Hacker News: jschomay

Show HN: Grid Words – sudoku meets Wordle meets crosswords

jschomay — Mon, 20 Jul 2026 14:12:50 +0000

I like puzzle games. I'm fascinated by crosswords but I am bad at them. I'm pretty good at sudoku. Wordle is always fun. I started to wonder if there was a way to play crosswords that worked more like sudoku or a 2D wordle. Grid Words is what I came up with.

The game is a 5x5 grid. As you fill in letters you get color-coded clues if they appear in that row/column or not. By following the clues and trying to form complete words you can fill in the whole puzzle. There is a new word every day.

Comments URL: https://news.ycombinator.com/item?id=48979155

Points: 4

# Comments: 1

New comment by jschomay in "Letting AI play my game – building an agentic test harness to help play-testing"

jschomay — Fri, 01 May 2026 20:57:07 +0000

Thanks for the suggestions. I thought tilted was less rigid and matched the aesthetic of the dungeon maps at https://watabou.itch.io/one-page-dungeon which I like. But I hear you. You can press space to see the full puzzle, but it can be hard to read the words on a large level. That was one UI concern I didn't quite figure out. I'll consider your suggestions!

New comment by jschomay in "Letting AI play my game – building an agentic test harness to help play-testing"

jschomay — Thu, 30 Apr 2026 00:42:40 +0000

Hi, thanks! That sounds really interesting. I'm curious how it compares too. What is the best way to get in touch?

New comment by jschomay in "Letting AI play my game – building an agentic test harness to help play-testing"

jschomay — Thu, 30 Apr 2026 00:32:12 +0000

OP here, cool to see all the similar yet varied testing approaches! Your situation sounds tricky with a real time physics based game. Converting it to step based sounds like it has promise, but as you mentioned, every dilution to the full e2e harness also dilutes the validation veracity. When you were describing your game I kept thinking of Bret Victor's "Inventing on Principles" talk where he "collapses time" in a physics game to render trajectories of objects in all positions at once to visually intuitively tell if it works right. Perhaps that could apply?

New comment by jschomay in "Letting AI play my game – building an agentic test harness to help play-testing"

jschomay — Thu, 30 Apr 2026 00:26:58 +0000

Thank you. You have a great suggestion. I didn't do that, but I did consider it and I think it can be very powerful. I had 2 example use cases that having an actual AI felt good for, first validating a new feature based on the spec, and second, finding unexpected bugs (like trying to enter a locked room through the back wall). It didn't do so well on the latter, but did great on the former. Having a million simulated games could probably catch those, but how would you track the reports after? Perhaps using an LLM to read the logs/reports could be a good use. Your set up sounds awesome, nice work.

New comment by jschomay in "Letting AI play my game – building an agentic test harness to help play-testing"

jschomay — Thu, 30 Apr 2026 00:21:13 +0000

OP here: Thank you and I appreciate the thoughtful questions. To answer: 1) I used a text representation because it made sense for my game and let me "render" certain details in a more AI-friendly way, like the compact map. You could use something like agent-browser and it would probably work just fine, but I figured it added an extra layer of indirection that I didn't need, plus it would be a lot of screenshots! Being able to have a turn based loop really helped make this work.

2) I had a skill on just how to use the playtest server. I also gave it context on what the game is and how to play it. From there, it probably depends on your use case. I wasn't that impressed with its natural ability to playtest for bug discovery, so I would consider making a skill describing what a playtester would normally do. Focused playtester instances is a good idea. Ultimately what I found to be most helpful was to point it at a feature or bug that I was aware of and have it validate it. Not only was it fairly successful, that was the part that saved the most time for me.

3) I think I only burned about 300K tokens on my longest play-test session, and that includes a bunch of code tweaks too. Running it after every feature as a validation step is pretty cheap. Running it overnight in "open" playtesting could add up.

Good luck, please let me know how it goes if you get somewhere helpful!

Letting AI play my game – building an agentic test harness to help play-testing

jschomay — Wed, 29 Apr 2026 12:43:12 +0000

Article URL: https://blog.jeffschomay.com/letting-ai-play-my-game

Comments URL: https://news.ycombinator.com/item?id=47947525

Points: 136

# Comments: 36

Context Engineering Explained in Pictures

jschomay — Mon, 16 Mar 2026 13:01:41 +0000

Article URL: https://mechanicalorchard.substack.com/p/context-engineering-explained-in

Comments URL: https://news.ycombinator.com/item?id=47398439

Points: 2

# Comments: 0

New comment by jschomay in "Rendering a game in real time with AI"

jschomay — Thu, 28 Aug 2025 17:44:53 +0000

OP here. Thanks for the feedback. I agree that frame to frame consistency is quite bad currently. I did address that in the post, hinting at some of the techniques others have mentioned here, like in/out-painting and masking previous frames. For me, the exciting parts of this experiment was finding the opportunities and limits of realtime generation, and exploring ways of grounding generated content in a solid yet player controlled world layer.

New comment by jschomay in "Rendering a game in real time with AI"

jschomay — Thu, 28 Aug 2025 17:28:43 +0000

That's really cool, thanks for sharing!

New comment by jschomay in "Rendering a game in real time with AI"

jschomay — Thu, 28 Aug 2025 17:25:01 +0000

OP here, I remember both of the draw fast and lens demos! I'm pretty sure those were in the back of my subconscious, inspiring me to explore my take on real time rendering. Thanks for sharing your similar experience. I agree, this was a lot of fun to work on, and like one of the other commenters pointed out, experiencing it viscerally is a whole new kind of feeling, even with the consistency issues. I'd also like to see more experiments on what new kinds of UX could be possible with this tech.

Rendering a game in real time with AI

jschomay — Thu, 28 Aug 2025 12:10:14 +0000

Article URL: https://blog.jeffschomay.com/rendering-a-game-in-real-time-with-ai

Comments URL: https://news.ycombinator.com/item?id=45051188

Points: 114

# Comments: 109

Building a Real Time Generative AI Game Assets Pipeline

jschomay — Thu, 02 Nov 2023 20:26:50 +0000

Article URL: https://blog.jeffschomay.com/lost-in-an-infinite-maze-building-a-real-time-generative-ai-game-assets-pipeline

Comments URL: https://news.ycombinator.com/item?id=38119623

Points: 2

# Comments: 0

New comment by jschomay in "Getting the most out of AI NPCs"

jschomay — Thu, 20 Apr 2023 00:34:57 +0000

Continuing experiment on adding Inworld AI NPCs to my existing narrative game. This time I explore how to more tightly integrate the conversational AIs with the existing game world for a better game play experience with actual game play examples.

Getting the most out of AI NPCs

jschomay — Thu, 20 Apr 2023 00:34:57 +0000

Article URL: https://medium.com/@jschomay/adding-inworld-ai-characters-to-an-existing-game-part-4-going-deeper-2c9f4f1084c3

Comments URL: https://news.ycombinator.com/item?id=35635010

Points: 5

# Comments: 1

Visual demonstration of monads

jschomay — Fri, 22 Apr 2016 02:44:55 +0000

Article URL: http://jschomay.github.io/monad-wang/

Comments URL: https://news.ycombinator.com/item?id=11546755

Points: 1

# Comments: 0

Learning to think in FRP: My experience coding a game with Kefir.js

jschomay — Sat, 09 May 2015 18:33:23 +0000

Article URL: http://codeperfectionist.com/articles/learning-to-think-in-frp-my-experience-coding-a-game-with-kefir-js/

Comments URL: https://news.ycombinator.com/item?id=9517230

Points: 1

# Comments: 0