Beth's Blog: How Nonprofits Can Use Social Media

FEBRUARY 18, 2014

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. The four levels are: Reaction.

Evaluation 131

Evaluation Train Training Tips 131

Beth's Blog: How Nonprofits Can Use Social Media

JANUARY 27, 2014

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.

Instructional Design 113

Instructional Design Instruction Instructional Train 113

The AI Alignment Forum

FEBRUARY 28, 2025

A nave answer might be to measure their L 2 -distance. For example, a complete answer to question (2) would be a set of necessary and sufficient conditions on two reward functions R 1 , R 2 which characterise when it would be acceptable (as measured by R 1 ) to maximise R 2 instead of R 1.

Research 40

Research Learning Method Policy 40

Google Research AI blog

APRIL 30, 2023

If you’re registered for ICLR 2023, we hope you’ll visit the Google booth to learn more about the exciting work we’re doing across topics spanning representation and reinforcement learning, theory and optimization, social impact, safety and privacy, and applications from generative AI to speech and robotics.

Google 105

Google Language Model Jing 105

The AI Alignment Forum

FEBRUARY 28, 2025

We also managed to leverage these results to produce a new method for conservative optimisation, that tells you how much (and in what way) you can optimise a proxy reward, based on the quality of that proxy (as measured by a STARC metric ), in order to be guaranteed that the true reward doesnt decrease (and thereby prevent the Goodhart drop).

Learning 40

Learning Discussion Classes Policy 40

The AI Alignment Forum

FEBRUARY 7, 2025

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. Alternative approaches to mitigating AI risks These research areas lie outside the scope of the clusters above. McAleese et al. Arnesen et al. Khan et al.

Research 52

Research Fund Open Technique 52

The AI Alignment Forum

MARCH 28, 2025

And the takeaway from this paper is that you can use proofs to measure how much compression you get. And then you prove this, and the measure of compression is how long your proof is. 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.

Model 52

Model Network Training Train 52