deleted comment - I will never learn to ignore this kinda thing (referring to GP comment).
It's difficult to not get defensive when you put a lot of work into something and you receive what you feel are very unfair / unjustified comments.
Of course like anyone, when I do a substantial launch on HN I do tell friends. Most probably the referenced comments came from one of my friends trying to be helpful, but I don't actually know that - I have no idea who the account is in fact.
But I feel (perhaps wrongly) an accusatory tone in the very deliberate pointing out of this, and I just don't understand what is trying to be acheived. If you look at my submission history, comment history, and account age here I think one could probably assume good intentions and treat my submissions here with grace and benefit of the doubt.
But anyway, I regret making the original defensive comment and have re-learned the lesson to not do this as it just detracts from the quality of discourse. My bad.
You're good, man. I get it. Your heart and soul goes into a thing and the only comment you get is 'hey, look at these other posts with this suspicious user activity'. Nothing about your work.
I've had to deal with this in various areas of my life. I can't say I have a good solution.
The money is in B2B. This is nice as a hobby project, but it won’t scale beyond that as meeting transcriptions/summarization are an actual business force multiplier.
I wouldn’t quit your day job to go all in on this.
I guess the whole point of it is that it isn't a transcription / automated summary tool :-)
It's a tool for people who want to use their own brain to pick out the key notes and actions in a meeting and get (and create!) a lot of value by doing so - not hand this off to AI.
Obviously some will do that but this tool isn't for them. It's not for everyone.
Ha, it's an ambiguous title. Yeah the post is about not using AI in the actual note-taking process.
You will be unsurprised to learn though that I largely haven't used AI to program it.
The main ways I do are documentation/research questions, obviously autocomplete when writing code (which I do, still exclusively in an editor), and some ancillary scripts and tools.
That’s like saying you haven’t used cocaine often. And using the autocomplete that uses LLMs to write out entire functions from a signature is still using AI.
https://news.ycombinator.com/item?id=48956314
https://news.ycombinator.com/item?id=48952724
https://news.ycombinator.com/item?id=46202090
It's difficult to not get defensive when you put a lot of work into something and you receive what you feel are very unfair / unjustified comments.
Of course like anyone, when I do a substantial launch on HN I do tell friends. Most probably the referenced comments came from one of my friends trying to be helpful, but I don't actually know that - I have no idea who the account is in fact.
But I feel (perhaps wrongly) an accusatory tone in the very deliberate pointing out of this, and I just don't understand what is trying to be acheived. If you look at my submission history, comment history, and account age here I think one could probably assume good intentions and treat my submissions here with grace and benefit of the doubt.
But anyway, I regret making the original defensive comment and have re-learned the lesson to not do this as it just detracts from the quality of discourse. My bad.
I've had to deal with this in various areas of my life. I can't say I have a good solution.
I wouldn’t quit your day job to go all in on this.
I guess the whole point of it is that it isn't a transcription / automated summary tool :-)
It's a tool for people who want to use their own brain to pick out the key notes and actions in a meeting and get (and create!) a lot of value by doing so - not hand this off to AI.
Obviously some will do that but this tool isn't for them. It's not for everyone.
You will be unsurprised to learn though that I largely haven't used AI to program it.
The main ways I do are documentation/research questions, obviously autocomplete when writing code (which I do, still exclusively in an editor), and some ancillary scripts and tools.
That’s like saying you haven’t used cocaine often. And using the autocomplete that uses LLMs to write out entire functions from a signature is still using AI.