hollowturtle

They would have used the voice by now and yet we're still all here correcting errors made by the touch keyboard. And no no one sane would use the voice in public or in office thinking out loud. Especially for doing basic things like pushing a button

That would be dumb and dangerous. That said local storage is used by all major frameworks/libraries for storing jwt tokens of the current session

Nah. You either are like Rick Rubin or you're not producing anything

These AI demos all look the same

You're not asking this seriously arent you? Local storage follows strict security policies, go read the spec

> next generation of AI-natives

oh please current generations can't barely use a keyboard

The end user of a product is a human and it will ever be. No matter how far you push it on the boundary, there will always be a human. So I don't understand this obsession with automated software factories going 24/7. And for building what? Can dot build or any super expensive model inside the most advanced harness build a reliable browser from scratch with better performance than chrome and with the same feature set? Hasn't happened yet, only crap experiments

Looking for a job? This sounds like personal marketing speech rather than a blog worth reading, no new insights no nothing

> There is not always a “dismiss” button to shoo them away for good, and when there is, some people have reported that it doesn’t seem to work.

Welcome to my world where "Show fewer shorts" on YouTube has been clicked I dunno anymore how many times, it's an habit now

> What gives you the impression an LLM made this? It doesn’t have any overt signs.

It's lazy, it doesn't look good on desktop too. The navbar screams justice. If it hasn't been made by an LLM it would still be a lazy human

Bummer it doesn't work on mobile, we used to be mobile first now it's whatever the clanker spits out. Before you push back I must remind you that https://ciechanow.ski/ has very complex visualization perfectly accessible from the mobile phone

I expected something like "I was wrong coding is not solved" alas

go is even more straightforward for llms imo. It's a dead simple language with a good garbage collector, where you can still do a lot memory management

> The original TypeScript implementation completed 7.55 of those lifecycles per second, while Rust running in-process managed 120 per second - representing a 15.9x speedup on that particular workload.

Does this impresses/surprises anyone? Two folds: 1) I believe the most optimized JavaScript code could near the performance of this phase 1 port without optimizations. I would have gone with that first, many would think that would not be as cost efficient but: 2) optimizing the rust code will require 10x the effort of the 1 by 1 conversion, just because you now need idiomatic rust code that likely has nothing to do with a plain translation. So defeating the initial gain, there's nothing to do the bottleneck gets just pushed elsewhere

Everyone uses AI - yes me too. Everyone to code? I dunno know and no one actually know for sure. I find it more productive in many ways, not much for producing code, if not for highly verbose structured output. And I'd be interested in a new language polished to solve specific problems differently even if it doesn't mention ai. We did engineering for decades in this way

> Agents can oneshot games that are actually fun.

HAHAHAHAHAHAHAHAAH

here we go again

Would the author have specified on the page that it's a fast new language with a new take on proof and so on, without mentioning ai and that alone would have caught my attention. It seems like if there isn't the word ai people are not interested anymore, we used to care many of us used to care

Hard to find a site this less interesting, for a product this less interesting from a company that i would never trust

Did you need ai to hold together a bunch of paragraphs and a table really? holy moly

> to the point that they can solve major outstanding problems in many fields of mathematics

I will die on this hill, humans solve math problems not machines, there's no automatic math prover out there. There are humans attempting to solve this problems either by leveraging these tools or not

psychosis

Does that mean no more react native skia sponsoring?

Imo Eventually we will circle back to nonfiction quality books, for one just to decrease screen time :) for second we actually need them even for chatgpt

Lately whenever I enter a book store in Italy, I'm overwhelmed by the amount of fiction romance for girls and womens. I get 3/4 of readers are womens but all I'm left with is a gigantic pile of nonfiction shit I'm not interested about, I know for sure most of it will leave nothing to me. Increasingly way too many people attempted to sell a bunch of nonfiction books, and it shows there amounts of unsold copies. Most of them being a marketing political campaign. There gems for sure but it's becoming increasingly harder to find them. Also the only fiction books I'm interested about are sci-fi, and the dedicated space is soo small that you feel a weirdo with strange hobbies. But I swear to you, cause I read a fantasy novel from my wife's selection, that a saga like The Expanse is 100 times better written than all that new shit. Finally rest of the book store is now dedicated to manga and graphic novels. Not bad I love them but the ratio is overwhelming as well

I would read it

> writing code, finding security bugs, and proving mathematical theorems

While the second can be automated as in "this is the repo go on and look for security issues", the first one and especially the last one do not ever happen alone. Terence Tao did the math proof not chatGPT that was just used as a tool, a tool can do smart things but it's not smart

> trying to process the sobering fact we will actually see machines meaningfully smarter than ourselves in our lifetime

Being able to reproduce useful patterns yes, smarter no

Is there any point anymore regarding this svg test? I would not be surprised if in the training they're fine tuned for this task too

> Jin reported that the proof was obtained with the assistance of OpenAI's GPT-5.6 Sol model during an approximately sixteen-hour autonomous reasoning session in ChatGPT Work, after which he checked the resulting argument

You're wrong

> People have been correctly excited about the many "sudden" breakthroughs LLMs are making in Maths

That people ARE making, surely not machines. Like Terence Tao or Knuts did using the tool to their advantage, for example it would have been impossible for me to prove the same thing Tao did with an LLM. Same reason I believe programmers won't go away