[az226]

And yet Mythos couldn’t find it. Whomp whomp

[amluto]

Mythos might be good at finding holes in an actual defined security boundary. But trying to audit Claude Code would be like trying to find the holes in Swiss cheese. Of course they’re there!

[stuaxo]

Oh is THIS the real reason they haven't released it?

It's the first thing people will point mythos at.

[amluto]

I’m fairly confident that almost any decent LLM trained on agentic command line workflows could break out of Claude Code. It’s really not hard.

[quinncom]

Probably it did, but just thought, “I’m saving this one just for me”

[perching_aix]

I honestly wonder if they run it against it. Like sure, it'd be very, very obvious for them to. But it'd be so quintessentially human not to.

The shoemaker's children go barefoot and all...

[philipwhiuk]

Maybe if they'd submitted each file twice instead of only once /s