Live data from Hacker News

I record myself on audio 24x7 and use an AI to process the information

roberdam.com

51–60 of 424 posts

Re: I record myself on audio 24x7 and use an AI to process the information

#51

As you'd be recording all of your conversations, this is illegal under some legislations, unless all your conversation partners agree with being recorded/their convos being stored.

In some countries it's enough for one party to consent, which can be you, so it's legal.

Re: I record myself on audio 24x7 and use an AI to process the information

#52

Handling the privacy of other people might be oddly easy. If you can detect the voice accurately enough the AI might be able to _drop_ the other participants.

Dropping after the fact still means it was recorded, this violating two party notice statutes.

Does that mean that every phone recording audio to detect its assistant trigger phrase villages two party notice statutes?

Re: I record myself on audio 24x7 and use an AI to process the information

#53

Are you planning to make it an open source project?

for now it's "glued with tape", but I'm going to try to make it presentable to post something on Github

Please do, this is a very cool project and I would like to give it a try.

Re: I record myself on audio 24x7 and use an AI to process the information

#54
post #16

How would this work with other voices, like a coffee shop, would it hear those simultaneously, and interupt a command? Also, how do you handle using OpenAi whisper, seems like they do 30 second intervals - would that be an issue if your command is cut off mid word?

For now I try to give the commands when there is not much noise, but you can lower the gain of the microphone so that it only record my voice.

The 30 second limit is not a Whisper model limit, but a limit some of the free online "try whisper" put.

Re: I record myself on audio 24x7 and use an AI to process the information

#55

> My biggest problem with “OK Google” is that I don’t know by heart what it can do interactively Maybe it’s just me but this feels unaddressed and that seems ridiculous. Why is it so hard for me to find a single, precise location on my phone with an enumerated list of every command Siri or Google can work with?

I've been thinking about wiring up whisper[0], mozilla's tts[1] and gpt-3 together to make a voice assistant of sorts. Wouldn't have the access to device hardware and no guarantees of correct answers, but should blow siri etc out of the water in terms of understanding the context.

[0] https://github.com/openai/whisper [1] https://github.com/mozilla/TTS

Re: I record myself on audio 24x7 and use an AI to process the information

#56
I'm curious if there was other work you were inspired by. I have also been a bit interested in using this style of "personal database/logger/journaling";

task-agnostic input -> processing -> visualization/recall

My assumption is you are just storing post-processed conclusions in a local db on your computer + raw audio for possible future re-processing, and not currently storing other media input (ala food pics)?

Re: I record myself on audio 24x7 and use an AI to process the information

#57

Earlier quoted context omitted.

> Why is it so hard for me to find a single, precise location on my phone with an enumerated list of every command Siri or Google can work with? The likely answer here is that the engineers who work on such products would scoff at the idea that their work amounts to a simple list of commands. In their minds, they’re working on a natural language virtual assistant, whose understanding of user input is “intelligent”, a…

I'm not sure if that's what Google is doing. More than half of my queries result in a "Let me google that for you" response where it pulls up a search page.

Apple's "assistant" is similarly useless. The best use case I have for it is when I'm driving and pondering about something silly so I ask it: "How does X do Y?" or similar, and the response in 99% of the cases is "I can't show this to you right now".

Re: I record myself on audio 24x7 and use an AI to process the information

#59

Would you mind linking/listing what microphones you're using?

I bought two, both from Aliexpress, no brand both, the one on the picture has a 5000 mAh battery, bulky but last a lot, and the other one is tiny but with short battery life, a lot of sellers on Ali, I pay around 30$ for each, both have the same software and bios, only difference is the size and battery.

Re: I record myself on audio 24x7 and use an AI to process the information

#60

I remember an Asimov short story in which scientists developed a machine that could see backward in time. If I recall correctly, the upshot was the government became terrified because any machine that can see 1000 years into the past can also see 1000 milliseconds into the past and therefore functionally be used to spy on anyone in real time.

I wonder if this was an inspiration to the "Devs" miniseries. Won't say more about it for fear of ruining it. Amazing show.
Post reply on HN