The MCP Events extension is now finalised in beta. This means it is ready for clients and servers to adopt and provide feedback, so that we can fix any spec issues and get it stabilised.
https://t.co/NmNbnhmIuv
Thanks to all the working group members, maintainers, and early implementers for getting this over the line. Very excited to see what people build with it :-)
(and here's a cheesy video that on one asked for)
There's never been a better time to be delusionally ambitious than today. I talk about Omarchy, agents, 90s demo culture, and so much more with the gang from @a16z. https://t.co/hsIBvgyJBz
OK, this is IMPORTANT to understand for any and all software engineers:
Inference engineering 101: reading from the KV cache is very cheap; speculative decoding makes sessions more efficient. Coding use cases make HEAVY use of both.
THIS is why inference is SUPER profitable!!
1 million views. Our fastest talk to get there.
@poteto of @spacexai on the engineering behind 11,000 production PRs in one month.
All Code Is Slop (Except Mine).
Watch: https://t.co/iYjSpi3Xwg
I regret to inform you that you need to do uncomfortable things sooner. The delayed conversation gets harder. The ignored problem expands. The minor repair becomes a major one. Peace isn’t found through avoidance. It’s earned through early action. The recipe for a good life.
Yes, this is what I’m talking about.
Having the ability to test without the cost, allows you to build confidence into your SDLC without the concerns of blowing out costs. Those small costs can add up real quick.
New emulator: @𝚎𝚖𝚞𝚕𝚊𝚝𝚘𝚛𝚜/𝚊𝚒
Test AI without paying for AI
Deterministic but also realistic: streaming, tool calls, latency, errors, varied responses
Built for CI, local dev and sandboxes
Introducing Warp Learn: A free, hands-on course on how to build a software factory of your own, taught by @BHolmesDev
Start with the fundamentals, write your first automation loop, and build up to a full software factory with specs, risk assessment, and end-to-end verification.
Today we're releasing a new streaming markdown parser called Words. It's built for any markdown, but it's especially useful for streamed llm responses.
@pierre/words is up to 2× faster than md4x, and 20× faster than streamdown. It supports DOM, HTML, and ANSI rendering. It has built in syntax highlighting and renders mermaid charts.
Check it out at https://t.co/nSN3H9Xglh
Brilliant article that’s a must read for all. Ben has nailed this 👌
I still do wonder if product and factory engineering will be a simple function of a set of much wider roles longer term.
Software engineering is becoming factory engineering.
If you're new to that term, let's discuss:
- What problems a "factory engineer" tries to solve
- What a software factory loop includes
- How to use metrics to measure and improve your agent's quality https://t.co/6W9A6NBMtT
Cloudflare just dropped Clairic on @huggingface ☁️✏️🧾
Clairic goes beyond decision models: it actually extracts information on a single forward pass, unlocking ultra fast system one decision-making process
▶️ https://t.co/4ugt9mqIdz
AI is everywhere. When and how you use it should always be your choice.
Starting today, you can switch generative AI features on or off and choose to limit AI-generated content in your Canva Settings. Let AI do some of the heavy lifting, handcraft every detail yourself, or do a bit of both.
Your creativity, your call.
#Canva #CanvaAI
HOLY F*CK. a user reports a bug. by 3 AM Lauren Tan's agents have fixed it and shipped it. nobody on the team even noticed
SpaceXAI engineer:
"most people still test every line their agent writes by hand. that's exactly why they can't ship 4,000 updates a month"
in a 37-minute talk she shows how she taught her agents to run their own code like a real user and check their own work
Agent Writes It - Runs It Like A User - Catches Its Own Bugs - Fixes Them - Merges It Itself
better than any $5,000 coding bootcamp
skip netflix, watch it tonight, then tell me - who tests your agent's code right now?
introducing Gemini 4 Neon: frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows
priced at $3 per million input tokens and $15 per million output tokens, with a 1 million-token context window
try it today via the Gemini API and in AI Studio https://t.co/dp8Frcr6y8
💥 We have a new WebMCP polyfill!
If you're exposing webMCP tools, this is going to be a useful part of your workflow. And if you want to experiment, it's a good way to try and give feedback on the spec.
npm install @w3c/webmcp-polyfill
It ships TypeScript types based on the latest webmcp-types. And has zero dependencies: It adds no runtime JavaScript dependencies to your app!
posted this into our Rex discord today... the new `𝚛𝚎𝚡.𝚞𝚒` primitives provides a new set of simple but powerful methods to build interactive scripts within Rex that require user interaction.
Now you can build the workflow of your dreams, that little action you always wanted or just a pizza topping selector.
I wrote some docs up that go into detail about how this feature works https://t.co/4UXo1zSrBt
In "stuff that @Steve_Yegge said 9 months ago, when few believed it would be true, but now it's more visible"
The "vampiric" effect of running AI agents, and how it drains people
I don't know how he does it, but he rarely misses
Full: https://t.co/fYR25YHscJ