Se você ainda tem o hábito de abrir links do X (antigo Twitter) para ler um post isolado, sabe como a experiência costuma ser irritante: ou o site pede login, ou carrega um monte de coisas que você não quer ver, ou simplesmente trava. Foi pensando nisso que Zhenyi Tan, desenvolvedor do site And a Dinosaur, criou o Litterbox.

O Litterbox é uma extensão para Safari (iOS, iPadOS e macOS) que abre links do x.com em um popup, permitindo ler aquele post específico sem sair da página em que você está — e sem precisar visitar o X de fato. A ideia, nas palavras do próprio desenvolvedor, é simples: abrir, dar uma olhada e fechar em seguida.

Alguns detalhes de funcionamento que valem a pena destacar:

• A extensão usa a mesma API que o X utiliza para os embeds oficiais do site, então não depende de gambiarras que podem parar de funcionar a qualquer momento.
• Nenhum cookie seu é enviado quando o popup é aberto — ou seja, o Litterbox não usa sua sessão logada no X para exibir o conteúdo.
• Links que podem ser abertos dessa forma ganham uma pequena marcação ao lado (um pontinho), já que nem todo link do x.com pode ser incorporado dessa maneira — perfis de usuário, por exemplo, ficam de fora.

O Litterbox é gratuito na App Store, sem assinaturas, compras no app, anúncios ou rastreamento, e exige o iOS 18/macOS 15 ou superior.

via Daring Fireball

Hot on the heels of OpenAI’s addition of a cloud-based browser to ChatGPT Work, Anthropic has added an in-app browser to Claude Cowork in its desktop app. What’s interesting about the two browser implementations is that while both ChatGPT Work and Claude Cowork are meant to be used for general knowledge work, Claude Cowork’s browser is something of a hybrid that mixes aspects of OpenAI’s Codex built-in browser with its ChatGPT Work cloud-based browser.

First of all, I do not yet have access to Claude’s in-app browser, so the following is based solely on Anthropic’s announcement and other documentation. Still, the differences are worth understanding since the tools are aimed at different workflows.

Like Codex’s in-app browser, Claude Cowork’s in-app browser is built into the desktop app itself. That ties Claude’s browser to the instance of its app running on your Mac. Turn your Mac off or close the Claude app, and the browser becomes unavailable. Leave the Claude app running, and you’ll be able to control the browser session remotely through the Claude mobile app or the web.

From there, however, the browsers diverge. As you’d expect, the Codex implementation is developer-oriented, with tools to build, inspect, and annotate web pages along with access to a terminal, repos, and diffs. In contrast, Claude Cowork’s in-app browser opens automatically as needed for general-purpose web tasks instead of development tasks.

Also, while both ChatGPT Work’s and Claude Cowork’s browser implementations benefit from being isolated from your other day-to-day browser use outside those apps, their handling of login credentials is a little different. As I wrote in greater detail yesterday, ChatGPT separates the login process from the model’s activity and evaluates the login page for things like phishing schemes. Claude Cowork’s in-app browser offers two ways to log in: manually, or by importing cookies from logged-in sessions in another browser. Currently, Claude supports cookie imports on the Mac from Chrome, Edge, and Firefox, but not Safari. In addition to the security benefits that come with a browser that runs isolated from your everyday browser, Claude also requests permission before acting on a site for the first time, blocks high-risk sites, checks actions against the your requests, and uses the same prompt injection protections as its Chrome extension.

My first-run experience with ChatGPT Work’s cloud browser was a mixed bag but showed promise. Although I haven’t tried Claude Cowork’s browser yet, I’m glad to see Anthropic moving in the same direction as OpenAI here. Isolating agent browsing by bringing the browser into Claude and ChatGPT doesn’t solve every security issue, but it’s a good starting point. I expect we’ll see both Anthropic and OpenAI iterate quickly on this theme in the coming months.

Yesterday, OpenAI introduced a new ChatGPT Work feature designed to let it navigate websites that require a login without revealing your credentials to the model.

Like a lot of people, I spend far too much time clicking around websites that require a login, looking at analytics and other data, checking whether new sponsors have been booked for our podcasts, and more. It’s a tedious but necessary part of my week that slows me down and takes me away from writing and other creative work. ChatGPT’s new Work feature is designed to handle that sort of work for you.

The feature works by signing into websites using a virtual, cloud-based computer. That separates the browsing session from any browsing session on your local computer, walling the agent’s computer use off from your open tabs, cookies, browsing history, passwords, and other data. Because the login and browsing happen in the cloud, that also means work can continue whether you close the ChatGPT app or power down your computer.

According to OpenAI, an additional review model checks the sign-in request and credential destination for signs of phishing or deception. ChatGPT Work then pauses while the user signs in. Credentials entered through its secure sign-in form go directly to the cloud browser and are not visible to the model. After the user authenticates, ChatGPT resumes its work.

