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.
It wonders me that a coupe of days ago I did the same with Unique and a single skill.md, repo: https://github.com/daedalus/uniq-reconstruction, on succes I tried with rar but failed. Kudos
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
> "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"
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.
Yes? What do you think fuzzing, unit testing, integration testing is for? It's an empirical evaluation of correctness. Literally just try and see.
For actual correctness verification in the strong sense, you'd need to start from a specification written in a formal language so that it's machine checkable, which if I had to guess not even win.rar GmbH has.
I added the second paragraph about formal verification at the same time you posted, in anticipation that you'd immediately dig your heels into it otherwise, despite me highlighting that the other methods are merely empirical.
I was immediately proven right once I pressed "update". That said, I have now deleted my snarky response that followed. Not in the game of capitalizing off of the human equivalent of a race condition.
I should make a browser addon to delay posting, this is the 2nd time this happens in the past few days.
Edit:
Nevermind, it's already a feature built into the site. Turned it on. I wonder if it applies to edits also...
Nope, doesn't seem to. Oh well, should still help.
> Well, it turned out that at some time during spec investigation, Claude needed to understand authenticity verification which is a paid feature. With a context full of reverse engineering tools it cracked WinRAR and bypassed product registration, then dutifully documented its crimes in the spec. The docs, when viewed, triggered OpenAI’s alarms and stopped it dead in its tracks. I squashed this out of the git history, and decided not to implement the feature at all.
You can draw your own conclusions as to what this says about the state of agentic development.
Really unsure why this is getting downvoted, to my understanding this is a massive, unsettled concern.
It wasn't even a disasm/pseudocode to formal spec flow, and then a separate human implementation. The same human has been in the loop throughout, and large parts of it were generated directly.
It's basically guaranteed tainted.
Edit: I should have skimmed a bit more patiently, there was in fact no "disasm/pseudocode + the human getting tainted" part to this apparently.
I read the post you're replying to as saying "this is copyright-encumbered and nonfree because it's a derivative work of everything in Claude's and GPT-5.5's training corpus", which is an argument I find fairly tiresome. (Realistically, if courts actually rule that this is the case, this tiny little project will be the least of anyone's concerns.)
"This is copyright-encumbered and nonfree because it's a derivative work of the legacy RAR binaries" is a different argument (and seems like it depends on details of the setup that were somewhat glossed over in the post).
The point is, excepting current legal standards which are already very murky, how can _you_ claim copyright, if you don't _know_ it isn't encumbered?
You can get these LLMs to generate copyrighted outputs both intentionally and accidentally. This is a known fact; therefore, if you're not checking the output to see if this has occurred then you're potentially generating legal risks for yourself and anyone who uses your code.
To not only ignore this for your own use case but to then release the code under a proclaimed license seems legally problematic if not ethically concerning.
If you did get sued for infringement I can't imagine that your defense would be that you find the argument tiresome? Honestly, do you think this would never happen, or how would you go about defending your actions here?
The human wasn't looking at the copyrighted code and was giving high level steering instructions. If you look at the spec generated it doesn't look like a derivative work of the copyrighted material. The program was generated from the spec. It seems mostly fine from my perspective.
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!
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"
As mathematicians say, optimization is left as an exercise to the reader. You did the hard part.
Kudos to the author. A fun read, thank you for sharing.
Maybe just cut the unprompted whining?
For actual correctness verification in the strong sense, you'd need to start from a specification written in a formal language so that it's machine checkable, which if I had to guess not even win.rar GmbH has.
Added, later: hey you changed your comment, added a whole paragraph.
I was immediately proven right once I pressed "update". That said, I have now deleted my snarky response that followed. Not in the game of capitalizing off of the human equivalent of a race condition.
I should make a browser addon to delay posting, this is the 2nd time this happens in the past few days.
Edit:
Nevermind, it's already a feature built into the site. Turned it on. I wonder if it applies to edits also...
Nope, doesn't seem to. Oh well, should still help.
No, it doesn't even need to compile. The mere fact that it's in Rust means it's correct.
Were you flagged for a cybersecurity violation?
You can draw your own conclusions as to what this says about the state of agentic development.
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?
It wasn't even a disasm/pseudocode to formal spec flow, and then a separate human implementation. The same human has been in the loop throughout, and large parts of it were generated directly.
It's basically guaranteed tainted.
Edit: I should have skimmed a bit more patiently, there was in fact no "disasm/pseudocode + the human getting tainted" part to this apparently.
"This is copyright-encumbered and nonfree because it's a derivative work of the legacy RAR binaries" is a different argument (and seems like it depends on details of the setup that were somewhat glossed over in the post).
You can get these LLMs to generate copyrighted outputs both intentionally and accidentally. This is a known fact; therefore, if you're not checking the output to see if this has occurred then you're potentially generating legal risks for yourself and anyone who uses your code.
To not only ignore this for your own use case but to then release the code under a proclaimed license seems legally problematic if not ethically concerning.
If you did get sued for infringement I can't imagine that your defense would be that you find the argument tiresome? Honestly, do you think this would never happen, or how would you go about defending your actions 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!