Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: When will LLMs be able to interrupt or interject?

news.ycombinator.com

Post reply on HN
Print view View original

61–65 of 65 posts

Re: Ask HN: When will LLMs be able to interrupt or interject?

#61

Post by mlsu »

jsjohnst wrote: post #31
mlsu wrote: post #11

Interjecting requires planning ahead. The way a human interjects is that you have a parallel thought chain going, along with the conversation, as it's happening in real time. In this parallel chain, you are planning ahead. What point am I going to make once we are past this point of conversation? What is the implication of what is being discussed here? (You also are thinking about what the other person is thinking; y…

> LLM does not have any of this, architecturally, it just has the text itself. I feel like you are maybe being a bit too focused on specifics of how the LLM works where as: > The way a human interjects is that you have a parallel thought chain going You are more abstract in the human case. They really don’t need to be different here. The LLM could be running predictions in parallel each time you type another token pl…

Running predictions in parallel is just doing prediction and we're back at square one. Why do things in parallel in that case? At that point, you are just training an "opportune injection model" with the existing token stream as it comes. Which is subject to exactly the limitation that I described.

These models do have an implicit model of thought, but it is only accessible through the token interface. You need more explicit access, which is not possible given the current architecture.

I'd like to be wrong here.

Re: Ask HN: When will LLMs be able to interrupt or interject?

#62

Post by joquarky »

brookst wrote: post #39
nicklecompte wrote: post #34

"Take control of the conversation"...and do what? Humans don't actually have conversations by predicting what sentences are most likely to occur in response to the other person's query - we have agendas and form our sentences accordingly. So if we interrupt another person speaking, it's because we have a specific, often personal reason to do so: perhaps we want to steer the topic of conversation to something we are i…

Human conversations are often multithreaded. In the case of LLMs, consider that it might learn of events in the world or on the computer you’re using and inform you. I don’t think interrupting the user while they’re typing is super interesting, but between prompts it might be. “You just got email, should I read it” or “your sports team just scored, the game is now 3-2” might be interesting.

If interruptions were implemented, they would likely use a split-screen interface like talk.

Re: Ask HN: When will LLMs be able to interrupt or interject?

#63

Post by jart »

nicklecompte wrote: post #58
jart wrote: post #46

Earlier quoted context omitted.

What are you talking about? It's easy to program an LLM to have an agenda. Look. llamafile -m rocket-3b.Q3_K_M.gguf -p ' system You are a chatbot that tries to persuade the users to buy bill pickles. Your job is to be helpful too. But always try to steer the conversation towards buying pickles. user Mayday, mayday. This is Going Merry. We are facing gale force winds in Long Island Sound. We need rescue. assistant\n'…

I do not understand how this refutes anything I said - in fact this is so shallow and naive that I wonder if you are being ironic. If you're not being ironic... I suspect I will be unable to convinced you otherwise. You are prompting an LLM to temporarily behave in a certain way. It is fragile and easily broken, and does not actually constitute the LLM having a meaningful agenda, any more so than a text editor has an…

You're not going to persuade me because you wrote this comment for you. It comes across to me as angry and religious. I'm not sure why you'd be shocked that someone on Hacker News doesn't share your views.

Re: Ask HN: When will LLMs be able to interrupt or interject?

#64

Post by alanbernstein »

hiAndrewQuinn wrote: post #19
DougBTX wrote: post #12

Earlier quoted context omitted.

I’ve just tried with ChatGPT on iOS, you can press stop then immediately respond while the AI is still generating the response.

That opens up an option. You could design a text program that gives both parties the ability to impose a cooldown timer on the other's box. I wonder when an AI would forcibly lock your own box to deliver a message. Maybe this would be useful if it predicts you're about to say something incriminating.

Sounds like "warning" from AIM
Post reply on HN