

Participants were then given real money to divide between themselves and the AI assistant
Uh huh… wat…


Participants were then given real money to divide between themselves and the AI assistant
Uh huh… wat…


The idea of giving an AI model access to my email or bank account makes my head spin.


Remember the days when hou could just pop the back off and take the battery out?
I just use ssh and manually type commands. Keep doing it and you will get good and it will become second nature.
No need to burn tokens on basic tasks.
Master your tools. Learn awk, sed, just, etc.
Some shell customisation can help. For example I’m fond of zsh-auto-suggestions and skim. Makes me quicker.


Join us…


Set aside some time to understand how your pension and the tax system works.
It’s dull as hell, but you will need it.
Does it work?


It was the kind of thing you could do painstakingly by hand with the likes of Ghidra.
You can give the model access to a tool like ghidra via a MCP and it will probably be able to solve the problem quicker and (if you ask it) you will get an annotated ghidra project out at the end.
Without it, it will likely write a series of python scripts using capstone etc.
But yes, local models are good. I just wish I could afford the hardware to run them.
Interesting. A couple of nodes nearby.
Will try.
Had a play with meshtastic, but no other nodes in my city.


I love bandcamp
Also, I have a touchscreen going :)
I added tmux packages for 32 and 64 bit pi a few months back.
They need you to install a utf8 compatible locale though.
Thats what picoreplayer is based on.
Tiny core linux + lyrion
Thats what picoreplayer is based on.
Tiny core linux + lyrion
I like picoreplayer.
Tried moode, but i think picore is a bit more flexible.


My thoughts exactly. And so the arms race continues.
Indeed!