting a PDF, uploading it to Confluence, and hoping it's the latest version. This post shows you how to treat documentation like code: version-controlled Markdown in a Git repo, automatically rendered to branded PDFs on every push. No manual steps, no stale documents. The stack PaperQuire gives you three tools that work together: .paperquire.yml — project config that locks in your template, branding, and document options CLI — paperquire render and paperquire batch for scripting and local builds GitHub Action — paperquire/render-action for automated builds in CI Each one builds on the previous. The config file means no one has to remember flags. The CLI means you can test locally. The action means it happens automatically. Step 1: Add a project config Drop a .paperquire.yml in your repo root. Every render — GUI, CLI, and CI — picks up these settings automatically: template : corporate toc : true toc-depth : 3 h1-page-break : true cover : title : " Project Documentation" author : " Engineering Team" branding : primary-color : " #2563eb" This is your single source of truth for how documents look. Change it once, and every PDF across every environment updates. Step 2: Test locally with the CLI Before committing, verify your docs render correctly: # Render a single file paperquire docs/architecture.md -o out/architecture.pdf # Batch render the entire docs directory paperquire batch ./docs -o ./out # Dry run — validate without producing output paperquire batch ./docs --dry-run The CLI reads .paperquire.yml automatically. The output is identical to what CI will produce. Step 3: Automate with the GitHub Action Add one workflow file and your docs build themselves: # .github/workflows/docs.yml name : Build Documentation on : push : paths : - ' docs/**/*.md' - ' .paperquire.yml' jobs : render : ru

AI Content Detection, Zig Low-Level Hardening, & Sub-1nm Chip Security Focus Today's Highlights This week's highlights include a practical tool for detecting AI-generated content, crucial low-level compiler enhancements impacting code safety, and a look at the future security implications of cutting-edge hardware. tropius: detect AI tropes in prose (Lobste.rs) Source: https://tangled.org/desertthunder.dev/tropius The "tropius" project introduces a tool specifically designed to identify common stylistic patterns or "tropes" often found in AI-generated prose. In an increasingly complex digital landscape, where AI-produced text can be deployed for sophisticated misinformation campaigns, advanced phishing attempts, or large-scale automated content generation, the ability to accurately detect such artificial patterns is becoming a critical defensive technique. This tool could be instrumental for security professionals in a variety of contexts, including verifying the authenticity of critical communications, combating the rapid spread of deepfake text, or ensuring appropriate human oversight in sensitive information flows. For security teams, integrating AI content detection utilities like tropius into their threat intelligence and defense strategies offers a tangible way to enhance information integrity. It helps in proactively identifying and mitigating risks associated with malicious AI-driven content, bolstering resilience against evolving social engineering tactics that leverage artificial intelligence to appear more convincing or credible. Comment: Identifying AI-generated text is increasingly important for verifying content authenticity and combating misinformation. Tools like tropius offer a practical approach to detect AI tropes, which could be vital for security teams monitoring for AI-driven threats and maintaining information integrity. Zig's new bitCast semantics and LLVM back end improvements (Hacker News) Source: https://ziglang.org/devlog/2026/#2026-06-25

A refreshing direction for a price change.

The whole industry seems to have agreed on a standard for design tokens. The shift it sets up is still on its way. Design tokens are not new. The term was coined in 2014, at Salesforce, by Jina Anne and Jon Levine. 1 By 2017, Amazon had open-sourced Style Dictionary and the idea had spread well past Salesforce. We have been shipping design tokens for over a decade. What we never did, in all that time, was agree on a format. Every tool and every team rolled its own shape. There was never one neutral way to write a token down, its value and its meaning, so that any other tool could read it. Have you heard of DTCG? I hadn't, until recently. It is the Design Tokens Community Group, a W3C effort to finally settle that format. 2 The repo is quiet, but that is because the spec reached its first stable version in late 2025, not because anyone walked away. The quiet is a thing being finished, not abandoned. The list of who is backing it is not quiet at all. Adobe. Google. Microsoft. Meta. Amazon. Shopify. Salesforce. Sony. Pinterest. The New York Times. Disney. Framer. Penpot. Figma. Plus a dozen more. 2 That is not a side project. That is most of the industry quietly agreeing on something. One of those names, Figma , is the reason for the title of this piece. We will get to it, because the irony is the whole point. Here is my bet, and I will say up front that it is a bet. I think a storm is coming for design tooling. You do not have to believe me about the storm, because the bet does not depend on it. If you are wiring your tokens straight into one vendor's format, you are exposed. Anchor them to the open standard instead and you are not. The downside is lopsided. If I am wrong, you have lost almost nothing. If I am even half right, everyone hard-coded to a single tool is facing a rewrite. The format is young and already fragmenting. That is the point. The obvious objection is that the standard is too new to bet on, and already splintering. It is splintering. Google's DESIG

"Model unit prices keep falling, yet our monthly AI bill keeps climbing." If you use AI personally, you can feel the creep of your subscription and metered charges. If you own AI usage inside a company, the gap is even more pronounced. Overseas, this feeling has started getting a name: Tokenomics . On June 3, 2026, the Linux Foundation announced its intent to launch the Tokenomics Foundation , dedicated to open standards for AI cost management. Google, Microsoft, Oracle, JPMorganChase, and others — both providers and large buyers — are on board. https://www.linuxfoundation.org/press/linux-foundation-announces-the-intent-to-launch-the-tokenomics-foundation-to-establish-open-standards-for-ai-cost-management This post isn't an explainer of the word itself. It's an account of what changes for the people who own internal generative AI usage — the platform owners, the FinOps practitioners, the engineering leaders watching the bills — once you have this word in your vocabulary. What Tokenomics gives you isn't another saving technique. It changes the unit of measurement and the lens through which you read AI cost. Why Tokenomics, why now Tokenomics sits in the lineage of cloud FinOps. The FinOps Foundation now classifies Tokenomics as the "AI Value" dimension within FinOps for AI . Where cloud FinOps tracked the variable infrastructure costs (compute, storage, networking) against value, Tokenomics tracks the variable cost of intelligence itself. It's not a replacement; it adds a probabilistic, non-deterministic layer of variable cost on top. Tokens here means what you see on every API price sheet and usage dashboard — the smallest unit a language model reads and writes, the unit of compute. The word "tokenomics" also exists in the crypto world, but that one is about issuance, distribution, and incentives on a blockchain — tokens as units of ownership. Same word, different economies. https://www.finops.org/insights/token-economics-the-atomic-unit-of-ai-value/ The term gained

