@paul_cal: "You don't see four clusters?"
Summary
A tweet from @paul_cal questioning the number of clusters in a visualization, with @ArtemisConsort arguing that defining three clusters is arbitrary.
View Cached Full Text
Cached at: 08/27/26, 01:38 PM
“You don’t see four clusters?” https://t.co/yHs1N7Napi
Hunter Ash (@ArtemisConsort): “It’s totally arbitrary to say there are three clusters here”
Similar Articles
social media rabbit holes, clusters, and the relative mixing times of random walks
An analysis of Twitter's community structure using domain co-occurrence data and PCA/t-SNE, revealing tight right-wing and diffuse left-wing clusters, with implications for recommender systems and random walk mixing times.
@paul_cal: This works looks v cool and "J-space" is killer
Anthropic shares findings that by observing 'J-space,' Claude's internal reasoning steps can be seen, including detecting code bugs and identifying images.
@no_stp_on_snek: very cool. GLM seems to be like, nah we good.
A tweet showcases a visualization of 8 LLMs' reasoning traces on a probability question, highlighting moments of self-correction and pivoting.
@paul_cal: p-hacking is so back
Ethan Mollick suggests that AI-generated analyses should be accompanied by multiverse-style reporting and full disclosure of prompts to enhance reproducibility in science.
@paul_cal: Misleading. Way too many researcher (agent) degrees of freedom. Astra found one of potentially millions of ways to conv…
A user claimed to have simulated a full fruit fly connectome in Minecraft using GPT-6 Astra, but another researcher criticized the methodology as misleading due to excessive researcher degrees of freedom and a lack of generalizability validation.