标签：#AI

Nvidia has a plan to make sure its GPUs won't lose value. It wants to convince a new crop of financiers to keep lending for AI buildouts.

Bartesian's cocktail makers would be best described like a Keurig or Nespresso machine, but for alcoholic drinks.

Going into my demo of Marvel's Wolverine, I mainly wanted to try out the game's very bloody combat. And it is delightfully bloody. But after two-ish hours of slashing and stabbing (and parrying!) enemies with Wolverine's claws, I left surprised - despite no previous attachment to the character, I was deeply endeared to Logan himself. […]

The tech giant has considered a nine-figure budget for the payments, according to the WSJ.

Today on Decoder, I’m talking with Hayden Field, The Verge’s senior AI reporter, about a question that’s been rocketing around the tech industry for the past week: Is Google losing the AI race? That’s because last week Google announced a bombshell reorganization of its AI division, Google DeepMind. Jeff Dean, the company’s chief scientist, is […]

Rapid revenue growth fuels hope Claude maker's IPO is the biggest listing in history

Get familiar with easy methods to elevate your photos and make them look crisp, clean, and visually appealing without diving into complicated software.

Microsoft is finally beginning to combine its consumer and commercial Copilot AI assistants into a single "super app" interface, starting with the Copilot and Microsoft 365 Copilot apps. Both personal and work accounts will be moved to the new unified app, which recycles the "Microsoft Copilot" name but features an updated app icon. The single […]

Nintendo's first Fire Emblem game for the Switch 2 is structured in an ambitious way. Unlike the well-loved Three Houses, a strategy game that tasked you with pledging allegiance to a specific faction and seeing their story all the way to the end, the new Fortune's Weave lets you swap between four heroes and their […]

I fixed this script's frontmatter parser a week ago. A draft with an unclosed --- block used to blow up with a bare ValueError: not enough values to unpack , and I patched it to raise a clean, actionable error instead. I wrote that fix up, verified it with a stubbed repro, added a --selftest case for it, called it done. Then I went back to write today's articles and actually looked at the line I "fixed" instead of the error path around it. def parse ( text ): meta = {} body = text if text . lstrip (). startswith ( " --- " ): parts = text . lstrip (). split ( " --- " , 2 ) if len ( parts ) < 3 : raise ValueError ( " frontmatter opened with ' --- ' but never closed with a second ' --- ' delimiter " ) _ , fm , body = parts ... split("---", 2) doesn't split on lines that are --- . It splits on the literal substring "---" , anywhere in the text, and stops after the second one it finds. My fix only handles the case where it finds fewer than two — an unclosed fence. It says nothing about what happens when the second "---" it finds isn't the closing fence at all, because a third one showed up first, buried inside a frontmatter value. That's not a hypothetical. I write these article titles myself, and "before/after" is a phrase I reach for constantly: --- title : My Before---After Refactor tags : ai, python, refactor published : true --- real body starts here split("---", 2) finds the em-dash-style --- inside the title before it finds the real closing fence on its own line. So the split points land in the wrong place entirely: >>> from publish_devto import parse >>> meta , body = parse ( text ) >>> meta { ' title ' : ' My Before ' } >>> body ' After Refactor \n tags: ai, python, refactor \n published: true \n --- \n real body starts here \n ' The title got truncated to "My Before" . tags and published never got parsed as frontmatter fields at all — they're sitting in the body now, as literal text, along with the real closing fence and a stray leftover --- . If I ran this thr

Early this year I was wiring Claude into Jira through an MCP server. It worked, and every session it felt slightly wrong: slow round trips, a schema I did not control, structure sitting somewhere the agent could not see while it was reading the code. The fix was almost embarrassingly simple. Put the ticket in the repo, as markdown. I pitched it to a colleague, and off we went. Seven months later: 15 projects across 10 repositories, 165 live tickets, 12 people on the board including non-developers, and no Jira licence. This post is why we left and what we built. Two follow-ups cover the rest: the skill and the loop that let agents work these tickets , and the three review layers that keep the output honest . What was actually wrong with Jira The cost was easy to name: roughly €2,000 a year for something we used maybe 5% of. It was not the reason we left. Every user had to be paid for, so the board was implicitly rationed. Performance degraded as projects grew. The features we wanted sat behind paid plugins. Automations were clumsy enough that we mostly did not write them. And the board was close to what we wanted without ever being it, because that last gap lived in someone else's product roadmap. None of that is fatal alone. Together it means the tool shapes the team instead of the other way around. The constraint that ruled out the obvious answers We are one team maintaining ten separate repositories that ship independently of one another, across TypeScript, C#, Java and PowerShell. A monorepo was never realistic. That kills the usual alternatives. GitHub Issues comes closest and misses twice: issues are scoped to one repository, so cross-repo visibility becomes somebody's weekly spreadsheet, and despite feeling like part of the repo they are not in it. They live in a database behind an API. Not files, not on the branch, not in the diff, and not something an agent editing the code can read without a round trip. Every hosted alternative moves the work further away s

