I tried this a while back and found it ended up being easier to just give the firmware agent a dedicated machine, there’s so much low-level stuff you want access to for iterating on firmware, and the docker layers kept confusing the agents when they were debugging faults, crashes, brownouts etc.
Combining a dedicated small machine with a USB hub that supports per-port power cycling lets the agent iterate and un-wedge stuff with no human intervention for very long (days) periods. Obviously any software produced that way is unusable, but it’s incredible for debugging. Agent gets a programmable oscilloscope, power-cycling, and peripherals (also power-cycleable) emulating the various things our product talks to in the wild.
TL;DR I found the docker layers just caused confusion for the agent and giving her an old laptop was way simpler and much more powerful
I find this a rather interesting quirk of linguistics. In many languages, nouns have a "grammatical gender". For example, in Czech, "inteligence" has a feminine grammatical gender, so you are supposed to use feminine pronouns when refering to it. This sometimes leaks through with ESL people. I wonder if speakers of these languages anthropomorphize AI (or even animals or non-living objects!) more than native english speakers...
It's annoying enough if "small" projects can't refuse to use LLMs to write their documentation, but large companies? There's really no excuse to use LLM garbage to write stuff intended for human consumption.
1. A laptop with the development environment (DOS or Windows) kept in a box to use for updates / fixes
2. A VM on a NAS to use when a firmware in maintenance needs a fix
With more embedded tooling available on Linux, a docker image becames a natural choice.
Combining a dedicated small machine with a USB hub that supports per-port power cycling lets the agent iterate and un-wedge stuff with no human intervention for very long (days) periods. Obviously any software produced that way is unusable, but it’s incredible for debugging. Agent gets a programmable oscilloscope, power-cycling, and peripherals (also power-cycleable) emulating the various things our product talks to in the wild.
TL;DR I found the docker layers just caused confusion for the agent and giving her an old laptop was way simpler and much more powerful
Also:
- https://wokwi.com/
- https://github.com/davidmonterocrespo24/velxio
Do better.