cube2222

Joined 10 years ago

Karma
9,886
Submissions
1,701
Member since
Feb 29
Director of R&D Engineering at https://spacelift.io

email: jakub.wit.martin at gmail dot com

work email: kubam at spacelift dot io

linkedin: https://www.linkedin.com/in/jakubmartin

github: https://github.com/cube2222

Author of OctoSQL: https://github.com/cube2222/octosql

View on Hacker News

Recent submissions

Comment · 2 days ago
After the recent somewhat discouraging stuff with clickbench that made the news, I must say this blog post is very cool.

Sounds like you found an excellent way of structuring this problem to solve it with Claude (for those who don't click into the article - writing hand/claude-optimized Rust code for each query, checking its assembly, and trying to make their own optimizer generate something close to that same assembly), and the writeup is very interesting and readable too!

Kudos, looking forward to more blog posts like this one.

Comment · 1 month ago
Quickly reading the article, one notable limitation seems to be that these checkpoints are 512-1024 tokens context size models, while Jev is seemingly 32k.

That's a pretty big limitation, I would argue, unless I'm misunderstanding and it can be worked around easily somehow? I'm surprised it isn't surfaced more prominently in the comparison.

Comment · 2 months ago
Comment · 2 months ago
Yeah, I think I agree with this. I think making GUIs and reverse engineering proprietary APIs are two things that frontier models make really pleasant - e.g. I made a menu-bar app (very similar to your temperatures dropdown, similar graph, SwiftUI) which connects via bluetooth to my Inkbird CO2 sensor, graphs the CO2 level over time, and looks fabulous.

The skills are useful, thanks for linking them! They'll be useful for my future projects like this. FWIW I've had good luck with using Claude Design first to do mocks.

At the same time, I think there's still the "is this worth doing a hyper-customized version of this software, if I'm also then responsible for fixing the bugs?". But I think increasingly as we improve our agentic workflows and make them more self-contained loops driving the result to completion, this becomes kind of a non-issue.

In general, I do think LLMs are bringing about a new age of hyper-customization, which I welcome.

Comment · 2 months ago
Comment · 2 months ago
Yep, you can enable a catch-all for anything that’s not a predefined alias.

I’m using that setup and have no issues with it, for exactly the use-case you mentioned.

Comment · 2 months ago
Nice, as a European customer, I appreciate this.

Side note, I moved to Fastmail a couple years ago, and so far I’ve been very happy with it! The Gmail migrator works great, too.

Comment · 2 months ago
Comment · 3 months ago
I think the reason for this is that if you're targeting folks for whom Europe-sovereignty resonates as an important factor, those will also care about sovereignty and self-sufficiency in general, and thus just skip your SaaS and go right for (semi) self-hosting.

While for the other side where the sovereignty is not an important factor, it's product quality that matters.

You can absolutely make a European startup that sells B2B SaaS, successfully, it just has to be better than the competition, and being European will not be enough.

Comment · 4 months ago
Comment · 4 months ago
I think it’s worth emphasizing that based on the article, those are third party apps, not first party LG apps.

Based on the headline I thought it’s the built-in apps.

Comment · 4 months ago
Comment · 5 months ago
Comment · 5 months ago
Comment · 6 months ago
Love the writing style!

> Nothing beats an organic, pasture-raised, hand-written spec.

Hah, I strongly empathize with the wording. I’ve been starting my design docs for fellow humans with “100% hand-written, organic content”, I might steal a part of yours.

Overall, cool idea. I don’t see myself using your SaaS, but the approach of tagging the requirements and constraints to make them easier to find sounds good.

One project you didn’t mention which I think is also, I think, a cool perspective on this is codespeak.dev , but I haven’t given it a go yet.

All in all, I feel like maintaining specs, and having agents translate spec diffs into code diffs is a promising area for the future. Good thing I enjoy writing!

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton