When agents are working for 8 hours, the prompt matters a lot less. At that point you're basically just writing "Root this tablet connected via USB cable" and the prompt doesn't really matter much.
The only human-written part of the prompt was "Explain to me in more simple terms the following". The rest of the prompt came from asking Kimi K3 for a handoff summary.
I was a little bummed about the detour into how I used AI in writing this blog post so I decided to add an addendum to address it: https://ericpardee.github.io/fire-hd-ownership/#how-this-pos...
In short, I get the anger, but let's not throw the baby out with the bathwater.
My intent in creating this blog was to share my tablet story and to get people talking about
- How companies control devices that you purchased and should own
- Today, US frontier models won’t allow users to even discuss exploits
- GLM-5.3 was more capable than Kimi K3 or GLM-5.2 in my experience
- You can be a prompt kiddie and accomplish things if you don’t accept LLM limitations
If I hadn't used GLM-5.3 to get this out, it would have never made it anywhere.