HNHacker News
TopNewBestAskShowJobs

hdjrudni

569 karma · joined July 18, 2018

submissionscomments
hdjrudni··on Why does Opus 5 feel worse to work with?
So let's make a benchmark wherein the agent can ask questions. Define a hidden FAQ for each task that will only be revealed when the agent asks.
hdjrudni··on DeepSeek V4 Flash 0731
Well, I'm impressed.

Someone else here said we could get the model via OpenCode Go for $10/mo and get about $120 worth of credit, so I decided to give it a whirl. My first month is actually $5.

In the 3 hours I've been using it I've burned 3% of my 5-hr, 1% of my weekly and 0% of my monthly.

It's fixed 3 or 4 issues in my C++ game, despite not having visual capabilities to see the screenshots I was trying to give it. One-shotted them too.

Luna struggled with what I thought was an easy task (had to replace a few ASCII chars with the correct unicode char but kept choosing incorrectly).

I'll keep using it.

hdjrudni··on TSON – A JSON superset with immutable, hash-pinned schemas
Author doesn't like protos.

> Protobuf even marks the required keyword a hazard developers must avoid. These rules exist because a single definition is forced to serve every document ever written against it. TSON removes this burden because schemas are immutable.

I personally don't have a problem with them. They've grown on me. Thought they looked icky before I actually had to use them. Now I see their merit.

hdjrudni··on TSON – A JSON superset with immutable, hash-pinned schemas
> Version 2 just added a new required email field to the person record. In mutable schema systems, adding a new required field is universally forbidden. The API guidelines for Google, Microsoft and Zalando all ban the practice. Protobuf even marks the required keyword a hazard developers must avoid. These rules exist because a single definition is forced to serve every document ever written against it. TSON removes this burden because schemas are immutable. A version is simply a new document with a new hash. Two contracts coexist at full strength, and employee composing person inherits the new requirement in the same declaration.

I don't understand how this helps. That just means I have dozens of schemas for the same data set. How is that better? I'd rather have one lowest common denominator schema for the entire data set and be forced to validate.

I mean I guess because the data blob specifies its own schema I can use that schema to ensure the blob is valid but then what. What is my code that processes this data supposed to do? `if(schema1) { ... } else if(schema2) { ... }`. How is that better?

hdjrudni··on Karpathy’s Pelican
I suppose. But real human-made games require lots of play testing to become fun. Maybe we just have the AI churn something out, have humans play it, and iterate. It could still speed up the overall dev time.
hdjrudni··on How to Block Some of the Bots
I wonder why you'd be unable to read it? :-)
hdjrudni··on 98.css
As opposed to tabs that either (a) get so small they're illegible, or (b) scroll off the screen so they're no longer accessible?

The moving tabs issue we can fix but just not moving them.

And the vertical space issue is much less of an issue now than it was then because we have higher resolutions but the answer to that is to start closing tabs when you can no longer see your content. It's like a quiet little nag that says you have too much stuff open.

hdjrudni··on Show HN: IKEA Complexity Index
I hired a guy to assemble a desk...he did a shit job. Won't be doing that again.
hdjrudni··on The human-in-the-loop is tired
Amusingly, when I know my peer is just going to point his AI at my feedback, I write for their AI, not for them. I'm much more curt. Maybe not so amusing but I don't feel bad about dumping a laundry list of fixes for them.
hdjrudni··on The human-in-the-loop is tired
I don't even want to put 'my' code or apps out into the wild anymore. I've built a a few things I think are useful and I'm using myself but I'm afraid it'll just get called slop or my only users will be bots. What's the point. So I don't get the joy out of sharing it nor the joy of the achievement. But I've widdled down what I thought was an endless backlog of features to nearly zero, I guess that's something.
hdjrudni··on Baml: The Programming Language for Agents
This looks pretty nice for humans too actually.

The "for agents" is a bit of a turn off for me. Are they just trying to jump on the AI hype train or is this really AI-centric? Because if its for agents and only agents then I guess I should expect it to get progressively worse for humans but its for humans & agents then maybe it stays a nice clean human-friendly language.

hdjrudni··on Codex Micro
It's actually kind of funny that the purpose of the Turbo button was to slow your computer down so you could play games that were running too fast.

But I guess they didn't want to put a "Slow" button on their PC towers.

hdjrudni··on Designing APIs for Agents
I did that too but not for the sake of the LLM, just for myself. Massively helps discoverability. It also protects from backwards-compat if you ever want to change a default without breaking existing users, knowing that whatever they had before has already been saved into their settings so some setting doesn't randomly change on them.
hdjrudni··on Designing APIs for Agents
My work recently changed an agent API. It was a certain CLI tool built for agents which I had copied into one of my Skills.

What they did was kind of clever. When the agent calls the old API/uses old args, I guess they told it to tell the human to fix their skill and 'upgrade' to the new API. They even provided a skill upgrader skill.

Anyway, my agent tried calling it the old way, must have received some sort of error message and then diligently reported to me that my skill needed upgrading and we should be doing it some new way.

