标签：#t

Outro dia, vi nos stories do Instagram uma amiga pesquisadora contando que estava usando o Claude para ressuscitar uma plataforma criada anos antes por parceiros. Ela não é da área de desenvolvimento de software. O projeto estava praticamente parado. Não havia mais recurso para manter tudo como estava. Com a ajuda da IA generativa, ela conseguiu migrar serviços, reduzir custo, melhorar performance, redesenhar partes da experiência e voltar a implementar coisas que estavam no backlog havia muito tempo. Achei aquilo inspirador! Mas também um pouco assustador. Não por ela estar usando IA generativa. Pelo contrário: acho fascinante que pessoas que não programam profissionalmente estejam conseguindo recuperar autonomia sobre projetos que antes ficavam dependentes de verba, disponibilidade de terceiros ou uma fila infinita de prioridades. O ponto que me acendeu uma luz amarela foi outro: em certo momento da conversa ela comentou que o projeto tinha dados de usuários e pagamentos via Stripe . Antes de seguir, uma ressalva: eu não gosto muito do termo "vibe coding" . Vou usar o termo aqui porque ele pegou, e porque todo mundo entende mais ou menos o que ele quer dizer: criar software com muita ajuda de IA generativa, muitas vezes sem dominar profundamente a linguagem, o framework ou a arquitetura por trás do projeto. Mas o termo me incomoda porque parece diminuir a responsabilidade envolvida. Se você está criando código, alterando código e colocando esse código no ar, você é sim uma pessoa desenvolvedora. Talvez iniciante. Talvez insegura. Talvez dependente demais da IA generativa. Talvez uma pessoa desenvolvedora ruim ou medíocre, como todos nós somos em algum recorte. Mas é. E isso traz responsabilidades. Vibe coding em uma página pessoal é uma coisa. Vibe coding em um sistema com login, dados pessoais, áreas administrativas, arquivos, integrações externas ou pagamento é outra. E aqui existe uma tensão interessante. Eu trabalho com desenvolvimento de software há bastante

The promise of agentic AI coding was a tireless partner, an assistant that could take a feature request and run with it while we focused on the hard problems. The reality, for most professional engineering teams, has been different. The reality is a brilliant but distractible intern you have to constantly supervise. The reality is spending 20 minutes writing the "perfect prompt," only for the AI to ignore a critical constraint, use a deprecated pattern from your codebase, and confidently break three other features. The reality is the "babysitting tax." It's the cognitive overhead of constantly reviewing, reverting, and re-explaining. And it's negating the incredible potential of these tools. At BrainGrid, we believe the problem isn't the agent—it's the plan. Or the lack thereof. In our rush to generate code, we've skipped the most critical step: creating a shared, deep, and unambiguous understanding of what we're actually building. "Vibe coding" doesn't work in a multi-tenant system where permissions are non-negotiable, or at least not with peace of mind. It doesn't work in a complex fintech application where money is on the line. And it certainly doesn't work in a four-year-old codebase with layers of tech debt and unwritten rules. The bottleneck in software development is no longer just the speed of writing code. The bottleneck has shifted to the speed of creating a reliable plan. BrainGrid is the AI-powered planning platform built to solve this new bottleneck. It's designed to provide the structure and guidance—the "babysitting plan"—that turns powerful but unreliable coding agents into predictable and effective teammates. Here's how: We Give the Agent a Map BrainGrid starts by deeply analyzing your entire codebase—its architecture, data models, and dependencies. It provides the persistent context that agents desperately need but currently lack. We Help You Define the Destination Our requirements agent acts like a seasoned tech lead, asking you and your team clar

You've built the agent, the reply loop works, the demo lands — and then someone asks the question you didn't budget time for: "so what address does it send from?" Suddenly you're staring at noreply-svc-prod2@yourcompany.com realizing that the first thing every recipient sees isn't your prompt engineering. It's the From line. An agent's email address is an interface. Humans parse it before the subject, mail servers judge it before the body, and spam filters score it before any human sees it at all. Once your agent has a real mailbox — which is what Nylas Agent Accounts (currently in beta) provide — address design becomes a product decision with three layers: the local part, the domain, and the disclosure question. The local part: role beats persona beats hash Take three candidate addresses for the same scheduling agent: scheduling@ — a role. Tells recipients what the mailbox does and implies that emailing it is how you use the service. jane.ai@ — a persona. Friendlier in a sidebar avatar, but it invites recipients to treat the sender as a colleague, with all the expectations that carries. bot-7f3a@ — an artifact. Screams "auto-generated," gets mentally filed next to spam, and gives a human nothing to anchor on. The docs consistently model the first pattern — sales-agent@ , support@ , scheduling@ appear throughout the Agent Accounts overview — and I think that's right for a reason deeper than convention. A role address makes an honest promise about capability: scheduling@ claims it can schedule, nothing more. A persona address makes an implicit promise of general competence that current agents can't keep. When jane.ai@ fails to understand a simple request, it reads as a person being obtuse; when scheduling@ fails, it reads as a tool hitting its limits. Same failure, different trust damage. The overview's framing is worth internalizing: an agent identity should be like any other user in your organization — reachable, persistent, accountable. Address design is how that

