It takes no effort to play LLM or not, you don't need to know anything about the topic or put anytime into reading and understanding the submission, just find that em-dash and you can turn every discussion into meta slop.
back
2 comments
I also think an LLM isn't going to just spit this all out and viola, it boots. I imagine there were many rounds of jtag debug, copy/paste into the LLM prompt, with enough human knowledge/context to say the right thing, suggest some existing implementation snippet, etc.
> I imagine there were many rounds of jtag debug, copy/paste into the LLM prompt
You may not be familiar with modern LLM tools.
You don’t need to copy/paste anything. You can easily instruct your agent to access the serial port and JTAG debugger and it will easily handle it through subsessions.
The tools have moved rapidly this year. Something like this is entirely doable by attaching the right cables, telling the agent where to access everything, and then keeping it fed with enough tokens to keep going.
There are some amazing projects doing reverse engineering or porting to micros fully automated. The results are still full of typical LLM output problems, but it’s amazing what can be brute forced with enough tokens in an LLM loop.
When I’m evaluating MCU platforms for new projects I’ll some times set an LLM loose on each to get a proof of concept running so I can do benchmarks or testing. It can save a lot of time finding showstoppers or roadblocks before I waste a lot of time on doing the problem correctly.
I've been writing code by hand for 30 years and nowadays use LLM too for embedded and Android development among other stuff. It saves a lot of time and is amazing that it can debug multiple embedded devices connected to the computer far better than my doing it by myself.
There is certainly slop but it was always like this in software engineering, just that now is far easier for anyone to write code that runs on ESP32 which in my opinion was already quite easy in the past but frankly bothersome to get any complex project running.
I'm old enough to remember when other developers criticized heavily the usage of Turbo Pascal in the 90s because "it wasn't a real compiler" but reality is that it made software writing far easier and fun for a whole new generation of kids. It seems we are going through a similar wave, it will take time until this settles as a new tool.
This is a common misconception among those who nothing about AI