Ryan Endacott 🌟

2.6K posts

Ryan Endacott 🌟 banner
Ryan Endacott 🌟

Ryan Endacott 🌟

@RyanEndacott

building star – ai game creator. yc s22. ex-google x. angel investor. always building, exploring, and learning. https://t.co/M4XbRQB9md

Bay Area Katılım Ağustos 2011
2.3K Takip Edilen1.8K Takipçiler
Sabitlenmiş Tweet
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
We open-sourced the SDK behind 2,000+ AI-generated games. Audio that works on iOS Safari. Leaderboards with no backend. One-command deploy. Free hosting. Built by LLMs, for LLMs - run "npx star-sdk install" and your AI agent gets the full docs automatically.
Ryan Endacott 🌟 tweet media
English
3
0
6
382
Ryan Endacott 🌟 retweetledi
Jesse Abraham Lucas 🌃
Jesse Abraham Lucas 🌃@JesseLucasSaga·
You must read God-Emperor of Dune understanding "precognition" as the computability and predictability of human individual/group actions, which will take off in our lifetimes; the computers/Bene Gesserit are the Fates, who Leto II frees us from. It is in dialogue with Foundation.
English
31
90
1.7K
55.3K
Ryan Endacott 🌟 retweetledi
Danny Limanseta
Danny Limanseta@DannyLimanseta·
I don't care if people call it AI slop. Vibe coding games is fun. It's become my main hobby now, and no one can take that away from me.
English
172
27
917
44K
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
Did they remove the Create and View PR buttons from Claude Code mobile? Or is my app just bugging out?
English
1
0
1
85
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
@Tomi_Tapio @liminal_warmth Oh that would be cool. We support voice generation on the website / platform but not the SDK yet. Thanks for the reference! I’ll check out that lib. Any other learnings you recommend for the sdk?
English
0
0
0
7
TomiTapio
TomiTapio@Tomi_Tapio·
@RyanEndacott @liminal_warmth you could have voice synthesis, quite easy when add some public such library. General MIDI pretty easy, send note on, note off commands, at x volume, y instrument. I used LWJGL library for Java game making. Did not import any 3d models, used triangle, rectangle, sphere, cube.
English
1
0
1
19
Ryan Endacott 🌟 retweetledi
Liminal Warmth ❤️‍🔥
Liminal Warmth ❤️‍🔥@liminal_warmth·
Does anyone have a really high-quality open-source game development harness or SDK set up to work with agents published right now? I'm working on a bespoke one just like everyone else is in my free time. Curious what other solutions are out there right now?
English
2
2
21
796
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
@Tomi_Tapio @liminal_warmth That looks sick! Thought about adding Midi support to the SDK but held off - is it something you’d be interested in? How was OpenGL to work with?
English
1
0
0
9
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
@liminal_warmth Our agents run into a ton of common issues across games, this SDK is what we built to address and fix those issues once and for all. Ask your agent to check out ‘star-sdk’ on npm and it’ll give you a rundown.
English
0
0
1
35
Ryan Endacott 🌟
Ryan Endacott 🌟@RyanEndacott·
Yes! Have been spending a ton of time on this. Battle-tested SDK built specifically for agents, working on over 2000 games across desktop and mobile. Many different ways to approach the problem - if you get a chance to try would love any thoughts or feedback. Really respect your ideas on game design :) x.com/ryanendacott/s…
English
2
0
2
79
Ryan Endacott 🌟 retweetledi
Anish Moonka
Anish Moonka@AnishA_Moonka·
Every time you get a cancer biopsy, the lab makes a tissue slide that costs about $5. It shows the shape of your cells under a microscope, and every cancer patient already has one on file. There’s a much fancier version of that test called multiplex immunofluorescence (basically a protein-level map showing which immune cells are near your tumor and what they’re doing). It costs thousands of dollars per sample, takes specialized equipment most hospitals don’t have, and barely scales. But it’s the kind of data oncologists need to figure out whether immunotherapy will actually work for you. Right now, only about 20 to 40% of cancer patients respond to immunotherapy, and one of the biggest reasons is that doctors can’t easily tell whether a tumor is “hot” (immune cells actively fighting it) or “cold” (immune system ignoring it). Microsoft, Providence Health, and the University of Washington trained an AI to analyze the $5 slide and predict what the expensive test would show across 21 different protein markers. They called it GigaTIME, trained it on 40 million cells in which both the cheap slide and the expensive test coexisted, and then turned it loose on 14,256 real cancer patients across 51 hospitals in 7 US states. The results landed in Cell, one of the most selective journals in biology. The model generated about 300,000 virtual protein maps covering 24 cancer types and 306 subtypes. It found 1,234 real, verified connections between immune cell behavior, genetic mutations, tumor staging, and patient survival that were previously invisible at this scale. When they tested it against a completely separate database of 10,200 cancer patients, the results matched up almost perfectly (0.88 out of 1.0 agreement). Nature Methods named spatial proteomics (mapping where specific proteins sit inside your tissue) its Method of the Year in 2024, and specifically cited GigaTIME in a March 2026 update as a model that “democratizes” this kind of analysis. The full model is open-source on Hugging Face. Any cancer research lab with archived biopsy slides, and most of them have thousands, can now run virtual immune profiling without buying a single piece of new equipment.
Satya Nadella@satyanadella

