That's kinda the goal. Imagine all the automation in the world being able to embed intelligence directly inside it - factories could route based on more complicated questions, hardware could anticipate your needs. Customer support could be done without humans 90% of the time.
I just turned my PTZ security camera into a VAR booth for my kid. Lawn (soccer) / Driveway (Floorball) / End. Live view, step back 10s, slowmo, frame step, scrubbing.
GLM 5.3 helped to root my camera so I could get proper endpoints for PTZ and stream. Claude built the api and frontend, hosted on Home Assistant.
For someone interested in this topic and happens to pass by, I can highly recommend a visit to Grimeton Radio Station[1], Sweden, which is still operational.
Coding agent that seems to beat Claude Code on SWE-bench at half the cost.
8/15 on SWE-bench Verified vs Claude Code's 5/15, ~$0.06/instance vs ~$0.12. Small sample, single repo, lots of caveats. But the direction feels right.
Event-sourced reducer, no framework deps beyond the Anthropic SDK.
> Z-mode means the front and rear wings are closed which generates more downforce for the corners. In X-mode, the drivers can open the flaps which will reduce drag and increase speed.
Driver-controlled aero has the potential to be way more interesting than the strictly-limited current DRS implementation.
The most interesting DRS era was in 2011-2012 when drivers could operate it (almost) anywhere they wanted in practice and qualifying. There was an element of risk in how early you could open it exiting a corner, and we saw real mistakes from drivers pushing that limit.
More driver controls leads to more opportunities for talented drivers to make a difference, which leads to a better sports product.
The problem with DRS is the zones and only being able to use it when close behind another car. My understanding is the X-Mode can be used pretty much anywhere and anytime.
reply