tweetindex
EN

Keenan Crane

@keenanisalive · Pittsburgh, PA · joined 25 Jan 2008

Digital Geometer, Assoc. Prof. of Computer Science & Robotics @CarnegieMellon @SCSatCMU and member of the @GeomCollective. There are four lights.

39 277Followers
519Following
5 344Posts total
605.1KViews on collected posts

Latest posts

People don’t make art for the artifact. 5.7K views · 30 likes · 0 reposts · 4 replies Open on X →
I am, shall we say, disinclined to push anyone to try to experiment, but I wonder how much longer my "yes, but my artform produces a physical object" moat is gonna stay moaty. 16.8K views · 308 likes · 7 reposts · 20 replies Open on X →
⚠️ PSA: This week will be like April Fool's regarding results made by (& ostensibly made by) frontier models. 🤖 Some of the demos are truly impressive. Others are things we could *already* generate in < 30 seconds, since the 1990s—like procedural terrain. Don't be fooled. 🤡 ht
1:07
14.2K views · 134 likes · 18 reposts · 6 replies Open on X →
This is what Astra did in Blender in 30 seconds. We are so unbelievably cooked. https://t.co/Rftidrc5ZT
1:07
242.3K views · 2.4K likes · 133 reposts · 166 replies Open on X →
@keenanisalive @UsePenrose Wow Penrose is amazing 388 views · 1 likes · 0 reposts · 0 replies Open on X →
@keenanisalive @UsePenrose too smart @keenanisalive ! 482 views · 1 likes · 0 reposts · 0 replies Open on X →
Yes… and we were making diagrams like this a few years ago, without any AI / LLM help, much faster and with more user control, via @UsePenrose: https://t.co/Lcvp4lvQ8U https://t.co/jfv0Bw7l0y But it's not an either-or: You are always going to get more mileage out of LLMs https
20.8K views · 200 likes · 19 reposts · 2 replies Open on X →
I AM ABSOLUTELY SHOCKED. A mysterious new model called Farris just showed up and completely demolished Fable 5 — it made it look like a toy. here is side by side comparison , 10x speed https://t.co/yjlTy8v6ao
0:10
188.4K views · 688 likes · 16 reposts · 16 replies Open on X →
Proud and excited that my former PhD student @nmwsharp, will be joining the CS faculty at the University of Washington next year! Check out his awesome work at the intersection of geometry + ML here: https://t.co/PkzcERom3P (And go work in his lab! 😀) 10.7K views · 133 likes · 1 reposts · 0 replies Open on X →
Excited to announce: In 2027 I'll join the UW Allen School (@UWCSE) in Seattle as tenure-track faculty in Computer Science! My group will advance core geometry processing + 3D AI for visual computing, science, & engineering. I'll be recruiting PhD students in the next cycle! htt
27.9K views · 448 likes · 32 reposts · 38 replies Open on X →
I work on fundamental algorithms for geometric and visual computing. Here's a taste of our group's work, as a list of "explainer" threads posted on Twitter/X over the years. (🧵) For a whole lot more, check out: https://t.co/VGiwZeOGVd https://t.co/TzozBQSgBy https://t.co/pecsfT
77.5K views · 641 likes · 93 reposts · 5 replies Open on X →

Against accounts of the same size

10 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views15 534this account928median for 10K–100K
Reach, %39.55%this account3.52%median for 10K–100K
Engagement, %1.09%this account1.95%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post15 53492816.7×
Reach (views ÷ followers)39.55%3.52%11.2×
Engagement rate1.09%1.95%0.56×

Others in this range →   Compare with another account →   How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

77.5K26 Aug
27.9K18 Aug
10.7K
188.4K26 Aug
20.8K
482
388
242.3K3 Sep
14.2K4 Sep
16.8K6 Sep
5.7K

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.96%26 Aug
1.86%18 Aug
1.26%
0.38%26 Aug
1.07%
0.21%
0.26%
1.13%3 Sep
1.11%4 Sep
2.02%6 Sep
0.60%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.95%.

What the audience does

Likes69.1%4 993 in total
Reposts4.4%319 in total
Replies3.6%257 in total
Quotes0.7%49 in total
Bookmarks22.3%1 612 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

Followers by day

7 Sep

Daily snapshots since 07 Sep 2026; the dashed line is the starting count.

Similar accounts