Hacker Newsnew | past | comments | ask | show | jobs | submit | seeknotfind's commentslogin

I would worry more about 5D chess or 6D and even 7D chess. This article talks about teaching models to be good and methods that could train goodness, but it sounds like there are some unsolved problems to graduate to 8D+ chess.

Is this supposed to be scary or amazing?


Your comment is probably the most disturbing thing I’ve ever read on this website


[flagged]


Astroturfing crosses all boundaries eventually.


Wow. This is incredible. Turning the entire field of mathematics into a formalized and connected system. An index of mathematical understanding. All fields will undergo this change!!!

My man Terrance Tao, I hope to contribute to your symphony of progress.

If the interrelationships of this are also exposed and searchable, if it can build many bridges inside itself, then this is truly the cipher key to all that can be known.


Every math paper ever (there are about 4 million of them) will get formalized. One benefit of this is finding out which ones were actually correct, and which had unrecognized flaws in their claimed results.

After that, we can do statistics to see which ideas in math are most used, and perhaps mine for unrecognized patterns, refactoring math to find new abstractions.


100%. Context is big for AI, but it's nothing compared to everything a human can learn. If you efficiently represent everything in context, it may be many papers, but if AI is actively working through proofs, it will quickly fill up. They're no denying AI is making strides, but pinning it to memory is an oversimplification.


We are?


Autocorrect changed “were” to “we’re” and I didn’t catch it


If you're calling this across translation units, the calling convention will come with a performance penalty, but boy have we come full circle since pre-ANSI C required you to pass args as a struct. Much love - wish the language required struct and arg list to be the same thing. You can send a list of em and it'll work with algebraic data types for batching calls. The dream. CPU doesn't play nice though since structs aren't register shaped, but maybe they could be in a future calling convention.


You can click on that to see more detail :)


I guess it’s just not designed for mobile. Tapping didn’t reveal anything.


It works well on Android. Just zoom in and click the number, and you can breakdown per state. Click on any state number and it breaks down per city.

Pretty functional design.


I had to click the blue number twice to get it to open on iOS, though I was also confused at first.


"I'm sorry". What do HN readers think about how this inclusion changes the meaning of the rest of the email?


Did you ever try multiple copies?


I did, but the combinatorics are mad. I have also tried training a meta-model that predicts the outputs of the combinations.

I will make another post if the topic is popular; its pretty geeky though, even more than my usual blog posts...


My first idea would be to generate one of those heatmaps using RYS as the base model. And see if it gets meaningfully better. And then again!


They're are plenty of mods that inject AI into games, like Skyrim. Though in order for a game to have LLMs and scale to a shipping audience without a subscription, you would want to run them locally.

The real technical blocker is performance and voice synthesis. If voice synthesis was at parity with human actors, it would be worth it to battle the performance aspect for major studios. In text based games especially, taking time to generate enough text is just too slow to be convenient


Yeh there is a skyrim mod that lets you talk to any NPC and basically queries an LLM behind the scenes even with a screenshot of the scene so it can react to your clothing etc. if you insult it the LLM understands it dynamically and makes the NPC attack.

I mean thats not a new game concept but I definitely think that levels up the experience.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: