Mike Brummett

Today we're announcing the all new @cloudflare/actors library to help make developing with Durable Objects easier than ever before. Powerful feature defaults, improved interfaces, and a new default export handler. So what all can it do today? - Get current instance by name -…

So stoked for Cloudflare's take on Containers! This is absolutely massive for devs building on workers. Shout out to @MikeNomitch_CF & team @CloudflareDev for shipping such a cool product! youtu.be/zUQM-bbIbUg

we've shipped taskmaster v0.21 🚀 → @kirodotdev @zeddotdev @OpenCode_AI @AmpCode → new taskmaster docs site → full provider integration + Kimi K2 via @GroqInc → better task update validations → @claude_code slash commands + many fixes follow + retweet + bookmark 👀👇

I'm joining Cursor to teach the future of coding! There are millions of developers learning how to use AI and they need pragmatic advice: 1. We need to teach new developers strong foundations, so they know what to learn, and how to solve issues when debugging. 2. We need to…

What if your React components were multiplayer out of the box? No messing around with WebSockets, no client side state tracking, use your Actor as a component and you got multiplayer real-time UIs. Coming soon to a @Cloudflare react framework near you....

Now that’s an ideal worthy of Aaron Swartz

Shoutout to Groq for 4x higher throughput on Kimi K2!

Windsurf - TL;DR Founders ➡️ Google Deepmind Researchers (core) ➡️ Google Deepmind Windsurf Team & IDE ➡️ Cognition Labs

Kimi K2’s pseudo-MIT license… not great. But a SOTA non-reasoning model: I can’t resist.

Thrilled to welcome @windsurf_ai founders @_mohansolo & Douglas Chen and some of the brilliant Windsurf eng team to @GoogleDeepMind. Excited to be working with them to turbocharge our Gemini efforts on coding agents, tool use and much more. Great to have you on board!

We ran a randomized controlled trial to see how much AI coding tools speed up experienced open-source developers. The results surprised us: Developers thought they were 20% faster with AI tools, but they were actually 19% slower when they had access to AI than when they didn't.

Sidebar is here (Sound on 🔊)

‼️Sentence Transformers v5.0 is out! The biggest update yet introduces Sparse Embedding models, encode methods improvements, Router module for asymmetric models & much more. Sparse + Dense = 🔥 hybrid search performance! Details in 🧵

icymi, openai also open sourced how their deep research prompt rewriter works + the full prompts today you can now build your own deep research agent - with full o3/o4-mini deep research quality - in 20LOC if you're a fan of Claude Research they ALSO dropped how to add…

And instead of polling, webhooks now let you receive notifications for certain API events—such as completed responses, fine-tuning jobs, and batch jobs. We recommend using webhooks for long-horizon tasks (like deep research!) to improve reliability. platform.openai.com/docs/guides/we…

Lovely hack to pay less to OpenAI when transcribing. Just speed up the audio you send to them.

I reverse engineered @cluely – and their desktop source code exposes their entire system prompts and models used. What's inside? 🧵

Announcing @webtui v0.1.2 - Landing page redesign - Small tweaks and improvements to components and documentation - 4 PRs and 5 issues closed webtui.ironclad.sh

* 25 months into 6 months away from AI stealing your jobs * month 1 of 24 months away from from AI stealing your editor

We got three words for you: zero egress fees! We triple checked the docs to make sure we read it correctly, but the new R2 data catalogue offering from @Cloudflare gives you Apache Iceberg with *zero egrees fees*. It even integrates directly with marimo! youtu.be/y_LAbR-fvKA