Nice DeepSWE score! Does it survive a lowercase filename?
Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement.
Models clustered around 74% on DeepSWE end up 23 pp apart.
Good at coding, or good at DeepSWE? 🧵
June 29, 1994. Almost 2,000 Japanese companies held their annual meetings on the same day.
More than 10,000 police were sent out to watch.
The reason was the sokaiya, racketeers who threatened to disrupt meetings unless companies paid them.
Before a 1982 law, there were an estimated 6,500 of them. After it, about 1,000. By 2023, about 150.
Japanese companies scheduled all their meetings together so the gangsters couldn't attend them all.
The shareholders couldn't either. That was the other effect.
I was shocked that 3/4s of designers work in coding agents rather than design tools. This is crazy?? Designers deserve a tool built for them, not just for developers.
That's why I'm building @proto_ide, the designer’s IDE. The shape of Claude Code and Cursor, but with every design feature you wish they’d ship.
Early access signups are open. If you want a tool that finally unlocks your full creative potential, sign up at https://t.co/9bLnGcipgZ :)