No single company should own and control our AI.
@hardmaru
-
NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning
By
–
NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications Excellent work from Google Japan presents many empirical insights about evolution methods at scale. If you’re using evolution and deep learning, this is the paper to read! https://
sites.google.com/view/neuroevob
ench
… -
Fooling AI Detection Algorithms Becomes Essential Survival Skill
By
–
Being able to fool AI detection algorithms IRL will be an important survival skill in the 21st century 👻 https://t.co/5Tyru7H2cT
— hardmaru (@hardmaru) 3 décembre 2023Being able to fool AI detection algorithms IRL will be an important survival skill in the 21st century
-
Universal Adversarial Attacks on Aligned Language Models Study
By
–
Universal and Transferable Adversarial Attacks on Aligned Language Models by @andyzou_jiaming et al. is wild. “Adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs.” https://
arxiv.org/abs/2307.15043 https://
github.com/llm-attacks/ll
m-attacks
… -
Favorite Discussion on LLM Jailbreaks and Adversarial Attacks
By
–
My favorite part is the discussion about jailbreaks and adversarial attacks on LLMs near the end!
-
Most cited neural networks research overview
By
–
The image from https://
people.idsia.ch/~juergen/most-
cited-neural-nets.html
… -
Open Research as Essential Path to AI Progress
By
–
This is why open research is the real path to any meaningful progress in AI. Ideas and breakthroughs don’t happen in a vacuum.
