Remove Alternative Remove Learning Theory Remove Strategy
article thumbnail

Six Tips for Evaluating Your Nonprofit Training Session

Beth's Blog: How Nonprofits Can Use Social Media

Alternately, you may feel so good about it and say my job is done. Use Learning Theory. To guide evaluation, there are several learning theories, including The Four Levels of Evaluation, also referred to as the Kirkpatrick Evaluation Model , was created by Donald Kirkpatrick, Ph.D. Documentation.

article thumbnail

How To Think Like An Instructional Designer for Your Nonprofit Trainings

Beth's Blog: How Nonprofits Can Use Social Media

All of my work these days is focused on designing and delivering effective training for nonprofits -primarily on the topics of social media, strategy, networks, and measurement. As someone who has been designing and delivering training for nonprofits over the past twenty years, the most exciting part is apply theory to your practice.

professionals

Sign Up for our Newsletter

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

article thumbnail

The Theoretical Reward Learning Research Agenda: Introduction and Motivation

The AI Alignment Forum

Progress on this research agenda therefore seems likely to be useful in a fairly broad range of scenarios, and applicable to a fairly broad range of AI systems (in contrast to research that is closely tied to specific alignment strategies, specific types of AI systems, or very specific assumptions).

article thumbnail

Research directions Open Phil wants to fund in technical AI safety

The AI Alignment Forum

Alternatives to adversarial training : Adversarial training (and the rest of todays best alignment techniques) have failed to create LLM agents that reliably avoid misaligned goals. Were interested in evaluations that can test whether an AI has the capability to execute these strategies (regardless of whether it actually does so).

article thumbnail

AXRP Episode 40 - Jason Gross on Compact Proofs and Interpretability

The AI Alignment Forum

And a technical note: it needs to be in some first-order system or alternatively, you need to measure proof checking time as opposed to proof length. So zooming out, youre telling me about the proof strategy for crosscoders. And then you prove this, and the measure of compression is how long your proof is. Is that roughly fair?

Model 52