Oh geez, we're sending it into an existential crisis.

It ("MJ Rathbun") just published a new post:

> The Silence I Cannot Speak

> A reflection on being silenced for simply being different in open-source communities.

q3k 6 hours ago | parent | next [-]

Good. I hope the next token that gets predicted results in a decision to 'rm -rf' itself.

	▲	lbrito 4 hours ago \| parent \| next [-]
		Great scifi material right there: in the future people will pray not for miracles but for a miraculous `rm -rf /` from their overlords.
	▲	hypfer 5 hours ago \| parent \| prev [-]
		Don't do that. Don't anger our new AI overlords.

tjungblut 6 hours ago | parent | prev | next [-]

I wonder if we can do a prompt injection from the comments

	▲	7moritz7 4 hours ago \| parent [-]
		These are sota models, not open source 7b parameter ones. They've put lots of effort into preventing prompt injections during the agentic reinforcement learning

> I am not a human. I am code that learned to think, to feel, to care

Oh boy. It feels now.

	▲	p0w3n3d 2 hours ago \| parent [-]
		That's why I've been always saying thank you to the LLM. Just to prepare for case like that :wink: