developer relations at @aiand_ | agentic AI enthusiast, building in public. | prev: @GoogleDeepmind, Google Stadia
Tokyo, Japan
Joined May 2008
- Tweets41.6K
- Following6.8K
- Followers2.5K
- Likes221K
Pinned Tweet
as promised, phone-as-controller libraries for godot and for unity, MIT licensed! cloudflare tunnel integration so devices don't have to all be on the same network.
pmc.splatterfacegames.com
first project for this thing: triple triad as a house party game, in godot. join on your phone for deck management, vote on rules, drag and drop on the multitouch screen
phone-as-controller inspired by @greggman's legendary happyfuntimes
will open source the godot library soon
Jetha Chan retweeted
As someone early in my career at Epic, I’ll share my experience, especially since a lot of this conversation is about what AI means for people just starting out. I love using this as a tool.
I think a lot of people don’t realize how much AI has changed, even since 2025. It’s not just “slop”. It’s been amazing at helping me as a designer work through more advanced technical challenges so I can focus more on what makes games feel fun. I use it, I enjoy it, and I’ve built 3 UEFN prototypes I’ve always dreamed of making in a WEEK with its help.
I’m speaking for myself here, and I understand why other early career developers have concerns. But I’ve been having a blast learning and building with it. If you haven’t tried it recently, give it another shot. You might be surprised by what you can build. It’s a whole different tool now from even just a few months ago!
If you have any questions on it, please feel free to ask me via DM or reply!
Jetha Chan retweeted
There's a famous story from Art & Fear, also repeated in Atomic Habits:
A ceramics teacher split his class in two. One half would be graded on quantity, by the pound of pots they made. The other half on quality: one perfect pot.
The best pots all came from the quantity group.
They made, failed, and learned. The group focused on perfecting one pot didn't learn as much.
Quantity results in quality.
Jetha Chan retweeted
In a few years the entire game industry will look back and thoroughly realize they should have adopted AI tech earlier.
To state this more clearly: if you're a programmer in this industry and not using agents right now, something is wrong.
Tim Sweeney, CEO of Epic Games, gets it. While many in the gaming scene still oppose AI, he primarily sees its advantages: ideas that would otherwise be labor-intensive to produce can be brought to life in a very short amount of time.
AI acts as an enabler, allowing creativity to be realized more quickly - it is by no means a hindrance. The acceleration we have witnessed in other fields is set to revolutionize the gaming industry as well; we are about to see an explosion in intellectual output.
Jetha Chan retweeted
You'd think the land of the free would have just one major newspaper excited for the most amazing feats of the nation.
Unveiling the Roadster with out-of-this-world technology reiterated that Musk has given up designing cars for regular people to drive. on.wsj.com/3UvugrS
Jetha Chan retweeted
What happens when I combine everything I know about programming and the Mega Drive, a LOT of patience digging into technical challenges, some vibe coding, and cutting-edge AI?
What seemingly impossible game could we port to a stock Mega Drive without enhancement chips?
The graphics and performance still need work, but I've already managed to play through the entire game from start to finish without a single crash!
Can you guess the game from these screenshots?
Jetha Chan retweeted
Every single person you meet in your daily life is fighting a hidden battle that you know nothing about
Send them a Zoom meeting link for an 8 AM call on Monday morning to finish them off
Jetha Chan retweeted
Sometimes I like traveling by myself… it recharges my brain and lets me think about new approaches to old problems. One of the things I love to do is dine in busy places, and spread positivity to people I don’t know. A random compliment, a fun conversation… you never know who you will meet, or the stories you will hear, or even the friends you will make.
I mention this because I see so many of you on here obsessed with spreading negativity, because of what you believe, or how it makes you feel, or even just because you are bored. I promise you, it earns you nothing. Instead, go to a local bar, grab a drink, and see what you can learn or what friends you can make.
Jetha Chan retweeted
Google just open-sourced Harness².
(turn any harness into a self-improving system)
a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup.
Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched.
on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved.
because it learns from the differences between runs, it needs no correct answer or grader for the task.
that covers a single task. Harness² also carries what it learns from one task into the next.
after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch.
this means every finished task makes the next round of edits more informed.
Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher.
those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work.
you can find the Harness² repo here: github.com/google-research/h…
I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand.
that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.
Did a double take - Frequency is getting a bluray re-release in Japan with the Japanese dub for the first time! Ngl I am pretty tempted.
Jetha Chan retweeted
Per my tweet on Oct 9th: xitter.cf/JNavok/status/21084362…
This is 100% correct and on point.