OpenAI also explains that its cloud-based browser doesn’t store your username and password. Instead, it saves cookies that allow you to return to a previously authenticated session. If you don’t want to remain logged in, ChatGPT’s cloud browser settings allow you to clear browser data for individual websites or all sites.

Similar to other features in ChatGPT and Codex, users have choices when it comes to which sites ChatGPT Work can access. “Always ask” is the default, requiring the agent to check with the user before using a website, but the permission level can also be set to “Auto approve” after ChatGPT checks a site for relevancy and risk or “Always allow,” which OpenAI discourages. Individual websites can also be allowed or blocked. These settings control website access, but consequential actions require separate confirmation.

I gave ChatGPT’s browser use a try and the results were mixed. I wasn’t able to get the feature to work at all using ChatGPT Work in Safari on my Mac. Some websites had security measures in place that prevented me from logging in. Other times, the cloud browser asked me to take over manually, but I was unable to do so because the UI was frozen or login panels didn’t appear.

I had better luck using my iPhone. On one site with a simple username and password system, a login sheet appeared. I entered my credentials, was logged in, and the agent navigated the site to answer my queries. On Apple’s affiliate link dashboard website, I had to take over the browser interaction manually to satisfy a CAPTCHA, which worked after several challenges. Once logged in, the agent pulled and analyzed the data I requested. Also, after I’d signed in to both of those sites on my iPhone, I remained logged in to ChatGPT’s cloud browser, which meant I could also use them from my Mac.

In its current form, the idea of having ChatGPT Work browse signed-in websites on your behalf is better than its implementation. If you can get logged in, having an agent collect and analyze things like analytics data is fantastic. However, getting past the initial login screen is still too frustrating. That said, I’ll be keeping a close eye on the feature, which is available on eligible plans depending on rollout and workspace settings, for future use collecting and analyzing data that would otherwise require a lot of clicking around.

Learn how to automatically group open Safari tabs in relevant topics to streamline multi-tab browsing in iOS 27, iPadOS 27, and macOS 27.

Nem sempre é fácil manter a produtividade em alta quando as distrações estão a apenas um clique de distância, sejam notificações, redes sociais ou aqueles sites que acaba por visitar quase sem pensar. Mas e se pudesse contar com uma ajuda extra para se manter focado?

The post Quer passar menos tempo nas redes sociais? Squishy ajuda a reduzir as distrações online com uma mascote virtual appeared first on Tek Notícias.

File Browser encerra manutenção e libera última versão. Saiba riscos e alternativas para este gerenciador self-hosted.

O post File Browser, popular gerenciador de arquivos self-hosted, anuncia fim da manutenção apareceu primeiro em Blog do Edivaldo - Informações e Notícias sobre Linux.

James Sun (via Tim Hardwick):

Lastly, with all these updates, we are going to be sunsetting Atlas.

All these capabilities were built on what we learned from Atlas users who took a leap of faith on a new browser.

You taught us how agents can help make browsing and doing work on the open web better, and we are applying these learnings to these new products.

Zac Hall:

With the new ChatGPT desktop app, OpenAI now has a desktop app with robust browser capabilities. ChatGPT (and Codex before it) also supports a Chrome desktop browser plugin. This lets Chrome users benefit from ChatGPT integration without completely switching browsers.

Kyle Hughes:

Anthropic and OpenAI have legacy software media in the blender because they are playing a new game. They are legitimately racing to build God. The products they release are one-off fundraising vehicles to buoy the next training run. They are not trying to build long-term consumer goodwill.

Previously:

• ChatGPT Work and ChatGPT Classic
• Codex for Almost Everything
• Discontinuing Sora
• Codex App
• ChatGPT Atlas
• AI in Chrome, Neon, and Dia

Rizki Kelimutu:

Firefox is evolving with a refreshed design that makes the browser feel more modern, approachable, and consistent across desktop and mobile. The refresh also extends to Firefox’s voice and writing style, making product experience feel more human, direct, and unmistakably Firefox.

Via Jeff Johnson:

Nothing says “consistent” like making your large-screen keyboard & mouse UI exactly like your tiny touchscreen UI.

And nothing says “more human” like a manufactured voice and writing style.

rjacob:

Internally, we’ve been calling this work Project Nova, and today we’re excited to share a deeper look at what we’ve been building and where we’re heading next.

The goal of this work is to create a more cohesive foundation for Firefox: making the browser feel cleaner, warmer, faster, and more adaptable.