Thanks to the component crisis, it's a bad time to want a new computer. But if you are waiting on a preorder for the Framework Laptop 13 Pro - which Framework's CEO has called the "MacBook Pro for Linux users" - the company shared good news on Thursday that might mean yours will cost less […]

Autonomous AI agents are transitioning from experimental developer playgrounds into the core of enterprise application architecture. For organizations looking to automate complex workflows that require decision-making, reasoning, and tool use, agentic AI represents a paradigm shift. However, moving from a simple demo script to a reliable, production-ready enterprise agent system requires addressing significant architectural challenges. In this article, we will examine the core components of enterprise agent systems, design patterns for robust execution, and security considerations. The Core Architecture of an AI Agent An enterprise AI agent is more than just a large language model (LLM) loop. It is a system composed of four critical pillars: Reasoning & Planning (The Core LLM): The orchestrator that decides how to approach a problem, breaks down tasks, and analyzes output. Memory: Storing short-term execution traces (context) and long-term knowledge (vector databases, semantic memory). Tools (Action Space): APIS, databases, calculators, and code execution sandboxes that the agent can invoke to retrieve information or perform tasks. Guardrails & Evaluators: Decoupled verification layers that inspect the agent's plans and tool execution to enforce policy and security. +-------------------------------------------------------------+ | USER REQUEST | +-------------------------------------------------------------+ | v +-------------------------------------------------------------+ | AGENT ORCHESTRATOR / LLM LOOP | | * Planning (ReAct, Plan-and-Solve) | | * Memory retrieval | +-------------------------------------------------------------+ | ^ v (Call Tool) | (Tool Results) +------------------------+ +----------------------+ | TOOL ROUTER | | GUARDRAILS LAYER | | * APIs * Code Exec | | * Safety filter | | * DBs * RAG Lookup | | * Data sanitization | +------------------------+ +----------------------+ Planning Patterns: ReAct vs. Plan-and-Solve When designing how an agent re

I started my career in the late 2010s, and I have had a front-row seat to the growth of the industry that has given me everything: software engineering. Looking back over the last decade, I have mixed feelings about some of the calls I made. And I am seeing the same patterns play out again now. So for engineers who are confused about where this is headed and how to navigate it, here is how I think about it. Generalist SWEs were a product of cheap money The late 2010s, I saw an huge amount of startup funding, globally. Flipkart, Snapdeal, Jugnoo, and hundreds of others were scaling hard and one hiring pattern I saw was that: everyone wanted generalist software engineers. People who could easily get upto speed across the stack.- backend, frontend, infra, deployment and simply ship. Building software was expensive. Automation was still low. Kubernetes had just gone mainstream. Shipping still meant a surprising amount of manual work: SSH-ing into servers, copying artifacts around, running mvn builds by hand, debugging deployments straight in production, duct-taping infrastructure that today you would never touch. Companies fought over engineers who maximized feature throughput. Breadth was a premium, because every extra engineer increased the rate at which software got built. It helped because the money was also free and VCs rewarded growth over efficiency, and hiring software engineers in bulk was the easiest way to spend it. Pull up a resume from an engineer who started around that time and you will usually see the same shape: a long list of technologies and frameworks, broad and adaptable, but rarely deep in any one thing. There was no incentive to go deep. LLMs Changed The Dynamics LLMs did not kill software engineering. It compressed the cost of implementation. The work that got hit first was the work that was already standardized: CRUD apps; API integration and glue code; Framework-heavy backend work; Frontend scaffolding; Standard architectural patterns. What use

All-in-one AI assistant — chat, images, voice & market data Discussion | Link

About a quarter of PCs are still running Microsoft's previous operating system.

Agent-testing startup Patronus AI, founded by former Meta AI researchers, is experiencing nearly insatiable demand, its investor says.

Microsoft announced today that the price of all Xbox models will rise in August, the second time in less than a year as memory prices continue to wreak havoc on every industry from cars to computing. Thankfully, we’re already out looking for Prime Day deals, and we were able to find some discounts on both […]

This week, Instagram launched a series of new features for its smart TV app that are all designed to get people to spend more time on the platform through the biggest screens in their homes. In addition to vertical Reels, Instagram for TV - which is currently available for Amazon Fire TV, Google TV, and […]

Carr cites screen time concerns, is accused of trying to be "the nation’s parent."

As far as prices go, Apple is kind of a reverse canary in the coal mine. With its famously generous margins and immense purchasing volume, it can afford to ride out price fluctuations in its supply chain in a way no other consumer tech company can. So when Apple raises prices across nearly all of […]

The prediction market giant Polymarket said it's refunding users who had funds stolen due to a third-party breach.

Have you ever opened an old Laravel 5 project and felt like you were walking into a house where every...

The company says the increases are being driven by rising memory and console storage prices, with costs more than 2.5x higher than previous levels.

The company said it is discontinuing its email inbox in favor of its AI agent offering as users are increasingly handing over the reins of their email to the agents.