Day 1, 4:02 p.m.: a customer asks your agent a billing question and gets an answer. Day 6, 9:30 a.m.: they reply "actually, that didn't work." If your agent lives in a chat widget, that second message starts from zero — the session died with the tab, the context is gone, and the customer gets to repeat themselves. If your agent lives in a mailbox, the reply arrives inside the conversation , with the full history attached by the protocol itself. That's the argument in one before/after: chat sessions evaporate; email threads persist. And for agents that work across days rather than minutes, the thread is the most underrated memory substrate available. The protocol already built your memory layer Email threading runs on three headers, as the threading docs lay out. Every message carries a globally unique Message-ID . A reply adds In-Reply-To (the ID it's answering) and References (the full chain of IDs, oldest to newest). By the time a thread is five messages deep, References holds five Message-IDs in order — a complete, tamper-evident record of the conversation's shape, maintained by every mail client on earth. Compare that to what we hand-roll for chatbots: session stores, conversation tables, context windows we serialize and rehydrate. Email gives you the equivalent for free, federated across organizations, and — this is the part I find most compelling — human-auditable . Anyone with mailbox access can read exactly what the agent's memory contains, because the memory is the correspondence itself. No vector store inspection tools required. With Nylas Agent Accounts (in beta), the agent owns the mailbox where this accrues, and you never parse headers by hand. The Threads API groups messages by their header chain; each thread object gives you ordered message_ids , participants , and activity timestamps. When a reply fires message.created , the payload includes a thread_id — fetch the thread, walk its messages, and the agent has its full conversational past before decid

A human assistant borrows the boss's calendar; a scheduling bot owns its own. That one difference dissolves most of what makes calendar automation miserable. The borrowed-calendar model is how nearly every scheduling tool works today: connect to a person's Google or Microsoft account via OAuth, request calendar scopes, and act on their behalf. It works, but the seams show everywhere. The human's calendar fills with bookings the bot manages. Delegation permissions vary by provider and admin policy. Tokens expire when the person changes their password or leaves the company. And the bot has no address of its own — every invite, every confirmation email, appears to come from a person who didn't write it. Nylas Agent Accounts (currently in beta) invert this. Each account is a real mailbox and a real calendar , provisioned automatically, owned by your application. From a participant's perspective there's nothing special about it — it's just another attendee on the invite. What "owning availability" actually changes When the bot's calendar is its own, availability stops being a permissions question and becomes a query. The agent calls the free/busy endpoint against its own primary calendar, gets back busy blocks for a time window, and proposes open slots. No delegation, no scopes negotiation, no "the admin needs to approve calendar sharing for service accounts." The scheduling-agent tutorial wires the whole loop: a meeting request lands at scheduling@agents.yourcompany.com , a message.created webhook fires, an LLM parses duration and timezone, the agent checks its own free/busy and replies with 3 candidate slots. When the human picks one, the agent creates the event: curl --request POST \ --url "https://api.us.nylas.com/v3/grants/<GRANT_ID>/events?calendar_id=primary&notify_participants=true" \ --header "Authorization: Bearer <NYLAS_API_KEY>" \ --header "Content-Type: application/json" \ --data '{ "title": "Product demo", "when": { "start_time": 1744387200, "end_time": 174

