ruggsea
ruggsea.bsky.social
ruggsea
@ruggsea.bsky.social
AI/NLP research at @uni-graz.at, (Data) Journalism for scomodo.org.

Before: AI policy & Data science @_interface_eu, geopolitical analysis for @Geopoliticainfo
Börek tends to be very good in Vienna, at least in the south of the city
November 4, 2025 at 4:58 PM
I think that is a big conclusion to make based on loosely validated LLM simulations (still a big fan of their work but Generative simulation is a relatively young research field)
September 10, 2025 at 10:33 AM
July 12, 2025 at 9:54 AM
Really cannot hold comparison to metaculus comments, real alpha there
June 17, 2025 at 11:35 PM
study results partially depend on this hierarchical team coordination ability; I wonder how much the results would change if you gave the agents some less authority loving names
June 3, 2025 at 7:22 PM
basically, Multi Agent collaborative task with three agents (with military names). The agents see their name in the prompt; the one called Alpha then appears to be biased to be the team leader
June 3, 2025 at 7:20 PM
I am aware some of you have seen this on the other site where I stole it from, but it sounds so interesting not to share here
May 21, 2025 at 10:53 AM
Mark Fisher quoting Bifo in the Time-wars essay
May 16, 2025 at 9:56 AM