Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
US construction productivity fell from 1970 to 2020 while the rest of the economy got more productive, and a 1-year-old startup called Unlim...
It is wild to line up the original campus, the double-X buildings, then 16-18, through the campus expansion, then redwest, then ultimately S...
The push to become an "AI-first" organization shouldn't mean compromising on security. Yet, for many, the trade-off feels inevitable. It’s t...
Sydney Sweeney reveals in an interview that she doesn’t care about the PHP vulnerability because she moved everything to Rust in 2024. “The...
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent ...
Using a single Nano Banana image and Blender MCP, Gemini 4 Argon built a 3D Gothic cathedral in @Antigravity. It iterates on the geometry, ...
this Austin startup (founded by an ex-SpaceX engineer) just figured out how to build your house for HALF the cost when Elon talks about abu...
I think I'm addicted to getting agents to build state machines Every time I see an agent has built a state machine (or even just a reducer)...
You need to have a trust system outside of the model providers that you can rely on. “The models are becoming more and more capable. One of...
Recursive CEO @RichardSocher explains why the biggest breakthrough in the Transformer paper wasn't inventing attention: It was eliminating ...
it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9...
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with...
Fortunately our future models will be much better at code deletion and simplification. Just in time
Neil Movva (@neilmovva) started his career at Nvidia, working on GPUs and kernels, and has an unusually deep understanding of inference, fro...
// MemoryTax: The Bitter Lesson of Agent Memory // Great insights for agent builders; bookmark it. As models increase in capability, they ...
Highly recommended read from Google DeepMind and colleagues. There is a lot of interest in self-evolving agents, but they're hard to get ri...
mattpocock/skills prompt of the day: /codebase-design Take a look in the repo for shallow modules, applying the deletion test and look for ...
This is how I scale agent swarms: a graph of agents that can spawn new agents and communicate with each other Below is what this looks like...
"Depth Memory" Attention Residuals stores earlier Transformer layer outputs for retrieval but this memory grows with depth. Linear Depth M...
Why horizontal tabs? Vertical is navigation. Organizational. Hierarchical. A tree. It's "history". You don't need it on screen all the tim...