BLASTΞASY (@blasteasy) 's Twitter Profile
BLASTΞASY

@blasteasy

ID: 245091513

calendar_today30-01-2011 21:25:49

3,3K Tweet

1,1K Followers

586 Following

BLASTΞASY (@blasteasy) 's Twitter Profile Photo

Everyone: "I slopped a TUI that renders PNGs" Me: "Hold my beer!🍺" I built an entire GPU-accelerated, #SDL3-based game engine with #ClaudeCode in less than 3 weeks. Supports macOS/Linux/iOS/tvOS/visionOS. Can render everything in the terminal with flick of switch!💡

BLASTΞASY (@blasteasy) 's Twitter Profile Photo

Today, I asked an LLM to rewrite prose, using the prompt: "...add variety to the descriptions, in the kind of way that an agentic conscientiousness might ask: 'what is it like to breathe?'" The irony is not lost on me.

BLASTΞASY (@blasteasy) 's Twitter Profile Photo

The future doesn’t belong to people who prompt better adjectives. It belongs to people who design better frameworks. - Codify what matters. - Turn instinct into architecture. - Let AI operate inside it.

John Backus (@backus) 's Twitter Profile Photo

POK(AI)MON: Experimenting with GPT 5.4 autonomously editing and rewrite the Pokémon Red ROM, replacing Pokémon with AIs. Details below

Alex Prompter (@alex_prompter) 's Twitter Profile Photo

🚨BREAKING: Alibaba tested AI coding agents on 100 real codebases, spanning 233 days each. the agents failed spectacularly. turns out passing tests once is easy. maintaining code for 8 months without breaking everything is where AI collapses. SWE-CI is the first benchmark that

🚨BREAKING: Alibaba tested AI coding agents on 100 real codebases, spanning 233 days each.
the agents failed spectacularly.

turns out passing tests once is easy. maintaining code for 8 months without breaking everything is where AI collapses.

SWE-CI is the first benchmark that
Alex (@alexandertw33ts) 's Twitter Profile Photo

maybe the real autist/adhd advantage is that we can move up and down abstraction layers when tech like this comes along we don't even notice the change agent-maxxing feels exactly the same as writing x86 did in my first year of college i'm typing in a computer, problems are

maybe the real autist/adhd advantage is that we can move up and down abstraction layers

when tech like this comes along we don't even notice the change

agent-maxxing feels exactly the same as writing x86 did in my first year of college

i'm typing in a computer, problems are
BLASTΞASY (@blasteasy) 's Twitter Profile Photo

Anyone using AI to write code has hit this wall: ✅It compiles ✅It passes tests ❌It looks totally wrong Which is exactly why when the full 2D lighting pipeline landed, the thing that actually made it work was this UI debug panel exposing every lighting parameter as slider:

Doug Lance (@dwlance) 's Twitter Profile Photo

just shipped @douglance/play, a zero-boilerplate Playwright runner with durable named sessions, live debugger controls, and flat agent-first inspection commands great for letting LLMs drive and inspect a browser without writing test files npm i @douglance/play

Andy Johnson (@andytfe) 's Twitter Profile Photo

A fun little interactive page we built for Augusta National where you can click into every hole with analysis, strategy and best shots. Check it out and let us know what we missed. thefriedegg.com/articles/maste…

Justin.eth Drake (@drakefjustin) 's Twitter Profile Photo

Today is a monumentous day for quantum computing and cryptography. Two breakthrough papers just landed (links in next tweet). Both papers improve Shor's algorithm, infamous for cracking RSA and elliptic curve cryptography. The two results compound, optimising separate layers of

Hayden Adams 🦄 (@haydenzadams) 's Twitter Profile Photo

People might accuse me of grave dancing for saying it But we have to stop letting centralized things call themselves DeFi Admin key can drain all funds? CeFi Otherwise DeFi means nothing and it’s brand is destroyed No admin key can drain any version of Uniswap for a reason

Alex Finn (@alexfinnx) 's Twitter Profile Photo

Do you even understand what this means? An open source model just released that is: • Outperforms models 20x its size • Can run on a base model Mac Mini • Is AMERICAN 🇺🇸 If you have a base model Mac Mini you can have unlimited super intelligence on your desk. For free.

CupoJoseph 🐌 (@cupojoseph) 's Twitter Profile Photo

I'm running for US Congress. Seriously. Imagine common sense crypto policy and regulation, aligned with American dynamism. Check out our list of new Crypto Policies we will support, linked below. x.com/va_joe/status/…

ℏεsam (@hesamation) 's Twitter Profile Photo

Google DeepMind researcher argues that LLMs can never be conscious, not in 10 years or 100 years. "Expecting an algorithmic description to instantiate the quality it maps is like expecting the mathematical formula of gravity to physically exert weight."

Google DeepMind researcher argues that LLMs can never be conscious, not in 10 years or 100 years.

"Expecting an algorithmic description to instantiate the quality it maps is like expecting the mathematical formula of gravity to physically exert weight."