But will this be released as a feature? For me it seems like it's an Anthropic internal tool to secretly contribute to public repositories to test new models etc.

I don't care who is using it, I don't want LLMs pretending to be humans in public repos. Anthropic just lost some points with me for this one.

EDIT: I just realized this might be used without publishing the changes, for internal evaluation only as you mentioned. That would be a lot better.

A benign use of this mode is developing on their own public repositories.

https://github.com/anthropics/claude-code

Don't we have PostIdent in Germany? At least I used it to open my bank account.

At least I started by playing around with microcontrollers (the ESP8266). From there you will get an understanding of how they work etc. Most of the time there’s an imprint of the chip type, so figuring out the type isn’t hard.

Dumping the firmware depends on the chip. While playing around with these chips you will also get to know the tools. In this case „esptool“.

For me, most of it is learning by doing and being curious how these systems work. At the start you may do wrong assumptions about the system. But the more you research the clearer it gets.

Interesting project. In one of our reverse engineering projects we used Gemini to interpret the decompiled C code. Worked really well. Hope to publish it next month.