271–280 of 478 posts
I've been working on wasm sandboxing and automatic verification that code doesn't have the lethal trifecta and got something working in a couple of days.
I'd like to do a clean rewrite at some point.
So review the code. Our rule is that if your name is on the PR, you own the code; someone else will review it and expect you to be able to justify its contents. And we don't accept AI commits. What this means in workflow terms is that the bottleneck has moved, from writing the code to reviewing it. That's forward progress! But the disparity can be jarring when you have multiple thousands of lines of code generated ev…
Totally agree. If I don’t understand the code as if I’d written it myself, then I haven’t reviewed it properly. And during that review I’m often trimming and moving things around to simplify and clarify as much as possible. This helps both me and the next agent. Using these tools has made me realise how much of the work we (or I) do is editing : simplifying the codebase to the clearest boundaries, focusing down the A…
Did it in one go, WAY better than I ever could have. Creates directories, generates configs from templates, all secrets are encrypted and managed etc.
I've iterated on it a bit more to optimise some bits, mostly for ergonomics, but the basic structure is still there.
---
Did a similar thing with Ansible. I gave claude a way to access my local computer (Mac) and a server I have (Linux), told it to create an ansible setup that sets up whatever is installed on both machines + configurations.
Again, managed it faster and way better than I every could have.
I even added an Arch Linux VM to the mix just to complicate things, that went faster than I could've done it myself too.
Earlier quoted context omitted.
Yes, I haven't even read most of the files, just threw it up there as an example for the OP (I too am tired of the lack of examples, so stepped up to the plate on this one). As a personal bit of development last weekend. I can see inconsistences myself, some of which result from scope creep during development (starting with the idea of a text-only app and then grafting on the web side) - it literally only started bec…
> Yes, I haven't even read most of the files, just threw it up there as an example for the OP (I too am tired of the lack of examples, so stepped up to the plate on this one). Right, kind of like an LLM skimming and missing the core points :) OP didn't ask for "Anything you've vibe-coded" but explicitly asked for code written with LLMs that is high quality and structurally sound, and "creates more value than it creat…
I've been programming for 20 years, and I've always been under-estimating how long things will take (no, not pressured by anyone to give firm estimates, just talking about informally when prioritizing work order together). The other day I gave an estimate to my co-worker and he said "but how long is it really going to take, because you always finish a lot quicker than you say, you say two weeks and then it takes two…
> "but how long is it really going to take, because you always finish a lot quicker than you say, you say two weeks and then it takes two days"
However these statement just kinda makes your comment smell of r/thatHappend. Since it is such a tremendous speed up.
Therefore I am intrigued what kind of problems you working on? Does it require a lot of boilerplate code or a lot of manually adjusting settings?
Earlier quoted context omitted.
[flagged]
I've never had a job where writing Javascript has been the primary language (so far it's been C++/Java/Golang). The JS Chrome Extension is a fun side project. Using Augment in a work context, I'm primarily using it for Golang and Python code, languages where I'm pretty proficient but AI tools give me a decent efficiency boost. I understand the emotional satisfaction of letting loose an easy snarky comment, of course,…
Earlier quoted context omitted.
> Yes, I haven't even read most of the files, just threw it up there as an example for the OP (I too am tired of the lack of examples, so stepped up to the plate on this one). Right, kind of like an LLM skimming and missing the core points :) OP didn't ask for "Anything you've vibe-coded" but explicitly asked for code written with LLMs that is high quality and structurally sound, and "creates more value than it creat…
NP, and the exact definition of vibe-coding is, I think, yet to be determined. This wasn't a yolo, it was read all the prompts and generally accept them. Overall I'd say the code and web page are at least of a quality I've seen in many commercial settings; the code itself looks reasonable and if I was to do anything to it for a real 'release', I'd update the documentation which has suffered due to the extensive scope…
Huh? No, that's been established since Karpathy coined the term; you don't review the code, only use the agent and don't care about how it was done, just about the results.
The actual interesting stuff is how to use LLMs together with a human, to build high quality code. More "augmenting the human intellect" rather than "autonomous robots building for you".
Overall I'd say if someone handed you a specification that named SSE specifically, you created files with SSE in the name, and the implementation talks about doing SSE, yet it doesn't actually do SSE in the end, it's pretty much on par with code in commercial settings, yeah :) But maybe our bar should be slightly above the ground at least? :)
I think it depends on your tooling, your code-base, your problem space, and your ability to intelligently inject context. If all four are aligned (in my case they are) it's the real deal.
Yes. The company I am working at currently is using it extensively and I have seen first hand what their senior people are producing with the AI, and I rarely have any comments. It's adding huge value, and increases the velocity of delivery. I think it depends on your tooling, your code-base, your problem space, and your ability to intelligently inject context. If all four are aligned (in my case they are) it's the r…