Opus 5 left, Opus 5.2 right. No search. Pretty massive difference!
Claude Opus 5.2 (they seem to be skipping 5.1 based on slugs specifically referencing "5.2" popping up recently) is likely being greyscale tested on Claude Code under the "Opus 5" name
Claude Opus requests on Web still go to the older model.
Posted by leo 🐾, 15 minutes ago
Claude Opus 5.2 (they seem to be skipping 5.1 based on slugs specifically referencing "5.2" popping up recently) is likely being greyscale tested on Claude Code under the "Opus 5" name
Claude Opus requests on Web still go to the older model.
Posted by leo 🐾, 15 minutes ago
Re: Ask HN: What are you working on? (September 2026)
I've been working on a voxel game engine called Bonsai for ~10 years.
Probably the most interesting thing about it at the moment is the editor. The world, and most things in it, are represented as collections of SDFs. More accurately, they're density fields, but, potato-tomato.
Bonsai has undergone a large rewrite over the last couple years that's nearing completion. A world edit is defined as a bunch of SDF parameters which get projected/rasterized into the voxel grid by a shader on the GPU. One neat thing about SDFs is they've been thoroughly researched and documented by a guy named Inigo Quilez, and they have a lot of nice mathematical properties. For example, you can do a smooth union of arbitrary SDFs to get nice rounded contours where shapes join.
I've written every system from scratch, all the way from the memory allocators and font rasterizer to the collision detector and simulation loop. I even wrote a metaprogramming language as a replacement for C++ templates, which is a whole other story. IIRC the only external dependency is the C runtime library for starting the process and my very occasional use of variadic functions arguments.
For a long time, an explicit non-goal of the project was to ship a game. It sounded insane to me to write an entire 3D engine and then ship a game. As it turns out, I've gotten it to the point where I can actually make a game. I've got a start on the game systems in a closed-source repo, and hope to have a steam page for it by the end of the year.
I'll do some shameless self-promotion and leave some links here for anyone interested in looking at the engine, language code, or some pretty pictures.
https://github.com/scallyw4g/bonsai
https://github.com/scallyw4g/poof
jesse__, 21 hours ago
I've been working on a voxel game engine called Bonsai for ~10 years.
Probably the most interesting thing about it at the moment is the editor. The world, and most things in it, are represented as collections of SDFs. More accurately, they're density fields, but, potato-tomato.
Bonsai has undergone a large rewrite over the last couple years that's nearing completion. A world edit is defined as a bunch of SDF parameters which get projected/rasterized into the voxel grid by a shader on the GPU. One neat thing about SDFs is they've been thoroughly researched and documented by a guy named Inigo Quilez, and they have a lot of nice mathematical properties. For example, you can do a smooth union of arbitrary SDFs to get nice rounded contours where shapes join.
I've written every system from scratch, all the way from the memory allocators and font rasterizer to the collision detector and simulation loop. I even wrote a metaprogramming language as a replacement for C++ templates, which is a whole other story. IIRC the only external dependency is the C runtime library for starting the process and my very occasional use of variadic functions arguments.
For a long time, an explicit non-goal of the project was to ship a game. It sounded insane to me to write an entire 3D engine and then ship a game. As it turns out, I've gotten it to the point where I can actually make a game. I've got a start on the game systems in a closed-source repo, and hope to have a steam page for it by the end of the year.
I'll do some shameless self-promotion and leave some links here for anyone interested in looking at the engine, language code, or some pretty pictures.
https://github.com/scallyw4g/bonsai
https://github.com/scallyw4g/poof
jesse__, 21 hours ago
Show HN: An e-ink frame that hears birds and draws them as 1800s illustrations
Article, Comments
https://github.com/tphakala/birdnet-go
Article, Comments
https://github.com/tphakala/birdnet-go
GitHub
GitHub - arnegiacomo/fugleramme: E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered…
E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
🔥3
This media is not supported in your browser
VIEW IN TELEGRAM
got @typesafeai’s new model Jev to play Super Mario Bros.
fast inference + structured outputs makes it surprisingly good for real time use cases.
I'm excited to see what can be done with these new models!
Posted by Faadil Shaik, 4 hours ago
fast inference + structured outputs makes it surprisingly good for real time use cases.
I'm excited to see what can be done with these new models!
