antonn @antonn

Continuing the journey of optimal LLM-assisted coding experience. In particular, I find that instead of narrowing in on a perfect one thing my usage is increasingly diversifying across a few workflows that I "stitch up" the pros/cons of: Personally the bread & butter (~75%?) of my LLM assistance continues to be just (Cursor) tab complete. This is because I find that writing concrete chunks of code/comments myself and in the right part of the code is a high bandwidth way of communicating "task specification" to the LLM, i.e. it's primarily about task specification bits - it takes too many bits and too much latency to communicate what I want in text, and it's faster to just demonstrate it in the code and in the right place. Sometimes the tab complete model is annoying so I toggle it on/off a lot. Next layer up is highlighting a concrete chunk of code and asking for some kind of a modification. Next layer up is Claude Code / Codex / etc, running on the side of Cursor, which I go to for larger chunks of functionality that are also fairly easy to specify in a prompt. These are super helpful, but still mixed overall and slightly frustrating at times. I don't run in YOLO mode because they can go off-track and do dumb things you didn't want/need and I ESC fairly often. I also haven't learned to be productive using more than one instance in parallel - one already feels hard enough. I haven't figured out a good way to keep CLAUDE[.]md good or up to date. I often have to do a pass of "cleanups" for coding style, or matters of code taste. E.g. they are too defensive and often over-use try/catch statements, they often over-complicate abstractions, they overbloat code (e.g. a nested if-the-else constructs when a list comprehension or a one-liner if-then-else would work), or they duplicate code chunks instead of creating a nice helper function, things like that... they basically don't have a sense of taste. They are indispensable in cases where I inch into a more vibe-coding territory where I'm less familiar (e.g. writing some rust recently, or sql commands, or anything else I've done less of before). I also tried CC to teach me things alongside the code it was writing but that didn't work at all - it really wants to just write code a lot more than it wants to explain anything along the way. I tried to get CC to do hyperparameter tuning, which was highly amusing. They are also super helpful in all kinds of lower-stakes one-off custom visualization or utilities or debugging code that I would never write otherwise because it would have taken way too long. E.g. CC can hammer out 1,000 lines of one-off extensive visualization/code just to identify a specific bug, which gets all deleted right after we find it. It's the code post-scarcity era - you can just create and then delete thousands of lines of super custom, super ephemeral code now, it's ok, it's not this precious costly thing anymore. Final layer of defense is GPT5 Pro, which I go to for the hardest things. E.g. it has happened to me a few times now that I / Cursor / CC are all stuck on a bug for 10 minutes, but when I copy paste the whole thing to 5 Pro, it goes off for 10 minutes but then actually finds a really subtle bug. It is very strong. It can dig up all kinds of esoteric docs and papers and such. I've also used it for other meatier tasks, e.g. suggestions on how to clean up abstractions (mixed results, sometimes good ideas but not all), or an entire literature review around how people do this or that and it comes back with good relevant resources / pointers. Anyway, coding feels completely blown open with possibility across a number of "kinds" of coding and then a number of tools with their pros/cons. It's hard to avoid the feeling of anxiety around not being at the frontier of what is collectively possible, hence random sunday shower of thoughts and a good amount of curiosity about what others are finding.

SUCCESS! I scored 10738 in King Thirteen! dev.js13kgames.com/2024/games/kin… #KingThirteen #js13k

@software_daily absolutely loved the 'adforprize' episode and it's format. Thank you for sharing and I hope to hear more!

Great point in #devopsdays Q&A: Don't just test your API, remember to test the clients that rely on it when you push API updates/changes.

Type a dutch word once, get multiple pages with search results: github.com/anton-107/dutc… @FluentForever #fluentforever

Cursor click effect codepen.io/cleric/pen/dIu… via @CodePen

Internationalisation is hard

Node.js and the new web front-end feedproxy.google.com/~r/nczonline/~…

@toivonens don't do that :)

@toivonens that's the exact feeling that everyone gets when coding apps with backbone

@toivonens но у них нет права на 30% рулинг

@toivonens эта карта дает безлимитный wifi. 3 часа - ограничение на библиотечный комп

@ppk feedly for the cloud, reeder as a client for feedly (feedly's own client is a bit annoying)

@toivonens после года катания на велосипеде амстердамские автомобильные пробки начинают казаться ужасными

@toivonens @Schiphol ура! :)

@toivonens мы тут в Амстердаме уже заждались :)

@andrebrov работает без перебоев?

This is epic: spreadsheet in AngularJS in 20 LOC thomasstreet.net/blog/spreadshe…

Achieved a new personal record with @RunKeeper: Distance... bit.ly/15JVIOU #FitnessAlerts

TXJS 1997 - 1997.texasjavascript.com Excellent JavaScript conference back in 1997. :-)