> web app I had launched using Claude was strikingly similar to his open source project, even reproducing a bug he had later fixed,
How? How do I prompt to get a literal copy of another app? When Claude/Gemini builds anything for me I have a thousand ideas for functionality improvements and UI/UX changes. How do you just stop at v1 of what Claude gives you?
Where did that trend start? Who writes like that, with emoji bullet points? I'm seeing it around, but surely nobody looks at that and says "yeah that's good"?
That is by design (on Firefox's part) to avoid someone registering e.g. steаmpowered.com (notice а as U+0430 instead of a as U+61) and running a scam that looks valid on the address bar.
But that means it had to be a trend already to be overrepresented in the training corpus, right? Or was it just something the RLHF evaluators got a kick out of...
I've really seen it a lot in Discord channels that have [emoji]channelname
Occasionally in some channels lists may be bullets with emojis particularly the welcome/rules, usually to match reaction emojis, or to automate channel(s) selection (click on the youtube icon to get notified when a youtube vid is posted, etc.)
This is written from a point of view of somebody who never went through the progression of CSS to CSS preprocessors to component-based frontend libraries. Tailwind is an answer to all the problems that become apparent in CSS in that progression.
I tried to embrace web components, but when I reached "declarative shadow DOM" I really just stopped seeing the point of all that complexity just to do what I can already do with a library. The target audience of that API seems to be library developers.
I’d argue that the target audience of Web Components in general should be library developers.
Web Components are great for distributing UI elements that work with every framework.
Web Components are terrible for just building apps. Use a framework!
From this perspective, Elena seems like a welcome approach. If Web Components are for library authors, and they are, then it stands to reason that Web Component frameworks optimize for that as well.
As much as I dislike Google, Lit has been a nice middle ground for me.
It's lighter then a framework, events are vanilla JavaScript so you don't have to figure out how to make a JS libray you've found work within some framework's custom event bus.
It has enough rendering support so you don't need to update everything with .innerHTML. Change the state of a component, lit will call your render function but only update the parts of the DOM that have changed. I felt that was a nice partial answer to suggestions you need a virtual DOM because updating the real DOM is slow.
> The target audience of that API seems to be library developers.
And then most library developers find them severely lacking, riddled with unsolved and unsolvable issues, filled to the brim with invalid assumptions and awkward APIs etc :)
They are somewhat okay as framework-agnostic "leaf" components if the authors spent a lot of time honing the usage and the APIs. Things like date pickers for example.
This post is full of things opposite of what I've found. An agent (claude code at least) will certainly refactor feature flags better than I ever could and is less likely to miss special cases. What the agent struggles with is business knowledge - context I hold in my head as a human communicating with other humans and working on a codebase over a long period of time.
One of the main problems I face is that business knowledge is not explicitly written down and formulated. No matter how much you describe something in human text format those are not formal rules about how something should work. If you can't inspect the output of the LLM you do not have full understanding of the business.
Most "classic" computer systems (code that runs on a CPU) are not strictly formal[1], but they are orders of magnitude more formal than human language.
[1] things like distributed systems, memory corruption, performance characteristics, etc can make a system behavior not predictable
That's true. But we always desired that more business knowledge be shared in written form between humans (people come and go, work across time zones, ...).
Presumably agents can both help maintaining/mediating such communication and also benefit from the context they acquire through that
> Presumably agents can both help maintaining/mediating such communication
What happens in practice, is that people use agents to write such communication down, don't review it, and then the wrong information persists, and future agents will regurgitate it, until it reaches a human who already know it's wrong who then goes "Huh, where did this come from?".
Kind of excited about this. 3.5 Flash on Antigravity has surprised me recently on a hobby project. When given opportunity to plan, it can deliver on tasks that would take me a while on my own and generates responses at blazing speeds - compared to what I'm used to at work with Opus 4.8 (granted I don't use Opus 4.8 on my hobby projects so just anecdotal). While with Gemini CLI I would just watch it run in circles and run out of 5h allowance before anything useful is produced (or even approached).
