Jon Radoff 👾/acc 🎮 Metavert Profile picture
Adventurer | Entrepreneur | Game Maker | Biohacker | AI bro | https://t.co/rMJUnF2Fb3 | Metavert | Blog: https://t.co/hPGtF9HkYv | #gamedev #GenerativeAI #AI
Aug 1, 2023 17 tweets 6 min read
🧵 1/ The first lab reported a replication of the #LK99 superconductor.

If it works, the applications and consequences are mind-boggling.

A thread on the tech tree it accelerates -- dreamed up with the assistance of GPT-4 and Midjourney: Image 2/ One of the most important apps will be advances in quantum computers

And one of the applications of quantum is simulations of chemistry & materials.

This results in a feedback loop where we create even better superconductors, which will lead to better quantum computers... Image
Jun 12, 2023 7 tweets 5 min read
1/ We won Grand Prize in LA @Techweek_ Virtual Worlds hackathon, creating a fully-playable RPG in 1 day.

We devised a new programming paradigm: Semantic Programming.

Generative AI + other tech used: @AnthropicAI @Scenario_gg @BlockadeLabs w/ @Beamable @unity @AILA_Community 2/ The core of our approach was using the @AnthropicAI Claude LLM with its 100K context limit.

This enabled us to maintain a long-story with a high level of cohesion.

But it was also a matter of using XML-encoded responses to inform our UI, chainging to other genAI. Image
Dec 13, 2022 9 tweets 5 min read
1/ The future is wild! Could you create a massively multiplayer game from a text prompt?

#ChatGPT shows us the natural-language interface that could enable this.

We worked on a PoC using @Beamable and @UnrealEngine to show how: #ai #gamedev

A thread: Image 2/ First, let's revisit some of the interesting examples that apply to coding or gamedev.

I recently created a text adventure game in ChatGPT:

medium.com/building-the-m…
Dec 10, 2022 7 tweets 4 min read
1/ I made an @UnderTale fan game using @ChatGPT in a few minutes this morning.

Follow this thread to learn how, along with some tricks and tips you might want to try in your own experiments.

#gamedev #chatgpt #undertale #ai Image 2/ Here's the prompt to make an Undertale RPG:

"Let's play an RPG based on Undertale by Toby Fox. You will tell me what I'm experiencing, and then present exactly 4 options. Never make a choice on my behalf. Whenever a set of choices involves an encounter with a monster..." Image
Mar 18, 2022 19 tweets 6 min read
🧵 1/19 What do Russians believe?

An exploration of my WhatsApp talks via @squad3o3 with Russians about #UkraineRussiaWar

As always, thanks to @dsmart @PeterCorless @Osinttechnical @int_osic @WarintheFuture @SpencerGuard @antoniogm and all others working to educate and inform. 2/19 The conversation starter works. It is authentic. It is curious. People do respond at a frequency I'd never have expected.

(This is in contrast this with the original prompt that told them they are being lied to, which mostly provoked explitives)
Mar 17, 2022 20 tweets 7 min read
🧵 1/20 open-sourcing my thinking on game theory, game design and geopolitics.

There's been talk about the geopolitical "game" being played. Most don't consider iterative play, irrationality, risk of ruin and asymmetric info.

Read on, & LMK how to improve my thinking. 2/20 The point by @balaji is neither side may be playing the same game.

But the problem we have here is really one of information asymmetry.

Not simply playing different games... but not even knowing the game being played.

Nov 22, 2021 25 tweets 4 min read
1/23 Podcast of the year - @tferriss and @balajis on:

transhumanism vs. anarcho-primitivism
Web3
Decentralization & counter
Code > principal-agent problem
DeFi=every asset tradable
new governments

Impossible to cover 5 hrs here; read for 22 ideas.

tim.blog/2021/11/15/bal… 2/23 The US went from winning everywhere without fighting, to fighting everywhere without winning (example: regarding Covid-19 as a military defeat for the US)