Sorry that you were unable to attend. I got a chance to talk to Karthik and hear about your work. It seems like a really promising method for secure NNs. Hope our paths cross in the future.
RESEARCH
-
Differential Privacy Tutorial at SATML Conference
By
–
Thanks Nicolas for the invitation! @satml_conf is a fantastic new initiative. This tutorial was a lot of fun to give. The video will be online soon. I may also record and release my own version, so that I don't have to leave out my favorite algorithm in differential privacy. https://
x.com/NicolasPaperno
/NicolasPapernot/status/1624048613318971392
… -
Data Oriented Architectures arXiv Paper Feedback Request
By
–
We would love input and feedback on this arXiv paper on Data Oriented Architectures from the AutoAI team here in Cambridge. https://
arxiv.org/abs/2302.04810 -
Machine Learning Algorithms Models Defined AI Glossary Series
By
–
In this @Cognilytica #AIToday #podcast AI Glossary Series episode, 'Machine Learning, Algorithm, Model' hosts @rschmelzer & @kath0134 define these terms, explain how they relate to #AI and why it’s important to know about them. Full episode: https://
aidatatoday.com/ai-today-podca
st-ai-glossary-machine-learning-approaches-supervised-learning-unsupervised-learning-reinforcement-learning/?utm_source=dlvr.it&utm_medium=twitter
…
#tech #data… -
AI and Computers Driving Environmental Sustainability Solutions
By
–
Explore the potential of AI and computers to tackle environmental sustainability. Stay ahead of the curve and discover new insights and solutions to protect our planet. Read more at: https://
bit.ly/3HHWoh2 @OUPELTGlobal @jeevprabnivash @_DigitalIndia @GoI_MeitY @NeGD_GoI -
Language Models Using Tools: Extended Mind and Practical Applications
By
–
Language models (LMs) using tools is one of the most exciting research & engineering directions in AI. Philosophically, it’s the extended mind hypothesis (
https://
en.wikipedia.org/wiki/Extended_
mind_thesis
…). Practically, it is likely to lead to LMs that are more accurate and factual, an to many cool apps. -
Which Company Today Resembles Xerox PARC of the 1970s
By
–
Which company today reminds you of Xerox PARC of the 1970s?
-
Bing Search correctly explains SolidGoldMagikarp GPT glitch
By
–
This one is impressive on a few levels — Bing Search gives a mostly correct answer explaining the "SolidGoldMagikarp" glitch, a recently discovered issue in which prior GPT models (incl. ChatGPT) cannot repeat back certain short strings:
-
Small Daily Improvements Drive Significant Technological Change
By
–
Small daily improvements can result in big change! #inspiration
-
Testing repetition of anomalous tokens in LLMs
By
–
How does it do with repetition of other anomalous tokens?