Yes, it's the Youtube phenomenon - often when looking for domain-specific videos on Youtube I tend to find videos by professional Youtubers not videos by professional domain specialists (overlap is very rare but occasionally you can find a domain specialist Youtuber who applies their domain knowledge to making Youtube videos).
Sharing knowledge is good, but just because an LLM crawls it doesn't mean it fits my mental model. The act of writing is fundamentally about drawing the shape of my own mental model.
Was it my comment you really wanted to reply to? My point is that there are things we can do right now/today in order to heal our society from the sort of malignancies that distract us from advancing as a race.
Spotify is fundamentally broken in a certain, unfixable way, IMO.
I use it and have a subscription, but I dread opening their app and looking at the starting screen that shows the same artists I listened to twenty years ago in pointless blurbs like "presave this (you can't listen to it)", "jump back in (you literally already listened to it)", "your favorite artists (not according to you but according to us)". There is no joy of discovery of new music that you haven't heard. There is no connection to other humans through music. Audioscrobbler/Last.fm is miles ahead of this. Youtube is miles ahead of this.
Here's how I discover music these days: I swipe Youtube shorts until its algorithm decides to show me an artist, then I look that artist up on Spotify. Thats how bad Spotify is - it's an audio server with search and a hundred layers of irrelevant features bolted on top.
It seems like every recommendation algorithm gets into a state that is broken eventually. For the music streaming services, I find they end up in one of two states, either it shows me the exact same artists and songs over and over again even if I skip their songs constantly, or I'll play a song once out of curiosity or accident and it decided that that genre is all I am interested in listening to for the next month. Is it really that hard to map artists
I got so frustrated with Tidal recently that I finally sat down and finally setup a media player on Linux to play my locally saved music (most of which is from What.cd).
I still find that, even after all these years, Pandora's recommendation engine still seems to be the best. I can tune into stations that I created, jeez, 15+ years ago, and it might play one or two tracks that I know, but it quickly diverges into new tracks that are still within the "flavor" of the station, but I've never heard of.
I had spotify premium for ~10 years i think.
I recently cancelled.
I travel a lot, so now they started complaining i was not listening near my address.
then they started blocking family members because i was not around.
then they wanted to charge in a different coin because i was not home, but EVEN if i would their login doesnt work because it redirects me to a different country if i am abroad.
they are vibe coding too hard that they add all bs they think is a good idea.
it was a good push for me to cancel that.
> There is no joy of discovery of new music that you haven't heard. There is no connection to other humans through music.
Hard disagree here.
For new music, Discover Weekly is great, if you take some time to engage with it on a routine basis. Even better, if you have an artist/genre you already like, the Fans Also Like or Discovered On will link you to other artists and playlists. Super easy to go down rabbit holes of new artists and playlists.
As far as connecting with others, I do like the spotify DMs (in-app share), the friend activity tab, and particularly the share attribution. When you share a song via link (url with ?si=), you'll permanently be linked to it. For a number of my favorite songs, I see "From {friend}" at the bottom while listening. Makes me feel super connected to friends I've bonded with over music.
> There is no joy of discovery of new music that you haven't heard.
I have my problems with Spotify, but this is not one of them. I discover new artists, or long forgotten artists, regularly - even some weird obscure shit like Tänzelcore.
But I have to agree, that the magic of discovering new music is not the same as, for example, digging records in a record store or via obscure boards and platforms (remember FF-Shrine?)
How? What's your secret? It's actively fighting me from discovering anything new. "Hey we'll show this artist you stopped listening to two years ago on your start screen forever. Wanna jump back in?" That's Spotify to me.
If you liked FF-Shrine, there are some active successor sites. Search for Sitting on Clouds (which is like FFShrine’s Galbadia Hotel) and SquidBoard (a forum).
Holy shit, thank you! FF-Shrine was phenomenal back then to find even the most obscure rearrangements of video game music. I know, that there has to be some backup archive of FF-Shrine, which I stumbled upon a few years ago, but unfortunately didn't save.
How? How do I prompt to get a literal copy of another app? When Claude/Gemini builds anything for me I have a thousand ideas for functionality improvements and UI/UX changes. How do you just stop at v1 of what Claude gives you?