やっとAimeを物理カードからスマホに移行できた。スマホ一台でログインも決済もできる快適キャッシュレスオンゲキ環境を手に入れたが知らないとトラブルになる要素満点だから書いておこう。 #Aime

We've developed a secure paste feature replacing traditional clipboard APIs. Users will be able to take away clipboard access from apps to use this instead. It integrates into the standard selection toolbar, input methods, accessibility services and keyboard shortcuts. We plan to get it merged soon. A small subset of apps including those written in Flutter implement their own text selection toolbar. We've worked around this by adding a Paste button to the default keyboard. We'll be replacing AO…

Text

Andrej Karpathy

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They wi…

이런애들 왜케 속이시커멓게보이지

VM？

20,000+ people have already joined the waitlist. I’ll be closing access soon. https://t.co/Hmq7qRgPd3

More to discover

More to discover