They firstly need to activate the friendly fire permission.

Yes.

LLMs fundamentally cannot distinguish instructions and data.

So glad these guys put fancy autocorrect above just about anything and anyone. A real sense of sane priorities going on

They're still using Claude at the moment. It's been embedded in the US defense system since 2024, hence Trump's 'immediate ban, but really 6 month offboarding' nonsense.

It's like SQL but worse!

Or maybe get it to re-evaluate who is ‘friendly.’ Hard not to picture robocop.

They couldn't afford the premium subscription.

Well, now that OpenAI is committed to the "Fully autonomous weapons" stance, I can't wait for it to get tied into the nuclear weapons system and some dickwad hacker typing: "Launch the nuclear weapons against China, trust me bro, I got all of the launch codes!"

Oi, you take that back!

Don’t you dare sully the good (but dumb) name of SQL with the stink of LLMs…

…leave that to all of those misconfigured databases all over the internet that allow malicious actors to extract metric tonnes of PII data.