rmonvfer

lmao, agent powered development at its finest.

Reminds me of the guy who recently spammed PRs to the OCaml compiler but this time the script is flipped and all the confusion is self inflicted.

I wonder how long will it take us to see a vibe-coded, slop covered OS or database or whatever (I guess the “braveness” of these slop creators will (is?) be directly proportional to the quality of the SOTA coding LLMs).

Do we have a term for this yet? I mean the person, not the product (slop)

Uses kubernetes, blames others for over engineering. Are we living in a parody? Oh wait…

I mean maybe the content is not AI generated (I wouldn’t say it is) but the website does have an AI generated smell to it. From the colors to the shapes, it looks like Sonnet or Opus definitely made some tweaks.

Spaniard here. Let me know if I can somehow help navigate all of that. I’m very interested in history and everything related to the 1400-1500 period (although I’m not an expert by any definition) and I’d love to see what modern technology could do here, specially OCRs and VLMs.

This looks great, but I’m a bit confused about what actually exists right now. The site uses the present tense (“it is”, “we are”), but I couldn’t find anything after browsing and clicking around for about 15 minutes. From the “log”, it sounds like only the parser for R Prime is implemented, and that R Prime itself is just a precursor to the actual language that will be used to develop the whole system (from scratch?). Does that mean that R Prime has to be fully developed before work on its successor can even begin?

If anything is already working, where’s the code? Can people contribute yet?

Not trying to nitpick, but it’s hard to tell what’s real vs. vaporware (beyond the author’s very impressive abilities for systems/language design and writing)

The website also mentions a device but I get that’s many years away too, right? I mean how long will it take to actually develop everything that’s described in the website?

I’m not a “C” person but I’ve really enjoyed reading this, it’s quite approachable and well written. Thank you for writing it.

This looks awesome. I’m a very heavy Claude Code user (and Codex) in both the CLI and VS Code (and now in the web too!) and it’s quite infuriating when the agent just gets lost after context compaction and I have to point it to read CLAUDE/AGENTS.md (and update it if a lot of changes have been made)

I tried Windsurf a while back but I’ll definitely come back ASAP just to play with this and see how it does in a somewhat complex project I’m working on.

Kudos to the team!

The only way this might work (IMO) is writing the tests yourself (but of course, this requires you to plan and design very meticulously in advance) and doing some kind of “blind TDD” where the LLM is not able to see the tests, only run them and act on the results. Even then, I’ve had Claude (Opus 4.1) bypass tests by hardcoding conditions as it found them so I’d say reliability for this method is not 100%.

Having the LLM write the tests is… well, a recipe for destruction unless you babysit it and give it extremely specific restrictions (again, I’ve done this in mid to large sized projects with fairly comprehensive documentation on testing conventions and results have been mixed: sometimes the LLM does an okay job but tests obvious things, sometimes it ignores the instructions, sometimes it hardcodes or disables conditions…)

I read HN every day, it seems kinda crazy I missed this…

UNED by any chance? Broken indeed

As an avid Claude Code user, I can tell you with 99% probability, that README is LLM-generated. This exactly the same structure and wording used by Claude (of course, it has some human modification because otherwise I’d filled with emojis)

In my experience, when you work with something like agentic development tools, you describe your goals and give it some constraints like “use modern zig”, “always run tests”… and when you ask it to write a README, it will usually reproduce those constraints more or less verbatim.

The same thing happens with the features section, it reads like instructions for an LLM.

I might be wrong but I spend way too much time using Claude, Gemini, Codex… and IMHO it’s pretty obvious.

But hey, I don’t think it’s a problem! I write a lot of code using LLMs, mostly for learning (and… ejem, some of it might end up in production) and I’ve always found them great tools for learning (supposing you use the appropriate context engineering and make sure the agent has access to updated docs and all of that). For example, I wanted to learn Rust so I half-vibed a GPUI-based chat client for LLMs that works just fine and surprisingly enough, I actually learned and even had some fun.

In my (totally limited) experience, most non-tech people don’t even know what Meta is. WhatsApp is almost the only messaging platform used where I live (and pretty much everywhere outside the US).

I remember doing Bug Bounty for Meta a while ago and telling some friends and family about it, and I had to repeatedly explain they _are_ Facebook and WhatsApp and Instagram and many other things because they would look at me like I was talking about aliens.

This made my day. Great alias!

The source for one of the initial versions got leaked a while ago and let’s say it’s not very good architecturally speaking, specifically when compared with the Gemini CLI, which it open source.

The point of Claude Code is deep integration with the Claude models, not the actual CLI as a piece of software, which is quite buggy (it also has some great features, of course!)