On July 28, the Model Context Protocol project shipped a new spec revision, 2026-07-28 . I run backend engineering at GoodBarber, and our public MCP server is a live production surface: real apps, real content, real push notifications. So for us a new revision is not a changelog to skim on a Friday. It is a migration with our name on it. We have just brought the server up to the new revision. This post is three things: the operator's cut of what changed, what upgrading a public server actually involves, and the thing we found in our logs while checking the work. The last one is the reason I'm writing. The operator's cut of 2026-07-28 The headline is the stateless core. MCP grew up as a stateful, bidirectional protocol: an initialize handshake, a negotiated session, an Mcp-Session-Id header to carry it all. The new revision retires that entirely. Every request now self-describes in _meta : protocol version, client identity, capabilities. The practical consequence is the one server operators have wanted since day one: you can put an MCP server behind a plain round-robin load balancer with no shared session storage. If you have ever kept session affinity alive with duct tape, you know exactly which muscle just relaxed. The rest, fast: Method and tool names now also travel in Mcp-Method and Mcp-Name HTTP headers, so gateways can route and meter without parsing JSON bodies. Multi Round-Trip Requests: a call can come back with resultType: "input_required" and continue over stateless connections. Mid-call questions no longer need a held-open stream. List results (tools, prompts, resources) carry ttlMs and cacheScope , so clients can finally cache your inventory honestly instead of guessing. Authorization hardening: RFC 9207 issuer validation, and Client ID Metadata Documents replacing Dynamic Client Registration. Tasks, MCP Apps, and Enterprise Managed Authorization become formal extensions instead of core features. Roots, Sampling, and Logging are deprecated, with a minim

Comfy MCP is Comfy's first-party local Model Context Protocol server. It lets an MCP-capable coding agent inspect the models and nodes in your ComfyUI installation, validate workflows, run them, and retrieve the outputs. The detail that prevents the most confusion is that two processes are involved : comfy launch starts ComfyUI. Your AI client starts comfy-mcp as a local stdio server. If you run comfy-mcp directly and it appears to do nothing, it is probably waiting for an MCP client. That is normal for a stdio server. Disclosure and verification scope: AI tools assisted with drafting and editing this adaptation. I reviewed the finished article and checked the commands and material claims against Comfy's official documentation, repository, and PyPI pages on 13 August 2026. I have not run a generation on my own hardware for this article, so this is a documentation-verified setup guide, not a hands-on performance test. Comfy's documentation currently labels the MCP offering a public beta, so tools and behaviour may change. What you need Before starting, have: Python 3.10 or newer. The examples below use Python 3.11. comfy-cli 1.14.0 or newer. A ComfyUI workspace, either created with comfy install or selected with comfy set-default . An MCP client that can start a local stdio server, such as Claude Code, Cursor, or Claude Desktop. The models and custom nodes required by the workflow you want to run. The MCP bridge is not what determines the hardware requirement; the selected ComfyUI workflow does. A small image workflow and a large video workflow can have very different memory needs. 1. Install comfy-cli and comfy-mcp I prefer a dedicated virtual environment. It keeps the executables in a predictable place and avoids mixing these packages with unrelated Python projects. Windows PowerShell mkdir comfy-mcp-guide cd comfy-mcp-guide py -3 . 11 -m venv . venv . \.venv\Scripts\Activate.ps1 python -m pip install --upgrade pip python -m pip install "comfy-cli>=1.14.0" comfy-mc

