eca

Enjoyed this post! I resonate, and have dreamed of living in a gadget filled workshop too :)

> I wish for the sort of community which could produce its own COVID vaccine in March 2020, and have a 100-person challenge trial done by the end of April.
I was part of the team which designed a shelf-stable omicron vaccine and set a record speed for founding -> first-in-human clinical trial. 

If this is the kind of thing you're talking about, I think you might be underemphasizing IMO the single most important vibe. Magic happens when brilliant people work together. We can get better and more powerful at working together. We can make returns to collaboration... (read more)

Really appreciate the response :)

Totally acknowledge the limitations you outlined.

I was aiming to construct an example which would illustrate how the loss metric would break in a black box setting (where X and Y are too gnarly to vis). In that case you have no clue that your model implements sin(x), and so I dont see how that could be the goal. In the black box setting you do get access to distance between scrubbed y and y_true (loss) and distance between scrubbed_y and original_y (my proposal, lets call it output distance). When you look at loss, it is possible for causal scrubbing to yield an explanation of the model’s performance which,... (read more)

Great stuff! