I absolutely love it. I find it empowers me more than ever before, and my satisfaction is at all time highs. I'm even building projects now (videogames) that I probably wouldn't have started before.
Here's where I'm at:
- Your subjective taste will become more important than ever, be it graphic design, code architecture, visual art, music, and so on for each domain that AI becomes good at. People with better taste will produce better results. If you have bad taste, you can't steer _any_ tool (AI or otherwise) into producing good outputs. So refining your taste and expanding it will become more important. re: "Yeah, I could've prompted for that too.", I see a parallel to Stable Diffusion visual art. Sure, anyone _can_ make _anything_, but getting certain types of artistic outputs is still an exercise in skill and knowledge. Without the right skill expression, they won't have the same outputs.
- Delegating the things where "I don't have time to think about that right now" feels really good. As an analog, e.g., importing lodash and using one of their functions instead of writing your own. With AI, it's like getting magical bespoke algorithms tailored exactly to your needs (but unlike lodash, I actually see the underlying src!). Treat it like a black box until it stops working for you. I think "use AI vs not" is similar to "use a library or not": you kinda still have to understand what you need to do before picking up the tool. You don't have to understand any tool perfectly to make effective use out of it.
- AI is a tremendous help at getting you over blockers. Previous procrastination is eliminated when you can tell AI to just start building and making forward progress, or if you ask it for a high level overview on how something works to demystify something you previously perceived as insurmountable or tough.
> Nothing feels satisfying anymore
You still have to realize that were it not for you guiding the process, the thing in question would not exist. e.g., if you vibecode a videogame, you start to realize that there's no way (today) that a model is 1-shotting that. At least, it isn't 1-shotting it exactly to your vision. You and AI compile an artifact together that's greater than the sum of both of you. I find that satisfying and exciting. Eventually you will have to fix it (and so come to understand parts you neglected to earlier).
It's incredibly satisfying when AI writes the tedious test cases for things I write personally (including all edge cases) and I just review and verify they are correct.
I still find I regret in the long term cases where I vibe-accept the code it produces without much critical thought, because when I need to finesse those, I can see how it sometimes produces a fractal of bad designs/implementations.
In a real production app with stakes and consequences you still need to be reading and understanding everything it produces imo. If you don't, it's at your own peril.
I do worry about my longterm memory though. I don't think that purely reading and thinking is enough to drill something into your brain in a way that allows you to accurately produce it again later. Probably would screw me over in a job interview without AI access.
- hiragana / katakana / number / time reading quizzes
- vocabulary quizzes based on wordlists you define and build
- learn and practice kanji anki-style (using FSRS algo)
- the coolest feature (imo) is a "reader": upload Japanese texts (light novels, children's books, etc), then translate them to your native language to practice your reading comprehension. Select text anywhere on the page (with your cursor) to instantly do a dictionary lookup. A LLM evaluates your translation accuracy (0..100%) and suggests other possible interpretations.
I just revamped the UI look and feel the other day after implementing some other user feedback! I'm now exploring ads as a way to monetize it.
- hiragana / katakana / time reading / number reading quizzers
- learn kanji with FSRS, anki-style
- vocab quizzer
- the coolest feature (imo) is a "reader": upload Japanese texts (light novels, children's books, etc), then translate them to your native language to practice your reading comprehension. Select text anywhere on the page (with your cursor) to instantly do a dictionary lookup. A LLM evaluates your translation accuracy (0..100%) and suggests other possible interpretations.
It's all elixir+liveview+postgres+pgroonga (though there are times when I would like to have SolidJS).
I've been considering open-sourcing it due to lack of commercial success, but might try an ad-based approach first.
grok-code-fast-1 has been my preferred model lately, but I don't see any mention of it as part of this release. I'm wondering if this might be better? Even if grok-code-fast-1 might be slightly worse than Gemini 2.5 Pro, the speed of iteration can't be beat.
I imagine (and hope) I'm not being billed for requests that fail.
In my own apps that use Anthropic API, sometimes the req just fails the initial connection (and so has to be retried), usually works in 1-2 retries.
Cursor doesn't auto-retry my request, it presents me with a button to click to retry. If you know the request failed, you could just retry on my behalf!
Basically all the bonuses of Windows re: gaming, with a great developer experience (like Linux/OSX).
The prime annoyances are:
- exposing a port to the entire LAN (for local phone debug) is non-trivial
- I imagine Android or phone dev might be a bit harder re: simulator, luckily I don't do this
- dev that spawns native windows would by default spawn through some WM layer with X11 or something (and they are laggy)