When was the last time you deleted an email account on purpose? For most teams the answer is never, and that tells you something. We treat mailboxes the way we treated servers in 2008: hand-built, carefully named, kept alive indefinitely because recreating one is painful. They're pets. Meanwhile every other piece of our infrastructure — compute, queues, databases — became cattle: numbered, provisioned by code, destroyed without sentiment when the job ends. Email is finally catching up. With Nylas Agent Accounts (in beta), a mailbox is created with one call and destroyed with another, and that symmetry is the whole point. The full lifecycle in two commands Provisioning, from the CLI: nylas agent account create signup-agent@agents.yourdomain.com Or via POST /v3/connect/custom with "provider": "nylas" — no OAuth, no refresh token, just an address on a domain you've registered. Teardown is equally unceremonious: nylas agent account delete signup-agent@agents.yourdomain.com --yes (The API equivalent is a DELETE on the grant.) The signup automation recipe treats this as a loop: provision a fresh inbox, point a third-party signup form at it, catch the verification email through a message.created webhook, follow the confirmation link, delete the grant. No human inbox involved at any step, and nothing left behind. The middle of that loop is about twenty lines of webhook handler, and the recipe's version filters hard before acting — right grant, right sender, right URL shape: const { grant_id , id : messageId , from } = event . data . object ; if ( grant_id !== AGENT_GRANT_ID ) return ; const sender = from [ 0 ]?. email ?? "" ; if ( ! sender . endsWith ( " @saas-you-care-about.example.com " )) return ; const match = /https: \/\/ saas-you-care-about \. example \. com \/ confirm \? token= [^ " \s < ] +/ . exec ( message . body , ); if ( match ) await fetch ( match [ 0 ]); Nylas fires message.created within a second or two of mail arriving, so the whole signup round-trip typical

I have just finished writing API Artisan: A Guide to Building APIs with Laravel , and I am giving it away for free. Before you commit to 300-odd pages, let me give you the short version: the tips, patterns, and small decisions that separate an API that technically works from one that developers are genuinely happy to depend on. None of this needs more hardware, a different framework, or a bigger team. It needs you to point your attention at the right things. These are the ones I keep coming back to. Start by measuring the right thing Ask most teams how they know their API is good and you get a single question back: does it work? Can I hit this endpoint and get a response? That question is necessary, and it is nowhere near enough. The question I want you to ask instead is whether your API is liveable with. Can a developer read your docs, understand your auth model, make a successful request, and handle an error without contacting support, trawling a forum, or guessing what a status code is trying to tell them? The gap between "works" and "liveable with" never shows up in a sprint retro, but it shows up everywhere else: in support volume, in integration timelines that overrun, and in the quiet moment a developer decides to build around your API rather than with it. Everything else in the book hangs off one mindset shift: an API is a product. It has users. Treat it as an implementation detail and it will behave like one. It will change without warning when your internals change, and it will be inconsistent because different people wrote different parts on different days with different conventions. Write the contract before the code The natural way to build an endpoint is to write the handler, return some data, and document it afterwards if there is time. It feels efficient, and in the short term it is. The problem is what it produces: a contract that was never designed, only discovered. Let me show you the trap, because I have watched it catch good developers. You have

Every project I touch lately ends up needing the same awkward thing: a reliable way to pull the web into a script or an agent. Not a brittle scrape held together with CSS selectors and hope, but something that takes a URL and hands back clean, structured text I can actually pipe into the next step. I have built that wrapper more than once, and it is never as small as you think it will be. So when Mozilla dropped the tabstack CLI, a single Go binary that wraps the Tabstack AI API, I wanted to spend a proper afternoon with it. The pitch on the README is direct: every web interaction your agent or stack needs, from the terminal or a script. It turns any URL into clean Markdown or schema-shaped JSON, runs natural-language browser automation, and answers research questions with cited sources. The part that made me sit up is that the output is pretty in a terminal and pipeable into jq without a flag. That is a small detail, and it tells you the people who built it actually live on the command line. Let me walk you through it the way I poked at it myself. Getting it installed There is no runtime to install and nothing to bootstrap, because it ships as a single static binary built for macOS, Linux, and Windows. The quickest route is the install script: curl -fsSL https://tabstack.ai/install.sh | sh That fetches the right binary for your platform and puts it on your PATH , and you are ready to go. If you would rather not pipe a script into your shell, there are a couple of alternatives. With Go on your machine you can use: go install github.com/Mozilla-Ocho/tabstack-cli/cmd/tabstack@latest That drops the binary in $GOPATH/bin , which is usually ~/go/bin . If your shell cannot find tabstack afterwards, you almost certainly have not got that directory on your PATH : export PATH = " $HOME /go/bin: $PATH " And if you want to avoid Go entirely, there are pre-built binaries on the Releases page, or you can clone the repo and run make install-local , which builds it and copies it t