Some of the areas we’re working on include:

• Simpler navigation and a redesigned Settings experience
• Easier access to features like tab groups, split view, and vertical tabs
• The return of Compact Mode
• Refreshed visual updates across tabs, icons, spacing, and browser surfaces
• More customization options, including new themes and wallpapers

Previously:

• New Mozilla CEO
• Mozilla Changes Firefox Terms of Use
• Firefox at 20
• The Negative Impact of Mobile-First Web Design on Desktop

Update (2026-07-28): athomas (via Thomas Clement):

Starting today, you can try out the next design evolution of Firefox in Nightly.

It’s still Firefox, now with a more cohesive look and feel across tabs, menus, panels, and other browser surfaces. You’ll notice softer tab shapes, a warmer color palette, updated icons, and – after hearing from many of you – the return of Compact Mode and new theme options to make Firefox your own.

Still no AppleScript support.

Update (2026-08-04): Marcin Wichary:

Contra the previous post, just spotted this “Same settings, new look!” callout in Firefox, on a page I have never visited before, talking about a feature I have never used[…]

Saron Yitbarek, writing on the WebKit blog:

In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more powerful. We know agents are increasingly integral to the coding process and the Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window.

Any MCP-compatible client can connect to the Safari MCP server. By connecting your agent to a Safari browser window, your agent can emulate what your users experience, giving it the information it needs to debug more autonomously, like access to the DOM, network requests, screenshots, and console output.

Importantly:

The Safari MCP server runs entirely on your local machine and makes no network calls of its own. It also does not have access to your personal information in Safari (e.g. AutoFill or other browser activity). When it captures page content, screenshots, or console logs, that data goes directly to the agent you’re running — not to Apple. What happens to that data from there depends on the agent and model you’re using. As with any agent you give access to your browser, only use ones you trust.

For the past few months, I’ve been using Google Chrome on my MacBook Pro and Mac Studio not because I like the browser (in fact, I really dislike Chrome’s text rendering and UI), but simply because it was the best option for agents. In Codex specifically, between Playwright, Chrome Dev Tools, and OpenAI’s own Chrome extension, I could kick off research tasks (such as vacation planning and booking a hotel) that involved a browser directly from my iPhone, letting Codex drive the research on my remote Mac.

Now, thanks to Safari’s new MCP server, I no longer have to use Chrome on desktop and can return to a unified browser setup across all my devices. Even better: it actually looks like Apple shipped the most ergonomic browser MCP for agents to date. The MCP server has dedicated tools for page extraction (including getting webpages as Markdown, based on WebKit’s own conversion pipeline), evaluating JavaScript, DOM interactions (clicking, scrolling, resizing the viewport for mobile screens, etc.), taking screenshots, and more. I set this up immediately in Codex, and I also asked Codex about comparing Safari’s MCP to its own Chrome extension and the older Playwright. The verdict: although Chrome has a richer API with Chrome Dev Tools when it comes to network requests, Codex actually preferred Apple’s leaner, more direct approach for letting an agent drive and debug a browser.

I’m really happy to see folks at Apple embrace agentic tools: between the new MCP capabilities of Xcode and now this, it looks like Apple’s software (on the Mac, of course) is becoming more and more approachable by people who are working in new ways thanks to agents. Whether you’re a web developer or tinkerer, I highly recommend checking out what Apple has released in Safari Technology Preview. More of this, please.

Unlike a few years ago, modern browsers now arrive with stronger privacy controls. The following are some examples

Está a meio de uma tarefa no computador, mas não quer perder um vídeo do YouTube? A boa notícia é que não precisa de escolher. Os principais browsers já dispõem de uma funcionalidade integrada que abre uma janela flutuante para reproduzir vídeos do YouTube, enquanto trabalha noutras aplicações.

The post Quer ver um vídeo do YouTube enquanto trabalha no PC? Descubra como ativar a janela flutuante no seu browser appeared first on Tek Notícias.

Uma publicação no Threads juntou mais de 1.700 respostas com os atalhos de teclado favoritos da internet. Recolhemos os mais surpreendentes, e há boas hipóteses de ainda não conhecer alguns dos atalhos sugeridos.

The post 7 atalhos de teclado para o PC que ajudam a poupar tempo e a tirar mais partido do Windows appeared first on Tek Notícias.

Concebida para quem está a aprender novas línguas, a Vocabi é uma extensão para o browser que permite traduzir e guardar palavras enquanto navega na Internet, sendo possível revê-las mais tarde para que não desapareçam da sua memória.

The post Aprenda novas línguas enquanto navega online. Vocabi ajuda a memorizar as palavras que encontra appeared first on Tek Notícias.

A Breathhh é uma extensão para o browser com ferramentas para quem se preocupa com o bem-estar e, além de sugerir pausas ao longo do dia, conta com exercícios práticos de respiração e alongamentos, bem como ferramentas de produtividade.

The post Passa horas no computador? Breathhh ajuda a fazer pausas para respirar e alongar ao longo do dia appeared first on Tek Notícias.