diffshub[dot]com
Take any public diff from GitHub and virtualize it nearly instantly, no matter how large, with DiffsHub. Built to show off our brand new CodeView component.
To try it out, replace `github` with `diffshub` in your address bar.
We are introducing EU Inc. To make building and growing a business across the EU faster, simpler, and smarter.
🔸 Start a company in less than 48 hours
🔸 No minimum capital requirement
🔸 Fully online and borderless
Double-slit experiment in JavaScript: a single rule about console.log() produces a zoo of quantum phenomena.
which(
function path1() { return 0 },
function path2() { return 1 },
) // → 0.5
https://t.co/yVoh5WPP4b
I think it must be a very interesting time to be in programming languages and formal methods because LLMs change the whole constraints landscape of software completely. Hints of this can already be seen, e.g. in the rising momentum behind porting C to Rust or the growing interest in upgrading legacy code bases in COBOL or etc. In particular, LLMs are *especially* good at translation compared to de-novo generation because 1) the original code base acts as a kind of highly detailed prompt, and 2) as a reference to write concrete tests with respect to. That said, even Rust is nowhere near optimal for LLMs as a target language. What kind of language is optimal? What concessions (if any) are still carved out for humans? Incredibly interesting new questions and opportunities. It feels likely that we'll end up re-writing large fractions of all software ever written many times over.
If you like vibe coding you should also like typed pure functional programming. Any other position is inconsistent.
Pure functional programming is the only sort of programming which permits unrestricted denotational reasoning. Denotational reasoning means the scope necessary for the LLM to perform its task is finite (and in principle knowable, as long as you have types). Even more important it also means that you (and the type checker) can review the LLM output and be confident in the lack of accidental coupling.
Denotational reasoning enables reliable top-down reasoning at arbitrary scale. You can be certain that high-level reasoning, albeit incomplete, is absolutely correct, you don't need to attempt low-level reasoning if you do not care about low-level details.
However, it seems to me that vibe coding enthusiasts do not care a bit about pure functional programming, or about software engineering in general. In fact I see an inverse correlation between people who care about scalable and correct engineering and vibe coding enthusiasts.
also added some quality of life improvements: quick buttons to switch between terminals, arrow key navigation, and a .text command to copy screen content as a text message
fork: https://t.co/3qsCNyZ6hz
I've just cloned tgterm and added Linux support (in addition to macOS), you can now use it to control remote agents on @flydotio's Sprites from Telegram
the updated README covers the headless setup with a virtual display
As an example of how we are building on top of Gemini 3, AI Mode in Search now uses Gemini 3 to enable new generative UI experiences, all generated completely on the fly based on your query. Here’s how you might use this to learn a complex topic like how RNA polymerase works.
The point of our work isn't to build an artificial human. The universe is full of questions far more interesting than our own reflection. The point is to create a new kind of mind to help us explore & understand the universe better than we can ourselves.
🔥 @GoogleDeepMind just dropped their "formal conjectures" project - formalizing statements of math's biggest unsolved mysteries in #LeanLang and #Mathlib!
This Google-backed project is a HUGE step toward developing "a much richer dataset of formalized conjectures", valuable for benchmarks and growing the Lean ecosystem.
The project was open sourced today! And you can be part of it! Check it out: https://t.co/JHrdeahAlU
#LeanProver #FormalMath #AIResearch #GoogleDeepMind
Introducing the next generation: Claude Opus 4 and Claude Sonnet 4.
Claude Opus 4 is our most powerful model yet, and the world’s best coding model.
Claude Sonnet 4 is a significant upgrade from its predecessor, delivering superior coding and reasoning.
"The ultimate goal of AI for math: the ability to generate new theorems...requires something we might even call 'taste.' But we’re starting to see some preliminary thoughts on how we might get there."
our latest from @AdamMarblestone
https://t.co/nhYhgXkUzD
We just launched Corca—a collaborative math editor. The main idea: there’s no 'text editor' for math. If you want to work on equations on a computer, there’s no app designed for that—so the only real option is paper.
↓
Microsoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. https://t.co/z9yOaV7VGo
@kingprotty It’s very cliche but something like art to me. It’s how I express my creativity. I’m not musical, I can’t draw well, etc. but I feel I can express logical abstractions in a way that makes me and others feel something
Introducing AlphaQubit: our AI-based system that can more accurately identify errors inside quantum computers. 🖥️⚡
This research is a joint venture with @GoogleQuantumAI, published today in @Nature → https://t.co/AtbWuddxxe