HackerTrans
TopNewTrendsCommentsPastAskShowJobs

enum

no profile record

Submissions

SlopOS: A tiny OS with the userland and parts of kernel in Scheme

github.com
2 points·by enum·5 個月前·1 comments

comments

enum
·5 個月前·discuss
Right. And the arguably simpler problem, where the model gets the C code directly, is active research: https://www.darpa.mil/research/programs/translating-all-c-to...

All of this work is extraordinarily impressive. It is hard to predict the impact of any single research project the week it is released. I doubt we'll ever throw away GCC/LLVM. But, I'd be surprised if the Claude C Compiler didn't have long-term impact on computing down the road.
enum
·5 個月前·discuss
This is a conjecture: modern chips are optimized to make the output code style of GCC/Clang go fast. So, the compilers optimize for the chip, and the chip optimizes for the popular compilers.
enum
·5 個月前·discuss
It’s in Rust…
enum
·5 個月前·discuss
Nice article. I believe the Claude C Compiler is an extraordinary research result.

The article is clear about its limitations. The code README opens by saying “don’t use this” which no research paper I know is honest enough to say.

As for hype, it’s less hyped than most university press releases. Of course since it’s Anthropic, it gets more attention than university press.

I think the people most excited are getting ahead of themselves. People who aren’t impressed should remember that there is no C compiler written in Rust for it to have memorized. But, this is going to open up a bunch of new and weird research directions like this blog post is beginning to do.
enum
·5 個月前·discuss
This isn't true right? You really can bring in zero dollars in grants and phone it in in the classroom. (Now, literally on Zoom!) I don't think it helps to pretend that everyone keeps pushing hard post tenure.

But, I think most people do. The system is deliberately designed to push an assistant professor so hard, that when they get a permanent contract, they're conditioned to keep pushing. It typically succeeds.
enum
·5 個月前·discuss
> For tenure-track professors at top-twenty schools, step five is hard. Their tenured professors jealously guard their status, so rejection is the default. However, as school ranking goes down, runaway nepotism swiftly supplants professorial pride. At schools ranked worse than fifty, acceptance is the default.

Like everyone else, I have always had the pleasure of being at a top-20 school (in some list or the other!). Fortunately, I think this article is only attacking tenure at schools rated lower. (Let me know if I misinterpreted the article.)

We could eliminate tenure at lower-ranked schools. I'm not sure who will teach there if we do. The 90th percentile salary for a new tenure-track professor is 145K (https://cra.org/wp-content/uploads/2024/05/2023-CRA-Taulbee-... page 49). Nobody competent is going to take that salary without the possibility of tenure.
enum
·5 個月前·discuss
I just have an unprivileged secondary local account and do ssh dummy@localhost.

Is this wrong?
enum
·5 個月前·discuss
This was vibe coded in a few hours with Codex 5.2 Medium. We now have examples of agent-written web browsers and Unix-y OSes (https://github.com/viralcode/vib-OS). I thought it would be interesting to try something a little more out of distribution. All done in a single Codex session -- transcript is part of the release.
enum
·6 個月前·discuss
Thanks. As I said, I have no idea. :)
enum
·6 個月前·discuss
I'm not sure this is true. Encoding theorems in dependent types takes a lot of expertise.

Even without the Lean technical details, a lot of math theorems just don't mean anything to most people. For example, I have no idea what the Navier-Stokes theorem is saying. So, I would not be able to tell you if a Lean encoding of the theorem is correct. (Unless of course, it is trivially broken, since as assuming False.)
enum
·6 個月前·discuss
The worst case is that you vibe code a theorem that reads:

False => P

Then you vibe code a proof of this theorem. Then you get excited that you’ve proven P.

Some of the X discussion that prompted the OP was quite close to this. There are screenshots on X of Lean code that doesn’t compile, with Lean being blamed.
enum
·6 個月前·discuss
The post says this in other words: in Lean, Rocq, or any other theorem prover, you get a formally-verified proof, but you do NOT get a formally verified theorem statement.

So, even if the proof is correct, you need to determine if the theorem is what you want. Making that determination requires expertise. Since you cannot "run the theorem", you cannot vibe-code your way through it. E.g., there is no equivalent of "web app seems to be working!" You have to actually understand what the theorems are saying in a deep way.
enum
·6 個月前·discuss
Referring to this: https://github.com/arjunguha/slopcoder

I then proceeded to use it to hack on its own codebase, and close a bunch of issues in a repository that I maintain (https://github.com/nuprl/MultiPL-E/commits/main/).
enum
·6 個月前·discuss
I'm trying to determine what programming tasks are not in this list. :) I think it is trying to exclude adding new features and fixing bugs in existing code. I've done enough of that with LLMs, though not in large codebases.

I should say I'm hardly ever vibe-coding, unlike the original article. If I think I want code that will last, I'll steer the models in ways that lean on years of non-LLM experience. E.g., I'll reject results that might work if they violate my taste in code.

It also helps that I can read code very fast. I estimate I can read code 100x faster than most students. I'm not sure there is any way to teach that other than the old-fashioned way, which involves reading (and writing) a lot of code.
enum
·6 個月前·discuss
I don't think I can scientifically compare the agents. As it is, you can use Opus / Codex in Cursor. The speed of Cursor composer-1 is phenomenal -- you can use it interactively for many tasks. There are also tasks that are not easier to describe in English, but you can tab through them.
enum
·6 個月前·discuss
I teach at a university, and spend plenty of time programming for research and for fun. Like many others, I spent some time on the holidays trying to push the current generation of Cursor, Claude Code, and Codex as far as I could. (They're all very good.)

I had an idea for something that I wanted, and in five scattered hours, I got it good enough to use. I'm thinking about it in a few different ways:

1. I estimate I could have done it without AI with 2 weeks full-time effort. (Full-time defined as >> 40 hours / week.)

2. I have too many other things to do that are purportedly more important that programming. I really can't dedicate to two weeks full-time to a "nice to have" project. So, without AI, I wouldn't have done it at all.

3. I could hire someone to do it for me. At the university, those are students. From experience with lots of advising, a top-tier undergraduate student could have achieved the same thing, had they worked full tilt for a semester (before LLMs). This of course assumes that I'm meeting them every week.
enum
·9 個月前·discuss
- https://publish.obsidian.md/aixplore/Practical+Applications/...

   Does it work if you change to torch.bfloat16?
- https://publish.obsidian.md/aixplore/Practical+Applications/...

  The PyTorch 2.9 wheels do work. You can pip install torch --index-url <whatever-it-is> and it just works. You do need to build flash attention from source, which takes an hour or so.
enum
·9 個月前·discuss
I think that personal computing is more fun than time-shared computing. :)

It's remarkable what can now be done on a whisper-quiet little box. I hope the Strix Halo's will be just as much fun, and they should be, so long as Flash Attention works.
enum
·9 個月前·discuss
I’m not complaining. The clusters are great. The non-Slurm H100s are great. The Spark is more fun.
enum
·9 個月前·discuss
+1

I have H100s to myself, and access to more GPUs than I know what to do with in national clusters.

The Spark is much more fun. And I’m more productive. With two of them, you can debug shallow NCCL/MPI problems before hitting a real cluster. I sincerely love Slurm, but nothing like a personal computer.