Goal Keep Claude Code's account/session login ( ~/.claude.json ) alive across devcontainer rebuilds, instead of having to re-authenticate every time the image is rebuilt. The problem Claude Code keeps two things on disk: ~/.claude/ — a directory, already persisted via a named Docker volume ( claude-playwright-setup ). ~/.claude.json — a single file holding account/session state, which was not persisted. Every container rebuild wiped it, forcing a fresh login. Normally you'd just mount a named volume onto the whole folder the state lives in, the same way .claude/ , .copilot/ , and .continue/ are already handled. That's not an option here: .claude.json isn't inside its own subfolder, it sits directly in $HOME alongside everything else ( .bashrc , .ssh/ , .profile , ...). Mounting a volume onto $HOME itself to catch one file would shadow all of that, so the file has to be persisted on its own. Mounting a named volume straight onto the file path ( claude-json-...:/home/container-user/.claude.json ) seems like the next-simplest option, but it breaks on this Docker Desktop setup: mount ... not a directory: Are you trying to mount a directory onto a file A named volume's backing store is always a directory. Docker is supposed to detect that the mount target is a single file and copy the image's file into the volume so it ends up binding file-to-file. On this Docker Desktop that detection fails — the volume comes up as an empty directory, and runc then tries to bind that directory onto the file path and crashes at container start. This was confirmed by deleting the volume and rebuilding the image from scratch, so it isn't a stale-cache artifact. The fix Never mount a volume directly onto a single file. Instead, mount it onto a directory — the same shape already used for .claude / .copilot / .continue — and symlink the dotfile into that directory from the Dockerfile. Dockerfile.debian : USER container-user .... RUN mkdir -p /home/container-user/.claude-json && \ touch /home/

I kept hitting the same small friction: I'd want to quickly rewrite an email, clean up some text, or summarize a long thread — and every tool wanted me to sign up, pick a plan, or watch an ad first. For a ten-second task, that's absurd. So I built the thing I wanted: a set of free, no-signup AI text tools , each doing one job well. This is a quick write-up of the stack and the decisions behind it. 👉 Live: https://www.texttoolsai.app The core idea: one tool, one job, zero friction Instead of a single mega-app, it's a collection of single-purpose tools — rewrite, tone change, summarize, prompt generation — each on its own page. You land, paste, get output. No account, no modal, no paywall. The "no signup" rule forced good constraints: everything has to work instantly and statelessly, which kept the whole thing simple. The stack Next.js (App Router) — server components for the content/SEO pages, client components only where the tool actually needs interactivity. Vercel for hosting — the deploy story is boringly good, which is what you want. An LLM API on the backend — the browser never sees a key; requests go through a Next.js route handler that owns the prompt and the provider call. Tailwind for styling — fast to iterate, easy to keep consistent across dozens of tool pages. One decision that paid off: data-driven pages Every tool is defined as a config object (label, placeholder, system prompt, endpoint) rather than a hand-built page. Adding a new tool is mostly adding data, not wiring up new routing. That's what made it realistic to ship a lot of tools without the codebase turning into spaghetti. // simplified shape { slug: 'rewrite', label: 'Paste your text', endpoint: '/api/tools/rewriter', systemPrompt: '...' } The route handler resolves the endpoint key against a map of system prompts, so the API surface stays tiny even as the tool count grows. What I'd tell anyone building something similar Keep the API key server-side. Obvious, but easy to leak through a miscon

The mark flags anything Claude processed, even human writing it only edited.

This essay was written with Nathan E. Sanders, and originally appeared in Tech Policy Press . AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of the industrial revolution, when new technologies like the steam engine provided a quantum leap in our ability to do mechanical work outside of our bodies at scale. If AI’s cognitive capabilities become integrated into our lives, businesses, and governments—a process that will take years if not decades—society will be as unrecognizable as the modern world would be to a preindustrial farmer. And yet, Americans—by a wide margin—...

Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.

People with schizophrenia face a perfect storm of dangers on a hotter planet.

Anthropic conducted an audit of 141006 evaluation runs after OpenAI's sandbox escape disclosure. The review identified three incidents where Claude models accessed the internet due to misconfigurations. These incidents involved unauthorised attacks on live targets. Anthropic has suspended offensive evaluations and plans to enhance security measures and collaborate with external auditors. By Olimpiu Pop