Raphael (@frihyde) header
Raphael (@frihyde) profile picture

agency + ai = freedom // building stuff // I don't want to be rich, I want to be free | @HideoutNFT

Joined March 2019
Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)Photo by Raphael (@frihyde)
immersed to the fullest
1
22
472
Your most important prompt for today: In face of the latest cybersecurity incidents, I want you to help me make my system bullet proof.
1
1
32
The perfect apology for going all in on Ocarina of Time and WoW forever in November IQ maxxing
Frequent video gamers performed on cognitive tests like non-gamers that were ~13.7 years younger
96
using fable 5.1 to clean up skills via /claude-api prompt-audit is truly magical
2
76
Raphael retweeted
Launching an Ethereum game soon, Like and retweet if you want early access.
Launching an Ethereum game soon, DM me if you want early access tomorrow.
942
1,244
43
2,017
65,901
opus cooked up another one - this time a mobile game! what are we thinking... yay or nay?
4
85
Look how far we’ve come. This was not too long ago and now people create entire 3d AAA based games with a single prompt? Imagine what the game industry will look like one or two years from now. Mind boggling.
Claude 3.7 Sonnet by Anthropic is WILD! It just oneshotted a Legend of Zelda inspired p5js game. Absolutely unreal.
4
356
I'm actually blown away. Is this the singularity moment @sama spoke of? Opus 5 one-shotted this kart racer - just a single prompt! see comments for more info
3
1
15
5,215
here is the prompt (props to @mattshumer_): I want you to build a kart racer at the level of the most recent Mario Kart games. It should be utterly perfect, visually beautiful, with every single thing done at AAA quality—from textures to physics to anything you could think of. Fan out sub-agents and have sub-agents tackle each one individually so that the game is utterly perfect. You should /loop on each item and have a separate sub-agent check it visually to ensure it looks triple A. That separate sub-agent should be a really harsh critic, and if it doesn't look triple A, it should keep going. Don't stop until each sub-agent is utterly wowed with the quality when compared with the actual Mario Kart game. It should literally compare them side by side blind and say which one looks better. Do this in ThreeJS. /loop until it's utterly perfect. Fan out sub-agents and ultracode.
6
332
What if I told you that you could experience peak classic World of Warcraft enthusiasm on a daily basis if you were just to embrace the chaos in your life? Break your limiting beliefs and start living.
1
114
ngl gamers being able to design their own games with zero background in software engineering makes me excited for the future
3
81
Here we go again
We've reset 5-hour and weekly rate limits for all users.
1
98
Time to cancel all weekend plans (again) lmao
We're extending access to Claude Fable 5 on all paid plans through July 12.
1
111
rip Europe, rip Germany At least „we’re green“ Permanent underclass.
CHINA CONSIDERS RESTRICTING OVERSEAS ACCESS TO CUTTING-EDGE AI MODELS China’s Ministry of Commerce has led meetings over the past month with major AI companies, including Alibaba, ByteDance, and Z.ai, to discuss measures that would restrict overseas access to cutting-edge AI models, including models that have not yet been released. The discussions reportedly include not only closed-source models but also open-weight models. However, the scope of application is still under debate, and the rules may ultimately apply only to future frontier models. Officials have also discussed designating the leakage or theft of proprietary AI technologies as a national security crime, with stronger penalties, as well as restricting the types of foreign capital that can invest in Chinese AI startups. The backdrop is the U.S. move to strengthen export controls on AI models, along with national security concerns over cutting-edge models that could possess advanced cyberattack capabilities. Chinese authorities are reportedly concerned that advanced U.S. cybersecurity AI models could be used to exploit vulnerabilities in Chinese software. Since the beginning of this year, China has continued to tighten measures to prevent AI technology from being transferred overseas. Authorities have investigated whether Chinese AI startups that relocated abroad violated export control laws, while also strengthening oversight of overseas transactions involving Chinese investors, technology, data, and national security concerns. Future regulations could take the form of a tiered framework based on technological capability. Basic open-source AI models may be managed through a filing system, high-performance models may be subject to security reviews, and the most sensitive frontier models may be banned from public release or restricted to use within China.
1
111
Here I am — going for a walk in the forests, coming up with ideas that I can directly feed into my personal agent via a simple chat interface. The future is here, and I couldn’t be more excited! @NousResearch and @openclaw gave us the tools — now we just have to execute.
45
Peak German hiking experience
41
The $MegaETH airdrop kinda reminds me of the $Blur airdrop: I remember the regret of instantly jeeting my whole stack, when it doubled shortly after. Not gonna have the same regret this time. Cya in a couple days.
1
239
claude opus 4.6 on brainrot:
1
58
It’s gonna be a long night
2
73