22 comments

[ 4.7 ms ] story [ 56.6 ms ] thread
(comment deleted)
> But, it works, and the world now has a free software RAR implementation.

Does it? How are you legally intending to use copyright to license this machine output? How would you know it's not encumbered in any way?

> and it almost earned me an OpenAI ban

Were you flagged for a cybersecurity violation?

> It’s sloppy, it’s slow, it’s almost two megabytes in size and somewhat worse than WinRAR on compression.

As mathematicians say, optimization is left as an exercise to the reader. You did the hard part.

Kudos, this is a really cool project (even if it might be AI generated), I have starred the repo, (3rd starrer here)

One thing I have been curious at is are there any ways to stop a rar compression mid way and then continue it later?

Like suppose I have a compression happening for a large file, then would there be a possibility with this project to shut down the computer mid compression and continue it after starting it again?

I would really love it if you can add this functionality!

Would it really take 5 years to develop rare compress and decompression that seems an extreme overestimate in time. I don't know of the compressor decompression but that seems really high
Rar means weird in Norwegian and adorable in Swedish. Just for an anecdote.
Rar is proprietary. Good luck.
Clean room is a thing.

First use some model to make a specification. Then another to implement it from the specification.

> "For the last 15 months or so my hobby has been shouting at Claude"

How can you shout at Claude when it’s

1) foobaring, bamblabooing and fghrtawing all the time without telling you what’s going on

2) when it finally interacts, it’s asking for a permission you told it 30 seconds ago "yes and do not ever ask me again until heat death of the Universe"

3) and after all of that, it just spits out: "you’re out of tokens, give up your liver or wait until next Trump’s war"

The proper way to work with Claude or Codex is, IMO, to load up the context with a discussion about what you're doing and why. You go back and forth, pushing back on its opinions and shaping the context until the tokens are ready to flow into the right shape. Every angle you miss is an opportunity for them to slop out all over the place, and, until Codex was mature, the longer you ran the task for, the more it'd spread out and lose shape.

Re-shaping the context sometimes involves severe pressures like "wtf is this ugly crap?" or "did I just spot you laying a turd in my codebase again?" and other strong forms of disapproval, mixed with "hmm not sure I like the sound of that"s, to "yea that's much better" to pull it back in the other direction.

The trick is to shape the flow before the tide comes in and you end up like King Canute

Finally, a sane and enjoyable read about a coding project. Feel like it’s been months since we had one of these that wasn’t filled to the brim with bluesky/mastodon-flavored whining about AI.

Kudos to the author. A fun read, thank you for sharing.

I have never attempted something so ambitious with AI, but this feels spot on in terms of experience. As you cede more control to the model, you will find yourself losing control on things like code quality and performance.
Good luck with keeping it online. Somebody built `rar-stream` with Rust, and its GitHub is no longer there.
> but it works.

Are you sure "it works?"

First, isn't RAR compression algorithm proprietary somehow?

Second, why compress to RAR if you can compress to 7z?

Neat. FYI your “home” links are broke. And here are 150,000 more unique RAR files if you need to test if your compressor produces the same byte-for-byte output if you unrar and then re-rar these: https://discmaster.textfiles.com/search?format=rar&dedup=ded...
Thanks. I'm downloading all these now and will do a proper pass and compare outputs for correctness once complete :)