[sk11001]

It’s possible now, no idea why anyone would want this though. The idea is that you want something helpful, and you can do some additional prompting to encourage the model to ask questions but outright derailing the conversation is contrary to what these models are trying to do.

[dougb5]

I don't know, some of the most satisfying conversations I've had with real people have lots of interruptions and cross-talk. Anyway, I'd much rather my friend interrupt me than let me prattle on about something stupid.

Good dialogue can be parallel streams of communication; people rarely do strict turn-taking. The half-duplex nature of current chatbots feels very constraining.

[sk11001]

Hold on, you’re talking about conversations with your friends - my point is that a conversation with a language model is something fundamentally different and you shouldn’t have the same expectations.

[sandspar]

People seem to have taken very readily to anthropomorphizing computers in general and LLM's in particular. Anthropomorphizing seems like a feature of our brains. Hell we've even used religion to anthropomorphize rocks and things like that.

[dougb5]

I don't have those expectations of current models. Your post says "I have no idea why anyone would want this" and so I explained why I might want this. It's not just me, there are many companies hawking AI therapists, friends, romantic partners, etc., and interruptions would be useful in these contexts too. These companies seem mostly sketchy to me but I can't deny there's demand for their products.

[yehosef]

right - this is what I meant.

[jeremyjh]

Is it actually possible now? In order to do this it would have to be reading your typing in real time and creating a relevant response and then decide (correctly) its response should be to interrupt or interject.

You are right that no one would want an existing LLM to do it because they are not capable of doing it correctly. The ones that are fast enough are far too stupid to do it correctly, and its not clear to me even if GPT 4 could be fast enough that it would do it correctly 8/10 times, which would be about the worst it could do before anyone would turn off that feature.