At @ThriveHoldings, we built a product with @OpenAI to automate tax prep for the 30+ accounting firms we own across the country.
This season, it processed 7k+ returns. But what I think is more interesting is that the product meaningfully self-improved as accountants used it.
New preprint with @J_Pablo_Bonilla! We built a neural network that decodes quantum errors — and discovered that fault-tolerant quantum computing might need far fewer qubits than we thought. 📄
Paper: https://t.co/hH1olBtR4I
Website: https://t.co/h3SeBuQSPI
1/ I’m excited to share recent work on a scalable and generalizable causal discovery framework from @mingZedh, me and @sophokevl, supervised by @elhamazizi. Open the thread 🧵 for a brief tweetorial of our method. arXiv link: https://t.co/xkSZEsSOal.
We rebuilt Cascade from the ground up. Think @figma meets @conductor_build: a visual canvas for coding.
Preview your latest commit → copy and paste to spin up new worktrees → edit visually → commit.
We still have prior commits, but now as a side panel where users can drag and prior version to compare visually on the canvas.
The core of Cascade is now freeform visual exploration with coding agents.
Reliving my recent japan trip through MinecraftLM (https://t.co/yKUiF2U1Fg), our world building agent. Some examples in 🧵
Prompt: "A traditional Japanese onsen as an isometric diorama. A small wooden bathhouse building with tiled roof, noren curtains at the entrance, and shoe lockers visible inside. Behind it, an outdoor hot spring pool surrounded by natural rocks, steam rising from the water. Wooden deck connecting the bathhouse to the pool with a small changing area, towel racks, and wooden buckets. Bamboo fence enclosing the space, stone lanterns along a path, maple trees with red leaves overhead. Snow on the ground and rocks for the classic winter onsen look. The bathhouse glows warm from inside, contrasting with the cold outside."
gemini 3 flash is the most impressive model I've seen in a while
not only is it super fast (great for prototyping) AND has frontier coding abilities, it has superior spatial reasoning compared to other frontier models. we tested it in our minecraft agent harness:
(1/3)
1/ All the structures you see here were generated by an LLM from a single text prompt (notably, Gemini-3 👀).
Over the past week, we’ve been researching the spatial understanding capabilities of agents and how they can build large scale, playable environments (particularly Minecraft to start). We found they do extremely well despite what many think.
We're open-sourcing our work for others to build on top of https://t.co/yKUiF2TtPI
Prototyping has never been this fun.
Spin up multiple explorations from a single prompt, each with a live preview and watch claude code bring them to life.
Agents don't just do tasks. They help you move across timelines.
Excited to share our take on a new kind of environment that enables creativity for web development.
People have been asking a lot about Cascade recently so we wanted to share more about its capabilities and why we've built it.
We're thinking about Cascade as a new paradigm. Rather than building another traditional IDE, we've built a "Creative Development Environment".
The last few weeks of nights and weekends have been a labor of love. v0.3 of @withcascade is the closest we've come to a tool that feels truly explorative.
Create n branches → visualize changes → merge an exploration back in → repeat.
More people want to vibe-code, especially designers. We’re making it easier to explore ideas and iterations. Try MANY things and select what you want.
We’re launching Cascade v0.3. We redesigned the canvas for more focused UI exploration.