Harmonic

259 posts

Harmonic banner
Harmonic

Harmonic

@HarmonicMath

Building Mathematical Superintelligence

Katılım Ocak 2024
5 Takip Edilen18K Takipçiler
Sabitlenmiş Tweet
Harmonic
Harmonic@HarmonicMath·
Many of us intuitively feel that the field of mathematics is going to change, so let's unpack the likely outcomes, without resorting to hyperbole or doomerism.
English
15
36
331
73.7K
Harmonic retweetledi
Kimon Fountoulakis
Kimon Fountoulakis@kfountou·
This seems to be working well. I tried it on a few lengthy but simple proofs that I got from GPT-5.4 Pro. It seems to have worked flawlessly.
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
1
1
8
1.4K
Harmonic retweetledi
Jiaxin Song
Jiaxin Song@JiaxinSongXYZ·
Really impressive work! It took just a few hours to formalize two classic algorithms in game theory. One of them took me three weeks, and I wrote nearly 2K lines Lean code, while Aristotle agent only spent three hours and used 400 lines. I am so surprised
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
2
6
43
3.8K
Harmonic retweetledi
Bernardo Subercaseaux 🐒
Bernardo Subercaseaux 🐒@b_subercaseaux·
It correctly formalized a graph theoretic proof from our recent STOC paper in one shot. It’s only 1 page on paper, but I’m still impressed; 450 correct lines of Lean is no small feat—that used to take me days!
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
2
5
42
3.1K
Harmonic
Harmonic@HarmonicMath·
Aristotle is now on @leanprover 4.28 Happy vibe proving!
English
3
11
115
4.3K
Harmonic retweetledi
Sidharth Hariharan
Sidharth Hariharan@SidharthHariha1·
Very excited to start using this!
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
0
2
23
6.4K
Adrian Miranda
Adrian Miranda@AdrianTMiranda·
I have also been having this issue with Aristotle by @HarmonicMath. It often claims to have proven something, only to include commented fine print in the lean doc saying that it has actually proven something else. Better flagging of partial progress would be appreciated.
Jasper Dekoninck@j_dekoninck

Aristotle just claimed it formally proved Q8 from BrokenArXiv, despite the statement being wrong. It then continues to point out an important caveat that states the problem is not expressible in Lean and it therefore proved something completely trivial and irrelevant instead.

English
1
1
9
615
Harmonic
Harmonic@HarmonicMath·
🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥
Harmonic tweet media
English
27
115
730
233.8K
EYOV
EYOV@everolivares·
@HarmonicMath Yes tried installing /running in a dedicated repo. Submit question on cli and get back Aristotle or Aristotlelib not found. Not sure how to ask a question
English
1
0
1
167
Harmonic
Harmonic@HarmonicMath·
@schulzb589 We can get a bit backed up sometimes. Working to make it faster …
English
0
0
2
24
Tudor Achim
Tudor Achim@tachim·
This is a huge upgrade -- Aristotle can handle much larger and more complex projects than before. Stay tuned for what's coming next! 🚢🚢🚢
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
2
9
70
8.3K
Harmonic retweetledi
Alex Meiburg
Alex Meiburg@Timeroot·
I've been using the preview version of this for a couple weeks and it autonomously proved Strong Subadditivity, a deep theorem in quantum information. I just gave it a relevant arxiv paper, ran it ~6 times in a row, and boom!
Harmonic@HarmonicMath

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

English
3
11
66
10.1K