4 Comments
User's avatar
glou's avatar

This is the way.

Compare/contrast the tools.

Only then can you determine which and how to use them (and for the appropriate task).

Jamie Freestone's avatar

Great idea! Even if not focused on governance, the basic project of building an eval is the best example I’ve seen yet of an AI literacy task that has relevance & longevity.

Andy Hall's avatar

Yeah absolutely! It can be extremely broad

Sriram MK's avatar

The student eval idea is great, but the vision for AI accountability needs an institutional layer to actually work. Like how investigative journalism needs a publication to make its work known. Do you think the next step would be something like GitHub for public evals where anyone can build their own and run them with the results accumulating publicly over time?