[TeMPOraL]

All the time, yes. But you have to keep two things separate in your thinking:

- Prompted as in prompt made of tokens -> for LLMs, tokens double as a clock signal. Time only flows when tokens are pushed through them.

- Prompted as in specific request placed in the stream of tokens -> Yeah, they do that all the time whether it's getting into infinite loops of repeating same pattern, or suddenly deciding to do things based on inputs they normally ignored.

Also don't forget that everything is a "prompt" for LLM. All input tokens end up in the same place.

[RandomLensman]

So without a token pushed into them they do something? Not sure I understand...

In the current UIs is there a lot of suppression then as I have not seen things start on their own?

I meant an LLM doing something without any external prompt at all. Not doing something different etc but rather do something without a token/prompt ever flowing to it.

[ACCount37]

Category error. You might as well say "I've never seen a human do anything without being alive, so humans must be very easy to use safely".

Today's AI harnesses just keep feeding AI tokens - and can, in principle, do so indefinitely. "Streaming LLM" is not mainstream but not unknown either. "Automatic context compaction" is somewhat similar in what it does, and very common. "Keeping the lights on" isn't hard. And you have to turn on those lights to have an AI do anything at all.

At the same time: that type of harness often provides a "tool call" interface. Plenty of tools that end up attached to LLMs can do things like run arbitrary code, spawn instances of the same AI, and more.

That's frankly enough. An AI that can spawn more copies of itself can, in principle, just keep itself running indefinitely - even in a non-streaming no compaction harness. An AI that can run arbitrary code on a system can, in principle, do anything a human using that system could do.

The thing that truly limits what an AI can do is the AI itself. Practical AI safety relies on AI being either too weak or too well behaved to cause major issues.

[baq]

You’d need to train a model to be able to do that.

We shouldn’t be doing that as a civilization in case it works.

[TeMPOraL]

Just so it's clear: we are talking about building an AI equivalent of a sensory deprivation tank.