I have heaps of experience with Stencil and it works great until a certain size indeed. It is a great way to ship web components quickly.
Coding agents will allow us to write plain JS way more quickly but it still takes a bit more time by humans to read compared to reading something that was written with in a framework.
Until the day that I don't have to do reviews of my AI generated code, or some sort of pseudocode abstraction layer becomes available, I think there is still a place for frameworks and libraries to create web components like Stencil.
>Now the transcript happens in the background, a summary lands in my Obsidian vault automatically, and I can actually be present in the conversation. That’s 20 minutes a day I got back, every day, without thinking about it.
Honest question: Do you actually read any of these notes?
I think there is a fundamental flaw with not taking notes. I'm convinced taking notes forces you to properly consider what is being said and you store the information in your brain better that way.
Taking notes during meetings isn't to improve understanding, or to "read" afterwards.
They're a record of what was discussed and decided, with any important facts that came up. They're a reference for when you can't remember, two weeks later, if the decision was A and B but not C, or A and C but not B.
Or when someone else delivers the wrong thing because they claim that's what the meeting decided on, and you can go back and find the notes that say otherwise.
I probably only need to find something in meeting notes later once out of every twenty meetings. But those times wind up being so critically important, it's why you take notes in the first place.
Right, so it's for accountability instead. Have you considered generating stories or tasks from the notes in that case?
Still I think it's better to discuss "action points" in that case and give a clear owner to those points. This always helps me to understand who's accountable and what actions actually need follow up.
The question is, what artifact records the action points, the owners, who is accountable? And all the necessary associated information?
Notes do. Ideally there is a meeting owner who produces official notes and emails them to everyone, but frequently that never happens. And when it does happen, sometimes they're wrong and you need to correct them.
Which is why you need your own meeting notes. Plus, like I said, there are facts that come up that you want to document as well, that aren't part of the action items, but have value.
And I'm saying, a lot of the time either the company doesn't use such tracking software, or it uses it for software development but not the meeting you just had with legal or finance or design or people outside the company or whatever.
The kind of stuff stored in Jira is a very specific subcategory of all the types of things that get mentioned and decided in meetings. It doesn't cover all of it, not even close. And the person putting the information in might also get part of it wrong, that happens surprisingly frequently. It's not a substitute for personal meeting notes.
You can use an LLM to generate first drafts of flashcards that you import into, and later revise in, a true spaced-repetition system — such as Mochi or Anki.
For learning new material, make your LLM assume a Socratic position. Kagi Assistant has a custom Study model that does this. The key is causing the model to increase your friction (causing learning and memory) instead of decreasing it.
When the LLM enters the "card" into the API it would define the required information, and then every time it would ensure you cover the required information. You could tell the LLM, "make sure I remember the date of this historical event", and then the LLM would ensure you mention the date when answering the card. If you get the date wrong, then it does the API equivalent of pressing "wrong / again" in Anki.
I don’t read the notes generated by AI during meetings - but that’s not their purpose, either. The agent reads the notes, and uses that context to be better at what I’m asking it to do.
It also lets me ask questions like “When did we decide to change the login modal?” and get an accurate response.
I think it depends. Honestly, for me, the alternative to automated notes from meetings is that I don't take notes. I know, I should, but I don't. I've tried numerous times to instill the habit unsuccessfully.
Where the value for me comes from is sending them out immediately after the meeting, not archiving them in a vault I never look at. "Here's the summary of what we discussed, and the distilled action items we each agreed to take."
Like the author, I've gone out of my way to avoid hosting my personal stuff with Big Tech providers, but when it comes to work, I give in to whatever we use, because I just don't have capacity to also be IT support for internal technology. It's still uncomfortable, but I have to be honest about what I have time for.
>Informal tone and mistakes actually signal that the message was written by a human and the imperfections increase my trust in the effort spent on the thing.
Isn’t this a bit short sighted? So if someone has a wide vocabulary and uses proper grammar, you mistrust them by default?
I'd say, not "people in general" but people form other socioeconomic strata. This guy is not talking like us, suspicious. He talks in an elaborate and thought-through manner, not simply, so, he's not candid, double suspicious!
Not necessarily but it carries less weight than pre-LLMS. Obviously it's just a heuristic and not the whole story and telltale AI signs are not purely about good spelling and grammar. But I just appreciate some natural, human texture in my correspondence these days.
Nice read! The main benefit for me is the reduced search times for anything I need to look up online. Especially for code you can find relevant information ware more quickly.
One improvement for your writing style: it was clear to me that you don’t hate AI though, you didn’t have to mention that so many times in your story.
>The engineer who opens a pull request, taps a colleague on the shoulder immediately, twiddles their thumbs for half an hour, and then revises and merges immediately has done the same amount of work, but much faster.
Completely agree. Unfortunately corporate environments tend to reward people that are "busy" instead of productive. I've been in many environments where I had to wait for a lot of people that were busy to gather requirements, slowing me down immensely. How do you deal with that?
Basically the same as every MMORPG that is still around today which are now just single player games.
For me LinkedIn is the worst offender of all social media. Users on there generate their slop posts and go so far as to share their slop-generation workflow with others to farm interactions.
Genuine question, doesn't this apply to coding style than actual results? Same applies to writing style. LLMs manage to write great stories but they don't suit my writing style. When generating code it doesn't always suit my coding style but the code it generates functions fine.
I got a pro subscription yesterday. With it you get a certain amount of tokens and you have a certain limit every 5 hours and every week.
Once the limit is reached, you can choose to pay-per-token, upgrade your plan, or just wait until it refreshes. The more expensive subscription variants just contain more tokens, that’s all.
Right. I understand the potential for maximum usage (and abusing) of Claude in production. I don't suspect Claude will get caught too easily giving free beer.
We'll both find out if Pro's token limits are sufficient for spending a weekend on a learning project, and what the fallback looks like.
Interesting to compare the US to Denmark while they are so different with respect to their healthcare system.
On another note, why are there quite a few articles posted on US healthcare? Genuine question. I deliberately skip many news websites because I don’t want to read about such topics but just want to focus on technology.
Coding agents will allow us to write plain JS way more quickly but it still takes a bit more time by humans to read compared to reading something that was written with in a framework.
Until the day that I don't have to do reviews of my AI generated code, or some sort of pseudocode abstraction layer becomes available, I think there is still a place for frameworks and libraries to create web components like Stencil.