pbronez

Interesting, makes sense. JIT in CPython main is a big deal, glad they’re proceeding with caution. Overall looks like they added it as an experimental feature for two years, then decided to back it out. Perfectly reasonable outcome.

Try Lewis Cole or The Comet is Coming

How do I find and hire a UX person like this?

I'm astonished you've managed to coax AI into a novel conversation partner. Interacting with AI usually leaves me exactly "super bored and partly drained by the lack of speed and creativity."

All the novelty of AI engagements comes from data it pulls in via tools. It's great to have a conversational interface over the public web, but there's a huge difference between knowledge retrieval and insightful conversation.

Please share how you've cracked this so we <2sd minds can enjoy the crumbs from your lofty table.

This is fascinating. I’m intrigued by the combination of discursive metaphor and weak convention to define actor identities.

The writing style is not natural to me. I was initially put off by phrases like “YAML Jazz” even though I love Tron’s “digital jazz”. Maybe this is because I’ve never experienced psychedelics. I’m at least two generations beyond / behind - removed? - from the movement that defined this way of thinking and communicating.

But sitting with it, it makes sense. I have to stretch my brain. It feels like thinking through a new algorithm… except I’m juggling jello instead of assembling a puzzle.

Ultimately it aligns with my understanding of AI as xkcd’s stirred pile of linear algebra. LLMs don’t understand anything. They project words into probability space, infer momentum vectors based on chunks that bubbling up in the soup of digested everything, and strike out in the prognosticated direction with blind confidence constrained only by temperature.

We constrain these systems with sandboxes and sturdy deterministic tools. Prompts default to the same shape: sharp, precise, hard, directive. But maybe a bag of words is also valid.

If the computer knows your references, each token is much richer than I might assume. Does “minsky” vendor the psychedelic moment? Does “SIMS” scaffold a game loop worth of the emotional energy people have poured into that series? Do these combine to elevate Claude, Qwen, or any other multi-million-dollar number box into an engaging partner?

I will play around it with it to find out.

AppleTV does support multiple users, but it’s terrible.

I have an AppleTV on the main television, with Apple accounts set up for each member of my family. It makes almost no difference which user you have selected.

Now, maybe I just haven’t spent enough time trying to set this up, and I’d be delighted to be wrong, but AFAICT:

All users share the same Home Screen layout

All users share the same screen saver

Third party apps have zero integration with the AppleTV accounts. This means I have 4 users on the AppleTV, then 3-5 users on every single app installed on the Apple TV, and any AppleTV user can use any app user.

All together this means the AppleTV users are useless to me. They don’t help me with parental controls. They don’t help me switch between personalized content collections. They don’t even help me log into third party apps!

This should be so much better than it is.

I think some of that is defensive. They don’t have a GPU or other AI Accelerator story right now. They have to remind people that regular compute is still relevant for all the other stuff around the AI workload.

That said AMD’s participation in this round + heavy hints on the podcast and YouTube suggest they will pursue an GPGPU Compute Sled built around an AMD product.

Yeah the README on OpenAI/Math says:

“On average, each result used three hours of ChatGPT Pro thinking compute with that model. Over the course of the evaluation, the model was posed approximately 4,000 problems.”

That leaves a lot of ambiguity. Is “result” exclusively “positive result shown here” or “all results”?

Since proving infeasibility is a valuable result, the unpublished problems must not have reached a valuable end state. Thus it’s an operator decision of when to turn the machine off and try another problem. I’d thought they had a three hour time box on this, but apparently not.

So much about LLMs can be framed as Information Retrieval, Compression, and Search. Computers have always been good at ruthlessly hammering through a huge but finite set of possibilities. The wild thing now is that you can define that set of possibilities as "all the ideas ever published in mathematics journals."

It makes solving advanced math problems feel like cracking a hash. If it's possible, it's just a matter of compute time.