News for hackers. Stuff that matters.

mikaelaast

Show HN: Screenstab (tilt-shift-style screenshots) is now free and open source

I built Screenstab [1] as a solo developer to make it easier to create the tilt-shift-style screenshots often seen in product launches, landing pages, blogs, and tech journalism.It used to have a paid PRO version, but I’ve decided to make the whole app free as well as open source. All former PRO features are now included in the free version: watermark-free exports, HD export, ambient colors,...

( Read More... | no comments | 3 points | on HN )
Re:We need an accounting system for cognitive debt on Saturday July 04, 2026 @01:36PM (#48787190)
That’s very intriguing. I guess it would involve specifying a mental model in clear enough terms for it to be comparable to an already verified model, or something.

Tell HN: We need an accounting system for cognitive debt

The term “cognitive debt” is gaining ground [1]. We can now produce code faster than we can understand it. The bottleneck is real, and so is the feeling of being choked. The situation is not new. We have always had code no one quite dares to touch. Agentic coding makes it much worse. You probably know the feeling. Everything can look fine. The code compiles. The tests are green. The pull...

( Read More... | no comments | 2 points | on HN )
Re:Ask HN: Is understanding code becoming "optional"? on Saturday January 31, 2026 @02:20PM (#46839830)
I like this. The few-shot example snippet method is something I’d like to incorporate in my workflow, to better align generated code with my preferences.
Re:Ask HN: Is understanding code becoming "optional"? on Saturday January 31, 2026 @01:44PM (#46839413)
(Those are hardly analogous comparisons to LLM generated code, are they?)

So you do a vibe check?

Re:Ask HN: Is understanding code becoming "optional"? on Saturday January 31, 2026 @01:30PM (#46839250)
If it’s in the second category, I struggle not to mentally model it. How do you stop yourself? And should you?
Re:Ask HN: Is understanding code becoming "optional"? on Saturday January 31, 2026 @01:28PM (#46839224)
How do you verify the code without actually looking at it?
Re:Ask HN: Is understanding code becoming "optional"? on Friday January 30, 2026 @06:32PM (#46831466)
Creating work for the clean-up crew and leaving good money on the table for them (because it ain't gonna be cheap).
Re:Ask HN: Is understanding code becoming "optional"? on Friday January 30, 2026 @06:28PM (#46831435)
Yes, and I like the points you are making. I feel like the mental models we make are exercises in a purer form of knowledge building than the code artifacts we produce. A kind of understanding that is liberated from the confines of languages.

Ask HN: Is understanding code becoming "optional"?

On Twitter, Boris Cherny (creator of Claude Code) recently said that nearly 100% of the code in Claude Code is written by Claude Code, and that he personally hasn’t written code in months. Another tweet, from an OpenAI employee, went: "programming always sucked [...] and I’m glad it’s over."This "good riddance" attitude really annoys me. It frames programming as a necessary...

( Read More... | 41 comments | 4 points | on HN )

Tell HN: "Write less code" now means two different things

I was the bemused recipient of a couple of Twitter screenshots in a Slack DM this morning. One was Boris Cherny saying pretty much 100% of Claude Code's code is written by Claude Code, and that he personally hadn’t made even small edits by hand for months. The other was a Member of Technical Staff at OpenAI saying programming "always sucked" and when asked what percentage of...

( Read More... | 1 comment | 2 points | on HN )
Re:Skills Officially Comes to Codex on Saturday December 20, 2025 @08:45AM (#46336151)
Yes. It would make it much easier to evaluate results if the input contents were parameterized and normalized to some agreed-upon structure.

Not to mention the advantages it would present for iteration and improvement.

Re:Skills Officially Comes to Codex on Saturday December 20, 2025 @07:12AM (#46335608)
Sure. Verifiability is far-fetched. But say I want to produce a statistically significant evaluation result from this – essentially testing a piece of prose. How do I go about this, short of relying on a vague LLM-as-a-judge metric? What are the parameters?
Re:Skills Officially Comes to Codex on Saturday December 20, 2025 @06:49AM (#46335496)
Are we sure that unrestricted free-form Markdown content is the best configuration format for this kind of thing? I know there is a YAML frontmatter component to this, but doesn't the free-form nature of the "body" part of these configuration files lead to an inevitably unverifiable process? I would like my agents to be inherently evaluable, and free-text instructions do not lend themselves easily to systematic evaluation.
Re:Diamond Subpixel Arrangement Simulator on Saturday January 13, 2024 @04:45AM (#38978486)
I love this. I tried doing sub-pixel simulation for a tool I created (screenstab.com if anyone’s interested – yeah I know, shameless plug, etc.). I ended up abandoning the sub-pixel aspect in my shader because of the distracting patterns caused by the Moire effect.
Re:Bead Patterns on Sunday July 30, 2023 @06:32AM (#36929757)
Shameful (-less?) plug: I’ve implemented dithering for creating bead patterns from images in my web application Beadifier https://www.beadifier.com

Ask HN: Will a digital experience ever emulate the joy of a physical blank page?

Twenty years ago, instead of a smartphone, I used to carry around a notebook. I would bring it with me everywhere, and whenever I had a spare moment, I would take pleasure in sketching out cool inventions and devices, imagining fictional worlds or characters. The notebook functioned as a workout for my creative muscle.Today, the smartphone has taken the place that my notebook once occupied in...

( Read More... | 4 comments | on HN )

Show HN: Text-to-Texture (ChatGPT Plugin)

Hello HN! I've been experimenting with ChatGPT plugins and developed a small plugin named "Text-to-Texture". It leverages ChatGPT to translate natural language into parameters for a set of SVG filter primitives, allowing users to create textures without in-depth SVG knowledge.In essence, this tool aims to make parts of SVG more approachable. The code output serves as an...

( Read More... | 1 comment | on HN )

Older »