For all the above 40s out there, do you remember when to study stuff like this you had to open an encyclopedia volume? I think schools should use this technology more.
A thread of early experiments with Claude Fable 5.2:
A 3D model of a cell, built entirely from code one organelle at a time. Built by @kevin_t_ngo.
63
Amazing! I hope for OpenAI they have something to rival this
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
63
The next Apple TV is coming out November 13th and honestly it looks like the best opportunity for kids to learn how to create and deploy games they can play with their friends!
My son and I made this game last weekend, he likes Fall Guys so obviously there is a bit of that in it. We grabbed a couple of old DualShock 4 controllers to test it on the TV and were going back and forth with Claude to fix bugs and improve each level. He is starting to see games as something that can be created, changed and improved rather than something that you can only consume.
@AppleArcade @johnternus hit me up if you are interested in this type of things!
I’ve been building games with a few different stacks lately. TypeScript+Capacitor, TypeScript+NativeScript and Rust+Bevy.
I expected Rust to be the clear winner but I was surprised about the results.
At 32,768 moving sprites, Android’s frame counters showed about 58 FPS for Capacitor, 57.6 for NativeScript Canvas 3.0.0, and 52 for Bevy. Capacitor also used less app memory than Bevy.
I also kept adding textures and allocating memory until Android killed each build. Capacitor lasted 8 minutes and 29 seconds before Android killed its WebView renderer; better than the others.
What I find surprising is how well TypeScript+Capacitor held up in this test. I’ve attached the charts so you can see what each stack did. To note that the NativeScript team is working on a new version of the Canvas which might end up outperforming this results.
I’d be interested in hearing the results from anyone else that has done a similar comparison.
Luxury DIY
Asimov 1 is an open-source humanoid robot you can build, train, and customize.
- 1.2 m tall, 35 kg
- 25 powered joints
- Open hardware with off-the-shelf parts
- Open-source SDK and simulation models
Available as a DIY kit.
Order yours at menlo.ai/order
2
61
I wanted to test how reliable was to load a DLL containing the code of a new mini game directly into a Unity game on iOS and Android.
I installed the game on my phone, then compiled a mini game as a separate Unity assembly DLL. The main game made two requests in parallel, one for the bytes of the DLL and one for the AssetBundle. Then passed the downloaded DLL bytes to Assembly.Load using HybridCLR to interpret the minigame IL inside the existing IL2CPP player.
This is huge for mobile games that have live services and events, it allows the creative teams to test any sort of things that otherwise would have needed code changes and a new build.
The best part is that AI was able to implement this in a way to avoid any impact on the main game, I am surprised not every mobile game studio does this.
The majority of my apps code now is done in Rust. I would never have made that choice a few years ago, mostly because of language difficulties. Now I can focus more on the consumer facing things.
I used to be a language lawyer. In the late 80s I _studied_ the ARM (Annotated Reference Manual for C++). I knew the language cold, inside and out. I could make it do backflips. I shipped a lot of code using it. A LOT.
I’ve attacked other languages with a similar intensity and depth. Until recently, that was simply the only way to become adept at building software systems.
I now consider the deep understanding of a language to be a supreme waste of time and effort. I don’t want to learn Rust, or Golang, or Typescript, or any of the thousands of other languages out there. I’ll leave that to my agents.
What I need now is to understand the high level gestalt of the system. I want to see the systems and subsystems. I don’t need to inspect the cogs. If I truly need to understand a detail at the cog level, I’ll interrogate my agents. I’m not going to pretend to be a language expert anymore.
1
1
130
GPT image 2.6 and the new model coming out tomorrow will bring games creation to new highs
Just tested GPT-Image-2.6, and the results are actually insane.
I built full of a cozy farming game where you can learn languages while playing.
Honestly blown away by the quality of the AI-generated art.
Built entirely with Opus 5.5 + GPT-Image-2.6.
AI game development is getting crazy fast.
91
All you need is a phone with T3 Code and Tailscale and then you never have to sit at your desk again.
55
Masterpiece reply
1
4
366
