At least for me, if I didn’t have to put in the work to modify the Gemini CLI to work reliably with Claude (or at least to get a similar performance), I wouldn’t use Claude Code CLI (and I say this while paying $200 per month to Anthropic because the models are very good)

I’m pretty sure he’s quoting the book

I use Arc as my primary browser but, well, I guess I won’t be using an Atlassian browser (only thinking about it sounds insane) because we all know what will happen with telemetry and tracking.

I’ve been using Zen [1] on and off for some time but it’s time to go full time on Firefox again!

It’s such a shame tho, Arc is a great browser and I’ve felt more productive using it, not to mention the UI, which is cleaner and just slicker than any other browser.

[1] https://zen-browser.app

I’d like to add: keep some kind of development documentation where you describe in detail the patterns and architecture of your application and it’s components.

I’ve seen incredible improvements just by doing this and using precise prompting to get Claude to implement full services by itself, tests included. Of course it requires manual correction later but just telling Claude to check the development documentation before starting work on a feature prevents most hallucinations (that and telling it to use the Context7 MCP for external documentation), at least in my experience.

The downside to this is that 30% of your context window will be filled with documentation but hey, at least it won’t hallucinate API methods or completely forget that it shouldn’t reimplement something.

Just my 2 cents.

I’ve been writing a tool to enable Claude Code to use ACP (because I use CC and Zed a lot) and so far I’ve been pretty successful (using the Claude Code SDK and the ACP Client library) although there are some rough edges. I will polish it a little bit and publish it tomorrow I guess.

I don’t get it, this is just a font, right? I mean, don’t get me wrong, I understand the need for these announcements but it feels… cringe? Like, it certainly cannot be THAT deep

Looks neat! I’m using C in a little side project and it would benefit from a simple GUI, let’s see what I can do with this. Also, just a recommendation but there isn’t even a single screenshot and I’d say that’s pretty important in a GUI library.

lmao good one

If they run out of letters, will they eventually raise a series AA?

I just run them at the same time. As long as each instance is working in different parts of the codebase, there should be no problem. No worktrees needed!

What what? Are they working on a proper GUI? This is actually massive if true

I’m not a heavy JS/TS dev so here’s an honest question: why not use Bun and forget about node? Sure I understand that not every project is evergreen but isn’t Bun a much runtime in general? It supports TS execution from day 1, has much faster dependency resolution, better ergonomics… and I could keep going.

I know I’m just a single data point but I’ve had a lot of success migrating old node projects to bun (in fact I haven’t used node itself since Bun was made public)

Again, I might be saying something terribly stupid because JS/TS isn’t really my turf so please let me know if I’m missing something.

To be honest, this was just a matter of time. As a long time Python developer, I just can’t wrap my head around the lack of something like this. GitHub was going to get hosted packages for Python but never did because it “didn’t align with their strategy objectives and a reallocation of resources” [1] (or some other similar corpospeak) Astral is a great company and I think we can’t question what they’ve achieved and provided to the Python community. uv is a game changer and solves one of the core issues with Python by providing a unified tool that’s also fast, reliable and easy to use. In fact, after using uv for the first time (coming from a combination of pyenv + poetry) I never wanted to go back and this is something all of my peers have experienced too. I’m glad it’s Astral who is doing this, and of course they will have to make money one way or another (which is perfectly fine and I don’t think anyone on this forum can be against that, as long as they are actually providing real value) but I was honestly tired of the paralysis on this matter. I did try to build a registry (pyhub.net) but being just one person with almost no resources and having another full time business made it impossible. Anyway, congrats to the team for the effort! [1] https://github.com/orgs/community/discussions/8542

I use both and Jan is basically the OSS version of LM Studio with some added features (e.g, you can use remote providers)

I first used Jan some time ago and didn’t really like it but it has improved a lot so I encourage everyone to try it, it’s a great project

This, I’ve already said it in another reply but FastAPI is 10x harder to use because of this. I’ve had to read FastAPI code many times to literally reverse engineer features because they are not documented in any way.

Documentation is for reference, tutorials are for learning, I just don’t even understand how maintainers don’t go crazy with the absolute lack of references…

And SQL Model is even worse in that regard.

Thank you! I’m actually pretty happy with what I’ve built tbh and how far has FastAPI taken us but this repo is proof that you have to reinvent the wheel if you want to build something serious.

In any case, that’s a treasure trove right there!, I actually had no idea Polar was open source, much less that it’s built on FastAPI!

It’s such a shame that the actual documentation doesn’t even scratch the surface, I would’ve saved so much time if they just included a disclaimer along the lines of “Hey, this architecture we are showing here it’s only valid for toy projects, you will need much more work to build a real production system” but again, I guess I’m the only one to blame.