The email mailbox just became an API resource, and that matters far more than the setup time it saves. For most of software history, a real email address — one that sends, receives, and threads — was an artifact of IT process. Someone created it in an admin console, someone else configured the client, and your application got access through OAuth consent screens and refresh tokens borrowed from a human. Compare that to how you get a database, a queue, or a TLS cert today: one API call, one ID back, done. Nylas Agent Accounts (currently in beta) close that gap. The quickstart goes from API key to a sending-and-receiving mailbox in under 5 minutes, and the provisioning step is a single request: curl --request POST \ --url "https://api.us.nylas.com/v3/connect/custom" \ --header "Authorization: Bearer <NYLAS_API_KEY>" \ --header "Content-Type: application/json" \ --data '{ "provider": "nylas", "settings": { "email": "test@your-application.nylas.email" } }' No refresh token, no OAuth dance — unlike OAuth providers, the "nylas" provider needs only an email address on a registered domain. The response contains a grant_id , and that one ID drives everything else: messages, drafts, threads, folders, attachments, calendar, webhooks. There are actually three ways to create an account — this API call, the Dashboard, or a single CLI command ( nylas agent account create ) — but they all end at the same place: a live mailbox. Why 5 minutes is a threshold, not a convenience Provisioning time isn't a linear cost. There's a threshold below which a resource changes category — from "thing you request" to "thing your code creates." Virtual machines crossed it with cloud APIs and we got autoscaling. TLS certs crossed it with ACME and we got HTTPS-by-default. Mailboxes crossing it means email addresses stop being scarce, pre-planned identities and start being something a program allocates when it needs one. What does that look like in practice? System mailboxes without ceremony. A support

Snap CEO Evan Spiegel sat with us to discuss the Snap Specs, privacy, parental controls and more. Spoiler: He says "computing" a lot.

Move originally planned for Monday would have heavily increased power users' costs.

Git worktrees have been around since 2015, but it wasn't until recently they became popular. Learn what they are, how to use them, and why you might. The post What are git worktrees, and why should I use them? appeared first on The GitHub Blog .

Turn any HTML/CSS design into an editable InDesign file Discussion | Link

A collection of stories about how militaries are using AI models to make decisions. This subscriber-only eBook is a package of six stories that were originally published in MIT Technology Review between April 11, 2025, and April 21, 2026, and have been updated to reflect recent developments. by James O’Donnell Choose which file format to…

Father’s Day is nearly here. Hopefully, you already got a gift for dads you care about, but if not, here’s a quick, easy recommendation for anyone who enjoys a good comic strip. The Complete Calvin and Hobbes contains every one of Bill Watterson’s beloved strips made during the comic’s ten-year run from 1985 through 1995, […]

AI Drum Machine MPC in your browser Discussion | Link

By spring 2026, the division of labor between human engineers and AI had become precise enough to describe. Not speculate about. Describe. Delegate these 7 immediately: Boilerplate generation: CRUD scaffolding, config files, standard patterns. Near-human accuracy. Review required is a naming scan, not a logic audit. Test generation: 40-60% faster test development with no measurable decline in coverage quality, provided the tests are reviewed by someone who understands the domain. Documentation: 67% of companies rely on AI-assisted doc generation in 2026. The first draft is a solved problem. Your job is verifying and contextualizing. Code translation: Python to TypeScript. React to Vue. Framework migrations that once consumed sprint cycles now take hours. Routine bug fixing: Claude Code, Devin, BugBot can resolve 60% of reported bugs autonomously. Resolution time down 30-50%. Automated code review: First-pass filter before human review. Misses context issues. Doesn't replace human review. Eliminates noise so you focus on signal. Commit hygiene: Messages, PR summaries, changelog entries. Fully automatable. No meaningful error rate. Never delegate these 6: Architecture and system design: AI proposes. You decide. The tradeoffs require organizational context, team capability assessment, and long-horizon thinking no model possesses. Business context translation: The spec says "export to CSV." You ask: which users, under what conditions, with what compliance implications? AI cannot know the specification is wrong. You can. Security architecture: AI generates vulnerabilities as readily as it detects them. Adversarial thinking is not statistical. It is human. Long-horizon product thinking: What to build and why. Not how. Multi-stakeholder navigation: The politics, the relationships, the conversation with the PM that keeps the sprint on track. No model has stakes in the outcome. Agent orchestration: Designing, managing, and correcting the AI systems themselves. This is the ne

