aka-rider
Joined 6 years ago
Joined 6 years ago
Jokes aside, Opus 5.5 and Fable 5.1 are on another level. I was recently vibe coding an app, and after three days of prompting or so: sigh “I need to bite the bullet, and finally face the slop” — I started to read the code, and to my surprise, it was adequate. Not an amazing code, not a slop either.
I cleaned it up in one session. 50k LoC of Golang. Although even language is less important nowadays. People make DSL, and LLMs immediately start programming on this DSL.
Writing Rust, Zig, or Go, you would still control memory manually, where it matters.
It would take at least some knowledge to hack, not just a random script from a forum.
Now, with LLMs, it's the '90s all over again.
Search Engine have chicken and egg problem, you can only have a good search if enough people use it to tune the ranking and see enough search spam cases.
“Just compete with a monopoly on their own field with one hand tied behind”
To be fair, I haven't try exactly "rewrite in Rust" prompt, but I cannot imagine for this to work.
Although, in the agentic environment, a benefit of not having GC at all definitely helps.
What is the scale? Because I'm pretty sure it's impossible to one shot 65k LoC with "good luck, make no mistakes" prompt.
I also did this within a subscription. I counted the number of tokens afterwards and calculated the cost as if I'm paying per token. $400 is of course arbitrary, but it's a ballpark number, bun was $165000.
> In my experience it mostly comes down to the harness (or lack of) that you use.
Yep, it is.
Tokens per task is a good proxy measure of skills, 'superpowers' or any other.
Either a skill gets you the thing more efficiently (less tokens), or you don't need to redo the result afterwards (less tokens). I benchmark all my skills that way.
Models need less and less steering at this point, especially frontier ones.
The way rune works with files minimizes chances of silent corruption. I keep original byte blobs immutable, separately there is a journal (kinda WAL) of positional deltas (inserts and deletes).
So I only need to validate that blob + deltas = snapshot.
Disk IO is encapsulated through VFS, and writes are atomics (write to a temp file, then rename).
Separate virtual rendering buffer is built on top of that. Rune, like Obsidian, renders markdown preview inline, so the same chunk could be rendered as "Header" as well as `## Header` when under the cursor.
All of that makes it quite easy to work with text. The core function is to translate offset in a byte array to line and column and back, which is pure math and relatively easy to test.
Another trick that helped a lot is to use sqlite extensively: blobs, deltas, vfs, redo and undo history graph are all sqlite tables.
I noticed that LLMs make stupid decisions when it comes to data structures, but they understand CRUD and SQL, so I turned all Rune's internals into dumb CRUD.
But somehow compiler has decided that i <= limit is always true.
In Ukrainian it’s «дощить» (from “дощ” — rain) — the form of the word tells you its function in the sentence. Same happens in other Slavic languages: Polish, Belarusian, Slovakian.
Latin languages rely on the order of words to explain their function. So much so, English speakers don’t say “blue big ball” in German, time before place is mandated.