Kind of like reverse feedback I guess? Not the AI giving feedback to them, but them giving feedback to me via my AI.

hdjrudni··on Today I Rescued 7,234 Old GIFs
There's probably some efficiency to it too. Encoding a dozen images as one and load them in one request will be quicker than 12 separate images each with their own overhead.
hdjrudni··on Today I Rescued 7,234 Old GIFs
Really? <map> was also supported since Chrome and Firefox 1. Is ismap older yet?

https://developer.mozilla.org/en-US/docs/Web/HTML/Reference/...

hdjrudni··on C++20 Improved the For-Loop Syntax
I don't like that semi-colon. AFAICT `i, s;` is not an independent statement. `i, s: vec` would have been fine, but `;` ?!?! madness.
hdjrudni··on C++20 Improved the For-Loop Syntax
> That one actually shows what the variable is initialized to. This one doesn't. reply

Which variable? `i` is clearly initialized to `0` and `it` doesn't have an initializer per se... it starts at the first value of the container.

It almost seems like an abuse to put 2 unrelated things in the `for(...)` but that's what they did.

hdjrudni··on GPT-5.6
I've been wanting to make an RTS but found it a bit daunting. I thought this might be a bit challenging for LLMs too but I guess not! This is nice to see.
hdjrudni··on Rewriting Bun in Rust
> I was hoping it’d end in a “so how much did this cost?” so that others team looking at similar migrations have an estimate on what they can expect

It was in the middle. $165k.

hdjrudni··on Rewriting Bun in Rust
Isn't that equivalent? The task here was port Bun from Zig to Rust. He's saying that task will cost more.
hdjrudni··on Rewriting Bun in Rust
It's only 4% unsafe and most of it is single-line pointers that came from C++

> At the time of writing, about 4% of Bun's Rust code sits inside an unsafe block (~13,000 unsafe keywords across ~27,000 lines / ~780,000 lines), and 78% of those blocks are a single line — a pointer that came from C++, or one call into a C library.

I don't know much about Rust but I imagine this is safer than 100% 'unsafe' code in Zig or C++.

hdjrudni··on Rewriting Bun in Rust
Box3D just showcased some stuff including deterministic replays. If you wanted to port that, you could probably import the replay and make sure it plays back the same way in your new language. I think it captures the inputs and forces applied, not the pixels.

I suppose rendering is a component of a game engine too though, not just physics. I don't know how to do that reliably. Even if you captured pixels, it'd be annoying. If you've ever tried doing screenshot based diffing on web you will know that slight changes in aliasing in Chrome bugger everything up. Things that should be equivalent randomly aren't but not in a way that any human would care.

hdjrudni··on GPT‑Live
At first I was really impressed, I thought granny was the voice. But it turns out it's the same kind of annoying voice and tone. And then Constance starts talking to it and it immediately cuts her off at 1:05, after they just explained it was better at conversation flow.

Seems a bit disappointing, but the 3 overlapping questions example was impressive.

hdjrudni··on GPT‑Live
I don't think it needs an 'internal clock'. It needs two things. (1) the timer tool, (2) to know not to lie about having a tool or using a tool. I think (2) is the hard thing.
hdjrudni··on Silent speech with ultrasound
> The two biggest hardware challenges are reducing the size and weight of the ultrasound probe and replacing ultrasound gel with a more practical coupling material, such as hydrogel. We think both are solvable, making it possible for the probe to eventually become a lightweight wearable or adhesive patch.

Not sure I'd want to put an adhesive patch on my neck every morning so I can silently talk to an LLM in the cubicle farm. I hope this is not our future.

Very cool tech though and surprisingly good results for so little training.

I think time might be better spent improving a lip reading model (no adhesive required), assuming we're unable to read brainwaves directly.

hdjrudni··on Why TypeScript 7.0 Was Rewritten in Go
The entire article is speculation. The real answer was posted by Ryan Cavanaugh in the official repo over a year a go: https://github.com/microsoft/typescript-go/discussions/411 Why would trust anything else?
hdjrudni··on Rlm-Workflow
I've used a very similar workflow somewhat by accident for some larger changes. I'll be chatting with Codex about the best way to implement and watch my context slowly dwindle down, so I ask it to write out the plan to some dir (e.g. tasks/some-feature/). I recently had it write out a 10 step plan, as in 10 large, detailed files. I just ask it to implement the first file in a fresh context, check it over, get it to fix anything up, then start the 2nd file in a fresh context. It was smart enough to document 'deliverables' and verification for each step. Worked relatively well.

Might not be a bad idea to formalize this process with a skill.

hdjrudni··on FrankenMarkdown
What does "clean room" mean here and why is it important?

Also the task list (checkmarks) render poorly in PDF.

Also why wouldn't rendering the same doc twice produce the same byte output?

hdjrudni··on 2026 Unslop AI-Written Fiction Contest Results
This one is a fair point... if all the characters have distinctive names then NPC can plausibly become aware that it is a character in that game and spoil things. I don't know how to stop that, short of training a clean model from scratch, but that seems a bit much for a game.
← PreviousPage 3 of 13Next →