I'm reminded of the infamous Dropbox Hacker News comment[1]. If you're looking at stuff like this thinking "what's the point? I could just make that myself" then you're not the target audience in the same sort of way Ikea isn't trying to sell stuff to carpenters.

This is true even when the barrier to entry in making these sorts of systems has gotten way lower.

1. https://news.ycombinator.com/item?id=9224

The core idea of modernity's tendency to take a Good Thing and chop it up into tiny pieces and bind it into Something Resembling Good Thing[1] hit me hard. I've long felt a discomfort with things that pretend to be other things[2]; just be the thing that you are! There's something particularly macabre about the fake version of the thing being built from the ground up bones of the actual thing.

Also: the Incas invented a natural freeze drying method‽ Totally tracks that would lead to a big military advantage before there were many effective ways to preserve food. But also like, what? It took ~500 years for us to rediscover that.

1. examples from the article: McNuggets, American cheese, instant coffee, deli ham, Pringles, particle board, sheetrock, video compilations, gig economy jobs

2. like fake window shutters on houses, brick siding that's meant to look like the house is made of brick, artificial food dyes, the fiberglass shell on the outside of cars, things painted look like they're a different color.

What I want at the core is to be able to open up access to my laptop's currently running Claude Code instance (without all these hacky backdoors that fork the chat with every message by using `--print`; I want a first class API that lets me append messages to the current chat), then I want to be able to send messages (with voice transcription) and approve/deny permissions and see the code diffs and all of that.

Maybe something like a Telegram bot? I had hopes for Claude Code UI[1] but the web interface is too clunky on mobile.

1. https://github.com/siteboon/claudecodeui

Where might I find the SDK or developer docs for how to make apps for this thing?

There’s a reason intermittent rewards are so intoxicating to naturally evolved brains: exploiting systems that give intermittent rewards is a great resource acquisition strategy.

Stars are only a proxy for use, of course, but I'm not sure what a closer public indicator might be.

1. https://github.com/google-gemini/gemini-cli

2. https://github.com/openai/codex

3. https://github.com/anthropics/claude-code

Personally, my life has significantly improved in meaningful ways with AI. Apart from the obvious work benefits (I'm shipping code ~10x faster than pre-AI), LLMs act as my personal nutritionist, trainer, therapist, research assistant, executive assistant (triaging email, doing SEO-related work, researching purchases, etc.), and a much better/faster way to search for and synthesize information than my old method of using Google.

The benefits I've gotten are much more than conveniences and the only argument I can find that anyone else is worse off because of these benefits is that I don't hire junior developers anymore (at max I was working with 3 for a contracting job). At the same time, though, all of them are also using LLMs in similar ways for similar benefits (and working on their own projects) so I'd argue they're net much better off.

Mochi has great native apps on macOS and iOS (and maybe more?), the cards are formatted in markdown so I can generate them with LLMs with a custom system prompt, and I just found out today they have an API so I might try my hand at getting an LLM to push new cards on its own via. an MCP server.

1. https://mochi.cards/

ChatGPT is the main spot where I'm going to be trying to understand a new concept, so after groking it I'll ask it to make flashcards which I can then just copy and paste into Mochi.

An improvement would be some sort of MCP integration between the LLM and Mochi so it can just add the card directly. I'm sure we'll get there soon.

1. https://gist.github.com/christiangenco/db4b61c315b93fc2a404a...

I spun up a quick survey[1] that I sent out to friends and family to try to get some numbers on these sorts of phrases. Results so far are inconclusive.

1. https://www.vaguequantifiers.com/

We probably watch one or two hours of Ms. Rachel videos a day with our daughter. We've got several family friends with a household rule of "no screens at all for kids" who would scoff at that but their rule seems both draconian and technophobic to me. Our daughter has picked up many words and concepts from the show and we've learned a lot of the songs as a family and sing them when the context comes up (ex: "baby put your pants on..."). Ms. Rachel has been a hugely positive parenting tool for us.

Every once in a while, though, YouTube will try to autoplay some Cocomelon after a Ms. Rachel video and wow it's just absolute garbage. I think this article captures it well: it feels like slop engineered to keep young eyeballs glued to the screen with no higher purpose than increasing the number of engaged minutes.

Instead of "no screens," the more granular "you can choose from this menu of approved content on your screen for a reasonable amount of time per day" is the better parenting move for our family.

I think a great use case for this would be in a company that doesn't want all of their employees sending LLM queries about what they're working on outside the company. Buy one or two of these and give everybody a client to connect to it and hey presto you've got a secure private LLM everybody in the company can use while keeping data private.

Hi thank you for writing this!

Life is precious and finite. Memento mori.

1. https://waitbutwhy.com/2014/05/life-weeks.html

2. https://res.cloudinary.com/genco/image/upload/w_1200/v173967...

It's fast? Not as fast as an LLM.

LSP code completion? Not as good as LLM completions aware of your entire codebase at once.

Snippets? These don't matter if an LLM can just make them up on the fly.

We've entered a new paradigm of what it means to be a good code editor. I'd love if Sublime added the LLM chat and code diff from Cursor but I think the new way to edit code is going to look a lot more like having a conversation (text or voice) with an LLM that's making the changes for you.