Hacker News: kkukshtel

New comment by kkukshtel in "Show HN: I made a flight simulator, except you're just a passenger"

kkukshtel — Wed, 16 Sep 2026 14:22:18 +0000

This immediately came to mind for me as well. The game straddles "game" and "performance art", and the totally straight-faced delivery really makes it stand out.

New comment by kkukshtel in "Pion, an agent designed to run any company autonomously"

kkukshtel — Tue, 15 Sep 2026 15:53:25 +0000

Devin is/was shit though, compared to the other options available both now and then.

New comment by kkukshtel in "DeepSeek v4.1 Flash"

kkukshtel — Thu, 10 Sep 2026 21:35:22 +0000

This is also what is compelling about Midjourney imo.

New comment by kkukshtel in "Nvidia agrees to acquire Hugging Face for $13B"

kkukshtel — Thu, 27 Aug 2026 18:58:34 +0000

DAU

New comment by kkukshtel in "Z.ai confirms Ox Alpha is a new GLM-series model and will release its weights"

kkukshtel — Wed, 26 Aug 2026 14:22:46 +0000

I think so much of this is people greenfield-ing things as benchmarks, which is nearly always a success case for any AI these days.

New comment by kkukshtel in "Show HN: A techno machine in one HTML file, with verifiable renders"

kkukshtel — Mon, 24 Aug 2026 20:49:25 +0000

the otherwise fawning praise in the comments for something that seems so obviously vibe-coded is making me wonder if all these one sentence replies are bots

New comment by kkukshtel in "Taffy: A flexible, high-performance, cross-platform UI layout library"

kkukshtel — Wed, 19 Aug 2026 15:33:03 +0000

Thanks for all this! I used Blitz a while ago for a product research spike around composing HTML to be rendered directly in a terminal with kitty or iterm's image protocol:

https://www.npmjs.com/package/kittyhtml

https://github.com/kkukshtel/kittyhtml

New comment by kkukshtel in "How Claude marks AI-generated content"

kkukshtel — Tue, 11 Aug 2026 14:31:47 +0000

I think a lot of the examples below are projecting more complicated options, but it could also be something just as simple as using a word with a hyphen in it every prime-numbered sentence. Or any other "puzzle-y" pattern.

New comment by kkukshtel in "Darktable"

kkukshtel — Fri, 07 Aug 2026 15:12:09 +0000

IMO Capture One is better suited to using separate catalogs. I usually create one per year or something similar. Having everything in one catalog is going to eventually get slow.

New comment by kkukshtel in "TSON – A JSON superset with immutable, hash-pinned schemas"

kkukshtel — Thu, 06 Aug 2026 03:33:10 +0000

This looks like AI slop, and also a worse version of CUE.

https://cuelang.org/

New comment by kkukshtel in "Position: LLMs Can't Jump"

kkukshtel — Thu, 06 Aug 2026 03:28:56 +0000

Noah Smith had an interesting idea related to this in a recent newsletter:

https://www.noahpinion.blog/p/what-will-more-intelligence-ac...

> Another way of saying this is that there may be laws of the universe that humans can’t understand but AI can. I call these “cloud laws” — causal regularities that can be exploited by technology, but which are too diffuse and complex for an individual human being to either intuit or communicate. Human language seems to obey cloud laws, so why not other phenomena too? Perhaps social sciences like economics, sociology, and political science obey similarly complex regularities, and AI can help us find them. Perhaps there are physical processes — plasma, or topological materials, or aerial turbulence, etc. — that obey cloud laws instead of chaos?

New comment by kkukshtel in "Darktable"

kkukshtel — Wed, 29 Jul 2026 14:44:39 +0000

I highly recommend people try out Capture One. After using Lightroom for years, switching to Capture One a few years ago felt like someone turned the lights on. Far and away the best photo and media mangement software I've ever used by at least two orders of magnitude, and reasonalbe license cost and generous free tier.

New comment by kkukshtel in "Claude Cookbook"

kkukshtel — Fri, 24 Jul 2026 18:51:36 +0000

This is also where I'm at. "Just ask the model stuff" continues to be the best, most durable advice. Karpathy himself had something recently about this on Twitter.

New comment by kkukshtel in "Tiny Emulators"

kkukshtel — Mon, 13 Jul 2026 18:57:45 +0000

Sokol is the best, thank you for your ongoing work :) And please open a patreon or something!

New comment by kkukshtel in "What to learn to be a graphics programmer"

kkukshtel — Thu, 02 Jul 2026 15:47:33 +0000

I work professionally on game engines and also have my own custom engine. Watching the space for 15+ years, I would say that nearly _every_ custom game engine exists as a demonstration of graphics capability, not anything to do with improving the actual experience of game development. This is in part to do with the fact that working on 3D at all is a slippery slope towards continuing to work on graphics stuff.

New comment by kkukshtel in "DiffusionGemma: 4x Faster Text Generation"

kkukshtel — Wed, 10 Jun 2026 16:49:34 +0000

I think this is the future. The sort of left-field rumble that turns into a quake in 5 years.

New comment by kkukshtel in "Thi.ng – open-source building blocks for computational design and art"

kkukshtel — Tue, 09 Jun 2026 13:53:04 +0000

This has been around for a long time and I've always been so surprised it has had seemingly so little traction outside of the author's own projects. The love and care and thoughtfulness of every library has always been so great to explore.

New comment by kkukshtel in "DaVinci Resolve 21"

kkukshtel — Wed, 03 Jun 2026 20:18:51 +0000

The audio-driven animation stuff here is so nice. A year ago I went on a journey to produce a video podcast waveform based off the audio track, and the process was incredibly painful for no obvious reason. My hope here is that I can now just do this all within Fusion and not need to render this in an external tool.

Also nice is built in loop (ping pong) animations! No more duplicating keyframes!

https://kylekukshtel.com/building-video-podcast-resolve-audi...

New comment by kkukshtel in "Claude Opus 4.8"

kkukshtel — Fri, 29 May 2026 14:13:48 +0000

Not only this but hermetic checks on local machines for spot testing new models is becoming increasingly difficult, if not impossible.

- We have 0 visibility into what Anthropic does with our own prompts server side (do they return cached results from similar queries? Do we develop our own hot paths?).

- Local memory files are written independent of project directory and are acted on by the new models, even if old models wrote them

- CLAUDE.md files have varying degrees of efficiency and different models (and effort) treat them differently

- Our own git history "supports" newer models - ie if you have a larger body of work in git when you adopt a new model (like 4.8) than when you started from scratch with 4.6 or something, 4.8 may "appear" smarter when in fact you just have more evidence and signal about what you intend for a model to do.

New comment by kkukshtel in "My new obsession: A horse-racing board game of pure luck"

kkukshtel — Wed, 27 May 2026 19:04:37 +0000

I'd look into something tactile, with simple rules but strategic depth:

Personally I'd recommend Hive or a similar (and simpler) tile movement game, High Tide.

https://boardgamegeek.com/boardgame/2655/hive

https://boardgamegeek.com/boardgame/430875/high-tide

Both have nice chunk tiles, no board requirement, few pieces, and can easily travel. And they can both be easily explained.