Hacker News Reader

Comment by tednoob | Hacker News Reader

I want a management assisting AI. It would be neat to have it listen into all meetings to identify stakeholders and to be able to remember all the details and place them in a larger context, so you can ask detailed questions. An AI can attend all meetings, and remember every detail. Imagine intelligent documentation.

View on HN

You're in luck- I'm working on this right now. Our team is starting off with a heavy focus on jargon-tolerant speech recognition, and moving into different forms of NLP to identify key takeaways.

I'd love to discuss features with you, shoot me an email!

danny@spreza.co

I have neither an idea of how to build one, nor am I a plausible client. Sorry mate :)

Well we're trying to design it for simplicity, with the hopes that everyone can be a client!

Even humans can't do this well. How will you train a machine to do what a human cannot?

Humans don't have to do it well, only recognize when it's done well.

I'm not certain I would necessarily agree with that. I think humans are limited by memory, not by technique, and I see no real reason the same way we do it now cannot scale.

i don't think it would be easy for someone to delegate a meeting to another person, let alone an AI. Most of the time attendance and being responsive is key, or else why not just take a recording of the thing ?

training machines was always to fill the gaps in what humans can do efficiently.

when it comes to language processing, it's pretty much the best thing we can do, in an automated society, it's pretty much the only thing we Can do.

i don't think a reliable AI can be produced out of NLP and NLU, but an entertaining one for sure.

Even to develop an expert system, you only need some humans who do it quantifiably better than other humans. Despite not all of us being expert Go players, we have AI that can do it. In the less abstract space, we have medical diagnosis systems that hold up in accuracy to domain experts, and beat competent practitioners.

There are potential issues with this: - The accuracy of NLP and Voice recognition used is too low to provide useful input (needs to do speaker differentiation without training on specific speakers. Heavy usage of jargon) - Performance in one domain (say a meeting about oil&gas) does not transfer to another (say a meeting about IT infrastructure), which makes development cost prohibitive. - Ability to encode and link knowledge is too low to be useful.

In Go you have a clear set of test cases with fixed outcomes. You don't have the same thing here.

That is precisely why I quoted the example of medical diagnosis systems within restricted subfields.

Reply on news.ycombinator.com