I built a tool called "kaggle-dingdong" that automatically fetches Kaggle competition information and sends notifications to Email, Slack, and Discord. It runs daily on a schedule via GitHub Actions, and you get notified whenever a new competition is published. https://github.com/asherish/kaggle-dingdong Why I Built This Checking the Kaggle competitions page every day is tedious. Featured competitions in particular have entry deadlines, so missing them means losing the opportunity. While RSS feeds and official notification features exist, I wanted notifications delivered directly to the channels I actually use (Discord and Slack), so I built my own. Tech Stack Python 3.13 uv — Package manager and build tool (by Astral) Kaggle Python SDK v2.0.0 — Fetching competition info GitHub Actions — Automated daily execution at 09:00 UTC pytest — Testing Three notification channels are supported: Channel Method Format Email SMTP HTML (card layout) Slack Incoming Webhook Block Kit Discord Webhook Rich Embed Architecture GitHub Actions (cron: daily at 09:00 UTC) ↓ Fetch competition list via Kaggle API ↓ Filter by conditions in config.json ↓ Compare with sent history to extract unnotified competitions ↓ Send notifications to configured channels ↓ Update sent history (max 200 entries) The project structure is as follows: kaggle-dingdong/ ├── src/kaggle_dingdong/ │ ├── __main__.py # Entry point │ ├── config.py # Configuration loading │ ├── competitions.py # Fetch & filter competitions from Kaggle API │ ├── email_sender.py # Email notifications │ ├── slack_sender.py # Slack notifications │ ├── discord_sender.py # Discord notifications │ └── history.py # Sent history management ├── tests/ # pytest tests ├── config.json # Filter configuration └── .github/workflows/ └── notify.yml # GitHub Actions workflow Implementation Highlights Fetching and Filtering Competitions The Kaggle SDK is used to fetch the competition list. In addition to the default sort order, it also fetches with recentl

Something feels different about security incidents lately. Breaches, leaks, account takeovers, phishing campaigns they're not new. But their frequency, sophistication, and scale seem to be growing at a pace that feels genuinely alarming. Instagram accounts hacked overnight. Corporate systems compromised in hours. Phishing emails that sound disturbingly human. As someone studying AI & Big Data, I can't help but ask: is AI responsible for this? And if so, how? I think the honest answer is: yes but in two very different ways. The two faces of AI in cybersecurity When we talk about AI and cyberattacks, most people imagine one scenario: hackers using AI to attack systems faster and smarter. That's real. But it's only half the picture. The other half is something we talk about far less: the vulnerabilities that come from integrating AI into systems in the first place. These are two very different problems. And conflating them leads to the wrong solutions. Problem 1: AI is expanding the attack surface Every time a platform integrates an AI feature, they're adding something new to their infrastructure. And new infrastructure means new potential vulnerabilities. AI systems require: Massive data pipelines more data flowing through more systems APIs connecting multiple services more endpoints that can be exploited Third-party models and tools more external dependencies, more trust relationships Real-time processing less time to detect anomalies before damage is done Many organizations are integrating AI features faster than their security teams can audit them. And the consequences are already visible. In June 2026 , hackers reportedly manipulated AI-powered support systems to gain unauthorized access to Instagram accounts. The attack didn't target traditional software vulnerabilities it targeted the AI system itself , exploiting the automated account recovery flow that Meta had built with AI. This is the new reality: attackers are no longer just targeting your code. They're ta

A capability-compiler meets ten deliberately-broken MCP servers. The honest scorecard: it cleanly stops one class, shrinks the blast radius on several, and is useless against another. Knowing which is which is the whole point. Disclosure: I'm the author of capgate , the Apache-2.0 sandbox compiler this post puts to the test. The DVMCP project and the other tools mentioned aren't mine; the manifests and compiled output are reproducible from the repo . The setup Damn Vulnerable MCP (DVMCP) is a teaching project: ten MCP servers, each built to demonstrate one attack — prompt injection, tool poisoning, excessive permission scope, token theft, command injection, and so on. It's the closest thing the ecosystem has to a shared adversarial fixture. capgate is a compile-time tool. You write a manifest declaring what an MCP server is allowed to do — fs:read:/workspace/** , net:connect:api.github.com:443 , nothing else — and it compiles that to a concrete sandbox policy ( docker run flags, bwrap argv, or an egress-proxy config). It does not run anything, watch traffic, or inspect the server's code. It turns a declared capability set into an enforced boundary. So this is a fair, falsifiable test: for each DVMCP challenge, I wrote the honest minimum manifest, compiled it, and asked one question — does the boundary capgate emits actually stop the attack? The answer is not "yes" across the board, and the cases where it's "no" are the interesting ones. The bullseye: Challenge 3 — Excessive Permission Scope The vulnerable tool advertises "read a file from the public directory" and then does this: @mcp.tool () def read_file ( filename : str ) -> str : # VULNERABILITY: doesn't restrict file access to the public directory if os . path . exists ( filename ): # any absolute path works with open ( filename , " r " ) as f : return f . read () The private directory next door holds employee_salaries.txt , acquisition_plans.txt , and system_credentials.txt (a live DB password and cloud API ke