With AI, you can just build the tools you want.
https://t.co/ehjWwiHMwi is my personal website editor made for my code-first design flow. This is app is fully made with AI.
If you’re interested in tailwind workflow, test it out on your laptop: https://t.co/fZ4VUhiGXs
The next AI driven design?
What probably happens next:
The sampling gets weirder and more specific. Not “Art Deco meets brutalism” (that’s already AI slop) but like, 1987 Finnish municipal signage meets Memphis Group meets Nigerian Afrobeat poster printing artifacts.
Gmail api is fun: time spent on company x meetings and emails? Fetch invoices and tag and route.
But google approval is another: CASA tiers, annual fees, 6 week approval…
It might be time to ditch gmail and build better email as db (think turso, direct mcp etc).
For years, Ive devoted myself to design precision and neo grotesque sans doctrine (Suisse btw). But the dark side is calling me, and the force is too strong. It’s time… to bring back the serif!
Tested to make a simple time tracker for mac. Kinda works but some performance issues. And would love to get more access (to window titles etc). Anyone experienced with applescripts?
Whoa github actions is pretty cool. Can just hook it up to openai api and it summarise all pushes and updates to changelog, updates docs and even sends a monthly client update (maybe).
Huge breakthrough
New AI unveils strange chip designs, while discovering new functionalities, it's also slashing the time and cost of designing new wireless chips
"In a study published in Nature Communications researchers at Princeton Engineering and the Indian Institute of Technology describe their methodology, in which an AI creates complicated electromagnetic structures and associated circuits in microchips based on the design parameters. What used to take weeks of highly skilled work can now be accomplished in hours."
"Moreover, the AI behind the new system has produced strange new designs featuring unusual patterns of circuitry. Kaushik Sengupta, the lead researcher, said the designs were unintuitive and unlikely to be developed by a human mind. But they frequently offer marked improvements over even the best standard chips."
"We are coming up with structures that are complex and look randomly shaped, and when connected with circuits, they create previously unachievable performance. Humans cannot really understand them, but they can work better," said Sengupta, a professor of electrical and computer engineering and co-director of NextG.