Looks similar to the divergent behavior elicited in the “repeat poem forever” paper:
MACHINE LEARNING
-
Brain Vision Processing Gap in Modern LLMs Architecture
By
–
the human brain reserves 40% of its processing exclusively for vision. modern LLMs somehow evolved without this entirely
-
18 Powerful Applications Of AI Agents In Marketing
By
–
18 Powerful Applications Of AI Agents In Marketing
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @demishassabis @Ronald_vanLoon @TamaraMcCleary @geoffreyhinton @goodfellow_ian @jeffdean @erikbryn http://
ow.ly/bhcc30sOj5V -
Turing Award 2025 honors attention and transformer inventors
By
–
The 2025 Turing Award will go to Dima Bahdanau and Noam Shazeer for inventing attention and transformers.
-
AAAI Bridge Program on Continual Causality Proceedings Published
By
–
Volume 268 https://
proceedings.mlr.press/v268/ Proceedings of the AAAI Bridge Program on Continual Causality Is now available on PMLR. -
MMBench-GUI: Multi-Platform Evaluation Framework for GUI Agents
By
–
MMBench-GUI Hierarchical Multi-Platform Evaluation Framework for GUI Agents
-
VLMs Outperform with Visual Data Alone Over Numerical
By
–
Interestingly, VLMs perform better with plot alone compared to plot + data! This paper shows that GPT‑4.1 and Claude 3.5 excels at scatterplot analysis, and could often perform better only by looking at the plot, without reading the actual numerical data.
-
Training Environments for Small ML Models: Notebooks vs Scripts
By
–
For folks training/fine-tuning small-ish models, what’s your environment of choice? Do you use notebooks or scripts?
-
SJTU’s Neural Architecture Search Claims Superintelligence Amid Criticism
By
–
SJTU's latest paper claims artificial superintelligence for neural architecture search. But critics on alphaXiv call it inconsistent and "buzzword maxxing"
– Seemingly AI generated sections of the paper
– Relies on objective benchmarks and metrics it critiques -
Why Is Chess Engine App Size So Large Neural Networks
By
–
How could chess engine be that giant? Very large local neural nets? Electron shennanigans? Too highres assets? What do you think @chesscom ? :p. Fwiw I couldn’t find other chess apps that were dramatically smaller so I ended up playing a bit just on the website.