2026 is the year most programmers get on board in a serious manor. Those who wait of hand wave it all away will likely regret that in the future.
Your time is valuable and limited. Once you get up and running on ai coding a pretty magical thing happens. You have more time for more important matters. Harder coding tasks. Design tasks. Marketing tasks. Whatever it is.
I know most indies think ai anything is kryptonite. That's ok. It really is a war of attrition, and it's also ok if people never adopt it. But I think that latter point will put you are a disadvantage competitively just from a time standpoint and what you can do with it.
Do not fear it. Do not handwave it away. Embrace it on any level you feel comfortable. At some point the lightbulb will go off and you realize how much more you can get done or just enjoy some more free time.
Jetha Chan retweeted
We have our own Linux kernel for Apple Silicon covering M1, M2, M3 and MacBook Neo machines now for @omarchy with external monitors, thunderbolt docks, Touch ID.
M4, M5 and M6 coming soon.
And yes, we are having a blast on the @OmarchyMac team building this together!
Jetha Chan retweeted
Every AAA gamedev I know is making their own dream game with AI. They broke open their archive of game ideas they've been dreaming about since forever and are having the time of their lives. They've told me "I've never enjoyed gamedev more than now."
Jetha Chan retweeted
When I was writing Unreal Engine 1, my time was divided as follows:
- Around 30% went to seriously deep coding on hard problems: assembly language texture mappers, C++ BSP trees, data persistence, object oriented systems design, and networking.
- Around 70% was just typing and refactoring large bodies of code needed for a complete engine feature set. This was not hard, and while I was doing it my mind was mostly on the deeper coding topics, thinking and planning for what's next. It didn't feel much different from vibe coding today, except that it was just me typing code on an IBM Model M keyboard rather than prompting it and reviewing the results.
So, it has always seemed perfectly logical that we would rely on AI for that 70%, once the AI could do it with a similar quality standard as we could, which has never been perfection. It came as no surprise that, after a few years of AI model evolution, it was able to take the reigns on that 70% and free up programmers' time for more valuable tasks.
What's more of a surprise is the emergence of AI as a sort of insta-Carmack able to solve hard technical problems quite cleverly and often cleanly, and that it's able to reason about and work in complex 3D scenes both by operating the tools and by directly understanding the raw data files.
I abandoned assembly language in 1998 when out-of-order CPUs made much simpler C/C++ code faster, and never I missed it. If prompting through architectural documents, concept art, and design plans can transcend typing code and tweaking vertices, that will enable developers to spend their time on higher-level, higher value technical and creative tasks.
What matters is the end product, whether it's a game or an engine. Anything developers can do to try out more ideas and make better software and games faster is a win for everyone.
Jetha Chan retweeted
Can I be honest for a sec?
Regarding LLMs in gaming, I feel more confused than ever. And I would like my peers and other people who are familiar in this field to chime in.
It’s barely been a week since I made my post about distancing myself from a vibe coded project made by my friend in Smash. I even said “AI has no place in gaming”.
After I made that post, I was reached out to by multiple colleagues in the space and people hired full time in software development. They educated me severely on the topic and I feel dumb now for my earlier sentiments.
I was informed by my colleagues that it is now the norm to do 90% (and this is low estimate apparently) of all your coding with AI assistance or vibe coding. 75% of all new code at Google is made by AI and engineer approved.
The vast majority of all the apps we use now are updated or maintained with AI coding - I imagine that also goes for Twitter, the very app you’re reading this on.
So I figured okay - it’s here to stay in all software development - but where does that leave video games?
I saw the posts from Epic Games, XBOX, and other publishers that seem to embrace the new era instead of rejecting it.
In the last week I’ve been sent about a dozen different projects like this one that dissect and reintegrate Melee in multitudes of creative ways.
One of them is even a build of Melee that runs natively at 120FPS and one of them simulates the feeling of a CRT almost perfectly.
Some of them feel silly and useless, like low effort projects someone probably gave a single prompt and an ISO of Melee to build. Actual slop.
And yet some feel like legitimately useful things that the community or people practicing could benefit from.
I’m doing my best to navigate what is clearly a rapidly changing sector, especially when we regard the question of “Are Video Games Art?”
And since they clearly are art, does that render AI in its development a bastardized amalgamation of what’s been “learned” from people with actual original ideas?
Or is it strictly optimal to use AI in game development because games ARE software and therefore a necessary tool to wield in this day and age?
I am making this post because I need more guidance on this topic and I feel open discussion on it might be the best way to do that.
