pshc

The Incredible Machine vibes.

Only 30 tok/s on Qwen 3.8 Flash Next? These days thanks to those specialized engines out there I can get ~2x that speed on a 24 GB video card with RAM offload. Thermal limits, I assume...

I wonder how its performance is on dense models.

Yeah, the documentary was going hard on the dissonant horror movie strings right from the opening.

And near the end, that bubbly euphoric/revelatory ascending arpeggio was a common motif.

Surely their goal is ever-faster recursive self-improvement.

Passkeys only give a random public key + some capability bits, whereas almost all password logins ask for your email or phone number, for the inevitable reset dance likely facilitated over antiquated email or SMS. Realistically the latter is much leakier.

I could believe it. Honest to goodness, they might save my eyesight. No more marathon sessions staring at the screen for hours editing text.

Rewrite everything in Rust has been a meme for so long that to see it coming to pass is surreal.

I think it’s similar to the reasoning behind HN stripping numbers from clickbait headlines. Numbers feel salient even when they represent nothing at all, because numbers are used universally in every field of human study and endeavor. Unlike field-specific jargon.

I've been experimenting with a Remarkable Paper Pro.

Additive inking works pretty well. As long as I am adding black ink to the page, everything is responsive. But if I want to push other updates asynchronously, or (god forbid) erase something, then there is the danger of clobbering the user's inkwork. I don't have any deep insights here, beyond waiting for human confirmation before updating anything.

I wonder if it is possible to detect when the pen tip has "left" the proximity of the page? If I knew this, I'd know when it was safe to update the UI.

I have decided not to use any scrolling at all. I am paginating everything and positioning input areas near the vertical middle of the device for comfort.

Very glad to see this, I've been dreaming about spatial representations for code for a long time.

Same, I was actually having interesting thought experiments with Fable.

Even though it's quantized-to-hell Mixture of Experts, honestly, it's crazy this model can run semi-coherently on an phone.

Wall mount? I'll pray for an e-Ink model.

With batched parallel requests this scales down further. Even a MacBook M3 on battery power can do inference quickly and efficiently. Large scale training is the power hog.

I was daydreaming of a special LLM setup wherein each token of the vocabulary appears twice. Half the token IDs are reserved for trusted, indisputable sentences (coloured red in the UI), and the other half of the IDs are untrusted.

Effectively system instructions and server-side prompts are red, whereas user input is normal text.

It would have to be trained from scratch on a meticulous corpus which never crosses the line. I wonder if the resulting model would be easier to guide and less susceptible to prompt injection.

Yeah, myself and several friends of mine with EOL Windows 10 PCs are looking to jump ship.

MacBooks outclass any other laptop in the market thanks to those chips.

We can spend more time on art, music, camaraderie, love, play, and the pursuit of grace.

apparently this is the source: https://youtu.be/1L2ef1CP-yw

The fan increases air speed at the centre of the rotor, creating a low pressure zone which then sucks in surrounding air. So it helps to place the fan away from the window (roughly far enough that the wind cone "fits" the opening).

This stuff is a dream of mine, editors in different modes that can collaborate seamlessly. Keep up the good work!

I think we need a spatial/physics model handling movement and tactics watched over by a high level strategy model (maybe an LLM).

Compared to google translate of yore, it’s gotten way more fluent thanks to transformers. Good translation relies heavily on context of course. Voice recognition and text to speech quality have increased dramatically. And near real-time (or as real-time as is possible given a pair of languages) is becoming feasible.

What’s wild to me is that we have basically manifested the Babel Fish in the last few years.

Meanwhile Switzerland is implementing e-ID which gives citizens private and public keys so they can sign and prove things without leaking their whole identity.

Sometimes a problem is a weird combination of hairy/obscure/tedious where I simply don’t have the activation energy to get started. Like, I could do it with a gun to my head.

But if someone else were to do it for me I would gratefully review the merge request.

They do discuss optimization of the IDs at the bottom of the article.

Use of server reconciliation makes me think client-side reconciliation would be tricky… how do you preserve smooth editor UX while applying server updates as they arrive?

For example, if your client-sent request to insert a character fails, do you just retry the request? What if an update arrived in the intervening time? (Edit: they acknowledge this case in the “Client-Side” section, the proposal is to rewind and replay, and a simpler proposal to block until the pending queue is flushed)

From a frontend vantage I feel like there may be a long tail of underspecified UI/UX edge cases, such that CRDT would be simpler overall. And how does the editor feel to use while riding the NYC subway where coverage is spotty?

Have you tried Zed?