Posted by Faadil Shaik, 4 hours ago
there is some funny shit going on here
Godot Engine has a method called ResourceLoader::load_threaded_get_status
this method's signature and documentation is pretty funny:
it returns ThreadLoadStatus enum
however, notice the second parameter: progress: Array
you may be asking: "ok, now what's that array? maybe you have to pass it some kind of list of something?"
their docs says:
this was really vague for me, like, why pass an array? what length should it be? what happens if you pass it an array of, say, 10
it really made me curious, so I decided to check their ACTUAL C++ code:
it resizes your array to len 1, then sets the first element as the progress
and the entire time I was like ????
why would you do that???
it turns out godot devs didn't want to introduce the concept of explicit pointers/references in their language, so they have to do all these weird array-plays all around their language (
they could either add a
result.status
result.progress
why do you have to ruin your APIs' readability LIKE THIS?
I really don't get it
Godot Engine has a method called ResourceLoader::load_threaded_get_status
this method's signature and documentation is pretty funny:
it returns ThreadLoadStatus enum
however, notice the second parameter: progress: Array
you may be asking: "ok, now what's that array? maybe you have to pass it some kind of list of something?"
their docs says:
An array variable can optionally be passed via progress, and will return a one-element array containing the ratio of completion of the threaded loading (between 0.0 and 1.0).
this was really vague for me, like, why pass an array? what length should it be? what happens if you pass it an array of, say, 10
it really made me curious, so I decided to check their ACTUAL C++ code:
r_progress.resize(1);
r_progress[0] = progress;
it resizes your array to len 1, then sets the first element as the progress
and the entire time I was like ????
why would you do that???
it turns out godot devs didn't want to introduce the concept of explicit pointers/references in their language, so they have to do all these weird array-plays all around their language (
Array object in gdscript is mutable and is passed by ref everywhere)they could either add a
ref param, or just return a single object like:result.status
result.progress
why do you have to ruin your APIs' readability LIKE THIS?
I really don't get it
Unicode 18.0.0 is released
it adds 13k characters, bringing the total to 172.k
it adds 13k characters, bringing the total to 172.k
This media is not supported in your browser
VIEW IN TELEGRAM
Bend 2 is here!
It is a new programming language that blocks AI mistakes via *proof checking* - the same technique big AI labs used to solve open math problems, like Navier-Stokes.
It is also very fast, and runs on GPUs.
https://bend-lang.com
Posted by Taelin, 12 hours ago
It is a new programming language that blocks AI mistakes via *proof checking* - the same technique big AI labs used to solve open math problems, like Navier-Stokes.
It is also very fast, and runs on GPUs.
https://bend-lang.com
Posted by Taelin, 12 hours ago
👍1
Re: AI-generated posters don’t have to be horrible
A lot of people in the comments say that the supposedly better examples in the article are still “horrible” because they can tell they’re AI and point to things that the AI did “wrong” and a human artist would do better.
That may be true if you’re working with a top of the line artist, but in my experience the average freelance designer online is significantly worse than AI. I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models. Will a great human designer produce better output than an AI? Maybe, but a small local event or business probably won’t have the budget to hire them or know where to find them. It’s cheaper, faster and easier to use AI to generate something that’s good enough for their purposes.
People also point out all the little flaws in the “good” examples and cite them as obvious tells that they were AI generated. I think it would be interesting to see if people could reliably distinguish between AI generated flyers and human made flyers. Sure, sometimes it’s obvious like when the AI adds those weird, cartoony people. But if the model is told not to create designs like that and stick to the styles used in the second half of the article, I expect people would have a much harder time distinguishing the human designs from the AI designs.
ajjenkins, 4 hours ago
A lot of people in the comments say that the supposedly better examples in the article are still “horrible” because they can tell they’re AI and point to things that the AI did “wrong” and a human artist would do better.
That may be true if you’re working with a top of the line artist, but in my experience the average freelance designer online is significantly worse than AI. I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models. Will a great human designer produce better output than an AI? Maybe, but a small local event or business probably won’t have the budget to hire them or know where to find them. It’s cheaper, faster and easier to use AI to generate something that’s good enough for their purposes.
People also point out all the little flaws in the “good” examples and cite them as obvious tells that they were AI generated. I think it would be interesting to see if people could reliably distinguish between AI generated flyers and human made flyers. Sure, sometimes it’s obvious like when the AI adds those weird, cartoony people. But if the model is told not to create designs like that and stick to the styles used in the second half of the article, I expect people would have a much harder time distinguishing the human designs from the AI designs.
ajjenkins, 4 hours ago
https://github.com/anthropics/claude-code/tree/main/mods/agents-md
this is not even overengineering at this point, it's literally a crime
all this "mod" does is to read a single .md file and pass it to the model btw
meanwhile they have telemetry for it
this is not even overengineering at this point, it's literally a crime
all this "mod" does is to read a single .md file and pass it to the model btw
meanwhile they have telemetry for it
GitHub
claude-code/mods/agents-md at main · anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo...