Andrew Fairless – Page 20 – Andrew Fairless, Ph.D.

What I Read: evaluating AI systems

By Andrew Fairless on December 5, 2023October 12, 2023

https://www.anthropic.com/index/evaluating-ai-systems Challenges in evaluating AI systemsOct 4, 2023 “…what many people working inside and outside of AI don’t fully appreciate is how difficult it is to build robust and reliableContinue readingWhat I Read: evaluating AI systems

What I Read: Problems of AI Consciousness

By Andrew Fairless on December 4, 2023October 5, 2023

https://thegradient.pub/an-introduction-to-the-problems-of-ai-consciousness/ An Introduction to the Problems of AI ConsciousnessNick Alonso9/30/23 “This brief introduction is aimed at those working within the AI community who are interested in AI consciousness, but mayContinue readingWhat I Read: Problems of AI Consciousness

What I Read: Visualizing Matrix Multiplication

By Andrew Fairless on November 30, 2023October 5, 2023

https://pytorch.org/blog/inside-the-matrix/ Inside the Matrix: Visualizing Matrix Multiplication, Attention and Beyondby Team PyTorchSeptember 25, 2023 “Matrix multiplications (matmuls) are the building blocks of today’s ML models. This note presents mm, aContinue readingWhat I Read: Visualizing Matrix Multiplication

What I Read: Data, The Land DevOps Forgot

By Andrew Fairless on November 28, 2023October 5, 2023

Data – The Land DevOps Forgot • Michael Nygard • YOW! 2023GOTO ConferencesSep 30, 2023Michael Nygard – General Manager of Data at Nubank & Author of “Release It!” “We willContinue readingWhat I Read: Data, The Land DevOps Forgot

What I Read: Privacy side channels in ML

By Andrew Fairless on November 27, 2023October 5, 2023

https://spylab.ai/blog/side-channels-machine-learning/ Privacy side channels in machine learning systemsEdoardo Debenedetti, Florian TramèrSep 12, 2023 “An additional application of our membership inference attack is to test whether specific data sources were partContinue readingWhat I Read: Privacy side channels in ML

What I Read: Estimate Token Importance in LLM Prompts

By Andrew Fairless on November 16, 2023October 5, 2023

https://www.watchful.io/blog/a-surprisingly-effective-way-to-estimate-token-importance-in-llm-prompts A Surprisingly Effective Way to Estimate Token Importance in LLM PromptsShayan Mohanty “Prompting is our primary means of instructing these AIs, yet the process of crafting effective prompts hasContinue readingWhat I Read: Estimate Token Importance in LLM Prompts

What I Read: Auditing AI, How Much Access

By Andrew Fairless on November 14, 2023October 5, 2023

https://aipolicy.substack.com/p/ai-accountability-transparency-2 Auditing AI: How Much Access Is Needed to Audit an AI System?Chapter 2 in our AI Accountability & Transparency series(By Sarah H. Cen, Cosimo L. Fabrizio, James Siderius, AleksanderContinue readingWhat I Read: Auditing AI, How Much Access

What I Read: Overton Paradox

By Andrew Fairless on November 9, 2023October 5, 2023

https://brilliant.org/lesson/the-overton-paradox/ The Overton Paradox “This apparent contradiction is what we’re calling the Overton Paradox: People become more liberal as they get older, but they are more likely to say theyContinue readingWhat I Read: Overton Paradox

Author: Andrew Fairless