I'm Begging You to Leave Your AI Note-Taker at Home
joanwestenberg.comAI note takers are so funny to me. Like what are you gonna do with all those notes? Go home after a long day, draw a nice bath, and flick through some shitty AI summaries?
And it’s AI so you literally can’t 100% trust it which is like half the reason I take notes by hand (to keep an honest record).
Tune out of the useless meeting and do something useful with your time. Read the 5 bullet point summary afterwards.
If it gets things wrong, oh well. Not much of value was lost.
This describes the vast majority of meetings held in the corporate world.
That's not what the article is about. The author describes using AI Note takers in PRIVATE meetings :)
That's astonishing for me, first time I hear about such a practice
> what are you gonna do with all those notes?
Dump them in Obsidian with an LLM agent bolted on. This note may never be consciously re-read, but it will become silent part of the context for conversations with the agent in the future. It is _ridiculous_ how useful this approach is.
That pertains to work meetings, though. I would never bring a recorder to a coffee shop.
So useful how? Like what does this context actually end up doing for you?
Just some recent case studies.
1) A stakeholder voiced a wish 1 year ago that I forgot about because it was far fetched and not my area. It went to die in a transcript. Today the AI found and resurfaced it in a context where it was actionable and I was in a position to implement it. I did not ask AI to dig it out specifically, like I said, I did not even remember about it, but it just brought it up. Stakeholder ecstatic.
2) I was able to recreate a huge piece of enterprise architecture without access to docs - from 20 meeting transcripts of people just blathering about other topics. From bits and pieces - word here, sentence there - the AI pieced together the big picture for me. Unfeasible manually, especially because the LLM used its training data to infer things that I wouldn't be able to infer myself.
3) I was added to a project as a consulting/observing party, did not pay MUCH attention, but recorded meetings just in case. Suddenly, plans change, and I end up in charge of the project architecture. Nobody bothered to keep any serious records. I throw transcripts, along with emails and chats, into a context window, and I get an excellent self-onboarding doc. I am ready to talk to clients competently next morning.
4) a vendor is failing us, meeting after meeting they defer, delay, gaslight, pretend to forget or misunderstand or not to have heard what they'd been told. I need to escalate, boss asks "give me details to work with". I throw in the transcripts, and in 1 minute I get the timeline of what was going on, with references. Re-tracing this manually would be hopeless.
5) I can talk to a person and ask their opinion virtually, by loading a corpus of meeting transcripts into AI and asking to pretend it's that person. Having 100k tokens of transcripts allows for a pretty high fidelity replica of that colleague!
Sounds about the same idea as taking a low-res picture of a document and saving it as a low-quality jpeg in folder full of low quality jpegs and then expecting those images to be useful.
I mean most of these tools pair the notes/transcript with a video recording of the call. It can be super helpful to search the summaries to find the right recording, and then click the line in the transcript to re-watch the meeting.
For work, this is strictly better than not recording the meeting, as it allows for much faster searching, and it is very rarely wrong about the high level topics of a convo. I almost always go "General AI summary search" -> Transcript -> recording when trying to remember a specific item from a call.
That being said the parent article is spot on and I can't imagine someone bringing a recording to a conversation they aren't being paid to have.
> I’ve adjusted to - and even embraced - the idea of AI note takers on every Zoom and Google Meet call, and they are indeed incredibly useful. Taking Granola’s output from a client meeting and dropping it into Poke to create all my tasks in ToDoist is a bloody useful workflow that shaves off a good deal of cognitive load.
What makes an in-person work meeting any different?
This feels like people several layers deep into devoid of all normal interactions.
We've had this technology (minus the auto summary) for years. People don't like being interrogated. It's crazy. Or maybe I'm crazy and someone needs to explain how all of this happened, it can't be all tiktok..
We had to issue a directive for an open attendance online board meeting I'm on. AI adjunct popped up unannounced, poses issues for formalisms like board minutes.
Aside from that I just think its rude. Ask permission not forgiveness. People talking to people is what a meeting is all about. If you need assistance there's a conversation to be had about why and on what terms.
This is strictly a San Francisco tech problem. This isn’t happening to most people
First thought was this sounds like a hyperlocal sf gripe
You think people in Austin or Denver or Atlanta don't have the same Zoom app, with the same AI helper as the one they give to San Francisco people?
I think they have the same app, but they don’t use it like this. It seems like you’re confident this happens a lot- do you live in San Francisco?
Yes! In the Ad Hominem district.
That you know of.
You’re the poster- do you live in the bay?
I do not. I live in fly-over country. I still see it happening.
At work, yeah, fine I guess. Outside of work? No way. And I don't mind being called a Luddite, I know what I am.
I can understand and appreciate the hesitation. I must admit I've simply adjusted to the idea that anywhere that I am, outside of my house, I assume someone is potentially recording or transcribing at a minimum audio.
I'm frankly far more upset by the lack of privacy due to poor security from credit reporting agencies than I am of these notetakers.
Just wait till this is baked into glasses…