We’ve trained a multimodal AI model to turn routine pathology slides into spatial proteomics, with the potential to reduce time and cost while expanding access to cancer care.

English
103
1.8K
11.2K
929.3K
Ryan Endacott 🌟 retweetledi
Ryan Endacott 🌟 retweetledi
Andrew Kang
Andrew Kang@Rewkang·
Researchers trained a humanoid robot to play tennis using only 5 hours of motion capture data The robot can now sustain multi-shot rallies with human players, hitting balls traveling >15 m/s with a ~90% success rate AlphaGo for every sport is coming
English
460
1.2K
8.8K
1.8M
Ryan Endacott 🌟 retweetledi
Paul S. Conyngham
Paul S. Conyngham@paul_conyngham·
DAY 5 of attempting to cure my dog's cancer using AI UPDATE: We finally found a way to sequence Rosie's DNA. A thread 🧵
Paul S. Conyngham tweet media
English
67
92
867
147.6K
Ryan Endacott 🌟 retweetledi
vittorio
vittorio@IterIntellectus·
this is actually insane > be tech guy in australia > adopt cancer riddled rescue dog, months to live > not_going_to_give_you_up.mp4 > pay $3,000 to sequence her tumor DNA > feed it to ChatGPT and AlphaFold > zero background in biology > identify mutated proteins, match them to drug targets > design a custom mRNA cancer vaccine from scratch > genomics professor is “gobsmacked” that some puppy lover did this on his own > need ethics approval to administer it > red tape takes longer than designing the vaccine > 3 months, finally approved > drive 10 hours to get rosie her first injection > tumor halves > coat gets glossy again > dog is alive and happy > professor: “if we can do this for a dog, why aren’t we rolling this out to humans?” one man with a chatbot, and $3,000 just outperformed the entire pharmaceutical discovery pipeline. we are going to cure so many diseases. I dont think people realize how good things are going to get
vittorio tweet mediavittorio tweet mediavittorio tweet mediavittorio tweet media
Séb Krier@sebkrier

This is wild. theaustralian.com.au/business/techn…

English
2.5K
19.9K
117.9K
17.3M
Ryan Endacott 🌟 retweetledi
cat
cat@_catwu·
my three favorite claude code shortcuts: 1. `!` prefix runs bash inline. the command + output land in context 2. `ctrl+s` stashes your draft. type something else, submit, and it pops back 3. `ctrl+g` opens the prompt (or plan) in $EDITOR for bigger edits
English
44
62
1.2K
88K