Comment by 28304283409234
2 days ago
Could we be heading towards a world where it's just more secure to write inhouse software again, only now with AI agents? Not closed source per se, but 'own source'?
2 days ago
Could we be heading towards a world where it's just more secure to write inhouse software again, only now with AI agents? Not closed source per se, but 'own source'?
Seems cheaper (and so far more robust) to have an agent audit downloaded code
The endgame is to generate a binary image for an entire single-purpose OS/unikernel that does exactly and only what you require of it. No source to open or close.
The build process is just as vulnerable.
Sounds more midgame.
It's more likely we will move to a world where desktop OSs have a security model like ios/android so malicious software can't steal your data.
this