matt bean retweetledi
matt bean
166 posts
matt bean
@mattbean
ai stuff, built https://t.co/h6skRA9JQ2
Katılım Şubat 2025
114 Takip Edilen23 Takipçiler
matt bean retweetledi
matt bean retweetledi
Chrome 146 includes an early preview of WebMCP, accessible via a flag, that lets AI agents query and execute services without browsing the web app like a user.
Services can be declared through an imperative navigator.modelContext API or declaratively through a form.
English
matt bean retweetledi
New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel.
Here's what it taught us about the future of autonomous software development.
Read more: anthropic.com/engineering/bu…
English
matt bean retweetledi
Granola has an MCP! It works with ChatGPT / Claude / whatever tool you want. Thanks for being patient 🙏🏼
(Hope everyone enjoys this change even more than the one we did on Monday 😅)
Granola@meetgranola
Hello MCP.
English
matt bean retweetledi
I didn't see a --dangerously-skip-permissions flag for Claude Chrome... so I made one.
English
matt bean retweetledi
we built our own background coding agent at ramp: it's called inspect
its powered by @opencode and @modal, and works with all the frontier models
it has a cloud hosted version of vscode, chromium, and terminal. has all the tooling and skills a ramp engineer would have, and is blazing fast
we're basically giving every ramp builder infinite laptops so they can yolo their most ambitious ideas at zero marginal cost with the biggest models we can find
@zachbruggeman @monasticpanic @nzgb
English
matt bean retweetledi
Introducing ChatGPT Health — a dedicated space for health conversations in ChatGPT. You can securely connect medical records and wellness apps so responses are grounded in your own health information.
Designed to help you navigate medical care, not replace it.
Join the waitlist to get early access.
openai.com/index/introduc…
English
matt bean retweetledi
matt bean retweetledi
matt bean retweetledi
matt bean retweetledi
Today, we are introducing Trinity, the start of an open-weight MoE family that businesses and developers can own.
Trinity-Mini (26B-A3B)
Trinity-Nano-Preview (6B-A1B)
Available Today on Huggingface.
English
@amorriscode @_catwu This is awesome! Are Anthropic Console accounts able to auth into this? Wasn’t seeing the login being picked up from the terminal.
English
Pretty excited to make it easier for folks to multi-Claude, use Claude without the terminal, and even kick off remote sessions without leaving the app!
Claude@claudeai
Claude Code is now available in our desktop app. Run multiple sessions in parallel: code, research, and update work all at once. And Plan Mode gets an upgrade with Opus 4.5—Claude asks clarifying questions upfront, then works autonomously.
English
Congrats guys! Magic Patterns = 🐐
Alex Danilowicz@alexdanilowicz
Announcing Magic Patterns 2.0 and our $6M Series A led by @Standard_Cap Since our first launch in 2023, we’ve grown profitably, hit $1M ARR with no employees, and quietly built an AI design tool loved by PMs, designers, and website builders. 1,500+ product teams use us to go from idea to production every day, prompting features to life with their existing styles. Free to try with a new brand look.
English
matt bean retweetledi
Multi tool use agents fail because they delegate routing to base models that can't learn.
My new post uses @dspyoss and MCP to orchestrate specialized agents, do step wise planning, and context threading.
We build a toy @Shopify Scout via @dspyoss to illustrate.
(Link below)
tobi lutke@tobi
The AI memo has been extremely successful inside of Shopify. People all over the company have built remarkable things in response to it. One of my favorite is Scout, built by a small team outside of R&D! Scout has indexed hundreds of millions of merchant feedback items from Social posts, video feedback, and all our customer support channels. Then it makes it available (via MCP) in our internal librechat tool for deep research. I use it all the time. Asked the team to do a demo:
English
This is hugely exciting for both users and merchants!
The need to optimize for LLM discovery only continues to grow.
OpenAI Developers@OpenAIDevs
We’re introducing the Agentic Commerce Protocol, an open standard co-developed with @Stripe that enables programmatic commerce flows between users, AI agents, and businesses.
English
matt bean retweetledi
This quote from Teller (of P&T) lives in my head rent-free:
"Sometimes, magic is just someone spending more time on something than anyone else might reasonably expect."
Gergely Orosz@GergelyOrosz
Linear has a 30-minute weekly meeting called "Quality Wednesdays." I sat through one and WOW Devs show a quality or perf-related fix they did last week. It can be big, or small. We went through 17 issues, from massive backend performance wins, to this tiny one. Can you see it?
English
matt bean retweetledi
Bugs don’t age well.
If you’re going to fix them eventually, it’s always better to fix them now.
That’s the simple idea behind our zero-bugs policy.
→ linear.app/now/zero-bugs-…
English
matt bean retweetledi
design is a moat
ramp vs brex
notion vs obsidian
macos vs windows
the winner always nails human-computer interaction
English