Cognition's Devin agent resolves decades-old open math conjectures
It refuted a 40-year-old conjecture using Terence Tao's prompting method.
1281.2K10341150.5K
Original post unavailable.
Sentiment
Many users praise AI Devin for refuting and proving decades-old math conjectures as a remarkable research milestone, while others dismiss the announcements as misleading or inauthentic.
Pos
88.9%
Neg
11.1%
15 comments with sentiment.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Related links
Posts from X
Most Activity
Most Activity
VIEWS11.9KBOOKMARKS27LIKES192
the math unhobbling is happening
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
RETWEETS6
Cool. Everything is about to accelerate… age of wonders if we get it right.
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
REPLIES6
it’s like a world wide easter egg hunt right now
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
Devin.
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
guys you can’t claim your Devin solved unsolved problems when it’s literally Fable and 5.6 calls in the backend. come on
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
EDIT: Looks like #154 was solved a month ago in https://github.com/demonstrandum-research/artifacts/blob/main/RESULTS.md
just solved another unsolved problem btw
1) Graffiti Conjecture 154 REFUTED. Open for ~40 years. Devin found the counterexample: glue a 50-clique to a 70-edge path (n=120). The violation reduces to a single integer inequality, proven in Lean down to the graph's distance sum. 2) Graffiti Conjectures 39 & 40 PROVEN. From the same 1988 Graffiti program. The standard deviation of a graph's distance matrix never exceeds its number of positive (#39) or negative (#40) adjacency eigenvalues. Both are TRUE. It’s a 4-line proof chaining Popoviciu's inequality on variances with a 2020 spectral lemma (Geng–Wu–Wang) nobody had connected to them. 3) Brandt's Regular Supergraph Problem from West's open problems list REFUTED. Found a 9-vertex counterexample where no amount of vertex cloning (duplicating a vertex with the same neighbors) can ever make it regular. Certified by an exact Farkas infeasibility certificate Now it's possible this is actually a 20-year-old typo. Brandt's original paper says strictly greater than n/3, but West's open problems list says at least n/3. And it's false exactly at that boundary.
@imjaredz All attributions shall go to Soltra, let's go.
@imjaredz is that fable, 5.6 sol?
@JTLonsdale Hey Joe how about instead of giving 90% of your wealth to taxes you pull together something considerable and drive a call to action amongst homies to run back the Rough Riders bringing in Baja California as a new economic zone while tapping into equity @LatinoFreeMinds for @GOP
@BensBeardButter @LatinoFreeMinds @GOP I am doing very bold stuff like this except the IQ-160 version with a lot of talented and aligned people in my policy group, university, and with mission-driven companies. I agree we need to be courageous and smart, and fight for our country and our future in novel ways.
@JTLonsdale @LatinoFreeMinds @GOP That's true you are doing great work with Cicero and Univesity of Austin I don't mean to dismiss - but Rough Riders has layers that integrate in terms of getting into the liver of progressive policy with prison reform that you're being sub 160 IQ on to dismiss so easily
@imjaredz This one is 20 years old
@ar0cket1 Devin Ultra mode
@JTLonsdale @LatinoFreeMinds @GOP Even if you want to reserve your Alpha for your current ambitions deploying your Sigma w @WhiteHouse could get momentum on the policy templates I'm cross pollinating on IG to build momentum I've backed what you're doing for free from the streets for years - we aren't competing
@imjaredz it’s just the beginning
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
Dinitz-Garg-Goemans conjecture is false. This graph theory problem was open for ~30 years. The graph below has fractional flow cost 58. Any unsplittable flow (with capacity violation <=15) has cost at least 60. Chat with GPT 5.6 Pro where this was found: https://chatgpt.com/share/6a60b2eb-0b64-83ee-9c76-7931ca1de063
Load more posts
I got totally nerd sniped today I'll share more of the methodology soon, but basically I had a few Devins research good problems similar to the one the OP solved Then I picked the best problems Then I spun up ~5 Devins in Ultra mode for each problem to find & verify solutions (machine-checked in Lean) Repo here https://github.com/jzone3/solving-math-problems