bluepoint

How does it fare with stability? The golden age version (e16?) was fun but would crash regularly.

I don’t know what you mean by negating the subexponential time. If the reduction is polynomial the time is still dominated by the 3SAT. Btw wikipedia says that the proposed algorithms correspond to 2^(n (log log n)^2/log n) which is subexponential but not in a practical way.

Edit: Ok, I a guess I am wrong if the reduction is n^ log n/(log log n)^2 we are back to exponential.

You are talking about high energy physics. In high energy maybe AI can help analyze accelerator data and physicists are probably already using it for that. There is theory all over the place, including condensed matter, a branch related to quantum physics of many problems and includes some hard problems like high tc super conductivity. Many (most?) theorists that manage to get interesting publications have early access to experimental results and can help direct experiments. AI maybe not have much to say about the occasional experiment that showed some unexpected result. Also in general in physics the objective is rarely to solve a mathematical problem exactly, it mostly finding the right model and right approximation and compared to math it is a bit like fuzzy logic. I am not sure if the process has been codified to the extent that AI can pick it up from its training set, but we never know.

I never heard of it. It says that it is a fork of lite cl, which is a fork of lite, but they are not driven by minimalist ideology. And they pose as an alternative to vscode without the webbrowser. Will it replace neovim for me? Let’s see.

> This I don't know about. I think math acquires meaning when it contacts reality: like an iota is pointless until there's some circuit that it explains. Abstract math can diverge from that and can become an exercise in playing with symbols for their own sake.

After talking to a mathematician friend I can assure you that contact with reality is not the main goal of abstract math. It is mental constructions that have logical consistency and probably this is not the perfect definition either. It is somewhat of an art which is rendered in the logical mind. However physicists (me) and engineers will align with you.

From them demo it looks like some search on structured data interface. So model the git data somehow and then index them?

I have thought that I want to share as a semi pro programmer. Nowadays it is so easy to ask an agent to code for you that every moment you spend coding seems like a waste. I am not even talking about the reasoning or planning, but the actual typing out. Even if I understand perfectly well what I want and how to type it, it is still faster and less error prone to ask the llm to do it. It is fine, but no fun. Also I can never be sure that the llm did the thing I had in mind. For exploratory programming and analysis I rather try 100 different queries my self, but then I have to type endlessly (which I may optimize in time, but not if I have a new quest or project where I need to look around first).

I want a very very coarse language that I can wrap around maybe an existing language, maybe after asking an llm to create an adapter that will allow me to type faster than the llm

Say SELECT c.name, c.email, SUM(o.total) AS spent FROM customers c JOIN orders o ON o.customer_id = c.id JOIN addresses a ON a.customer_id = c.id WHERE a.country = 'AR' AND o.created_at >= '2026-01-01' AND o.status <> 'cancelled' GROUP BY c.id, c.name, c.email HAVING SUM(o.total) > 1000 ORDER BY spent DESC LIMIT 10;

and compress it to

c+o+a|a.cn=AR,o.d>26,o.st!X|c:nm,em,$tt>1k|v10

(I made up a random example with claude).

I know about J and Q but they cannot be used with sql databases or existing python libraries.

Anyway. I am not sure if anyone has such concerns.

Is this paper in arxiv?

Actually I get improvements when I ask two llms to simplify each other’s work repeatedly.

This sounds like a resolution for the Fermi paradox.

How dis he do all these animations? Any idea?

You mean they don’t understand the “but no simpler” part?

Reading the comments, is it safe to say that LLMs are a digest of the internet which is some update over google search, but with the caveat that you need to double check the results? I mean they basically have some compressed version of almost all the written knowledge and will respond correctly about things that have already been written, and hallucinate (extrapolate) about things not explicitly written. Of course if someone carefully curates the input data to filter out misinformation, it might even be an upgrade over google. Is there a consensus on this?

The author claims to be able to tell AI content. I am wondering, is there any test to help me train to distinguish AI content? Like: this paragraph is written by a human this by an AI and see how well we all do?

Does anyone of if there are any consequences of the existence of monotiles in algebra or number theory?