Remove Comparison Remove Difference Remove Learning Theory
article thumbnail

Why Movement Is the Killer Learning App for Nonprofits

Beth's Blog: How Nonprofits Can Use Social Media

As a trainer and facilitator who works with nonprofit organizations and staffers, you have to be obsessed with learning theory to design and deliver effective instruction, have productive meetings, or embark on your own self-directed learning path.

Learning 139
article thumbnail

Moving from Red AI to Green AI, Part 1: How to Save the Environment and Reduce Your Hardware Costs

DataRobot

In the graph below, borrowed from the same article, you can see how some of the most cutting-edge algorithms in deep learning have increased in terms of model size over time. To illustrate the energy needed in deep learning, let’s make a comparison.

Green 145
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Research directions Open Phil wants to fund in technical AI safety

The AI Alignment Forum

We link to hundreds of papers and blog posts and offer approximately a hundred different example projects. Motivation: Two lines of recent work have looked for undesirable behaviors in LLMs, approaching the problem from two different angles: Andriushchenko et al. Kumar et al. , Another way could simply be to use low perplexity.

article thumbnail

AXRP Episode 40 - Jason Gross on Compact Proofs and Interpretability

The AI Alignment Forum

So when youre doing mechanistic interpretability, you have some claim about how the model behaves, and how the model actually behaves might be a bit different than this, but if your understanding is any good, itll be pretty close. Can you tell us: in this case of max of n, roughly, what are you doing to get different kinds of proofs?

Model 52