Remix.run Logo
Remix clone Hacker News
new | show | ask | jobsGithub
▲ Microsoft agentically ports Copilot runtime to Rust for $120K(theregister.com)
24 points by pjmlp 2 hours ago | 17 comments
▲Rexxar an hour ago | parent | next [-]

They don't have to tell us they are vibe coding everything.

- there are now ridiculous vibe coded localisation in VS2026

- task manager started to not report cpu usage correctly recently (the number becomes stalled)

- file explorer display the "loading" icon infinitely on some directories

- and many other things!

▲chrischen 16 minutes ago | parent [-]

The line between vibe coding and just coding has now moved. Vibe coding is specifically when the output is not understood by the prompter. Even in the back in the days of the earlier models i used the models to do my basic typing because it was easier than me typing it out…

▲hollowturtle 12 minutes ago | parent | prev | next [-]

> The original TypeScript implementation completed 7.55 of those lifecycles per second, while Rust running in-process managed 120 per second - representing a 15.9x speedup on that particular workload.

Does this impresses/surprises anyone? Two folds: 1) I believe the most optimized JavaScript code could near the performance of this phase 1 port without optimizations. I would have gone with that first, many would think that would not be as cost efficient but: 2) optimizing the rust code will require 10x the effort of the 1 by 1 conversion, just because you now need idiomatic rust code that likely has nothing to do with a plain translation. So defeating the initial gain, there's nothing to do the bottleneck gets just pushed elsewhere

▲tecoholic an hour ago | parent | prev | next [-]

    One of the thorniest conversions was the session.ts file, which was over 30,000 lines of TypeScript that touched all aspects of the runtime.
This can’t be real. Single file with 30K lines? Which human being is working on it and how much RAM does it take for a code editor to load that with full symbol tree? I am genuinely curious. Is this common? I think most files I come across stretch to maybe 2-3k lines max.
▲Rexxar 38 minutes ago | parent | next [-]

30000 is not that big in very old projects with many contributors. There are always one or two files that no one wants to take the time and responsibility to clean up. And 30000 is not a big number for RAM. The fact that you find it choking is more and of an indication of how bad our tools have become than anything else.

For example, until recently the main file for donet runtime GC was more than 50000 lines (it has since been split).

▲wayvey an hour ago | parent | prev | next [-]

I recently saw a ~60k lines / 3mb .cpp file in one vibe coded project (and yes I was a bit horrified) Surprised it works at all but it apparently does. Not really for a human though and even for an LLM it would be more beneficial for it to be split up.

▲NewsaHackO 41 minutes ago | parent [-]

This has to be 1) early LLM vibe coding or 2) “hand” vibe codingwhere the user asked the LLM to code sections and stitches them together manually, and the programmer is a novice. The second part I speak from experience; got to ~2k before realizing this is out of the script range and started to break it up. Regardless, it would be almost impossible to get an SOTA LLM agent to ever do this.

▲formerly_proven an hour ago | parent | prev | next [-]

> Which human being is working on it

If you've ever used that tool you wouldn't ask this question, since it's obviously fully vibecoded.

▲smitty1e an hour ago | parent | prev [-]

Was the documentation for each function a full-on essay?

▲meerita 10 minutes ago | parent | prev | next [-]

I wrote to the post of Andrea (a dev from the Copilot team) about their 800K LoC: 128 PRs, shipped incrementally. Existing end-to-end tests ran against the new code at every step.

Half of the 832K LoC are mostly tests she answered:

> Yeap, 832,378 lines of production Rust. the +800K number is production only; unit tests are another +469K on top.

https://x.com/acolombiadev/status/2100660224298193081?s=20

▲jsnell 2 minutes ago | parent [-]

> Half of the 832K LoC are mostly tests she answered:

No? That quote is clearly saying the opposite of your summary.

▲dmix 30 minutes ago | parent | prev | next [-]

> agents converted 430,000 lines of TypeScript into 800,000 lines of production Rust

The +400k new lines were probably code comments the agents added to everything

▲amelius an hour ago | parent | prev | next [-]

Still hoping for a company to agentically port the python ecosystem to GIL-free python.

▲rienbdj 21 minutes ago | parent | next [-]

If runtime performance is the goal it’s easier to port the required libraries to another language at this point.

▲andrewstuart 43 minutes ago | parent | prev [-]

I did a lot of benchmarking of Gil free python.

Greenlets were much faster.

Gil free python gets stuck on all sorts of python locks. It’s slow.

▲perching_aix 35 minutes ago | parent | prev | next [-]

Is that why session compaction stopped working for me in VS Code at the end of last week, or is that just the integrated extension itself having a normal one?

Though it's the same extension that can't keep its session timestamps straight, randomly hides sessions I was just in (then suddenly remembers them after going in and out of a session), and completely shits itself visually when using OpenAI's models, so maybe it really is the latter.

▲andrewstuart 41 minutes ago | parent | prev [-]

Can we not say “agentically” please?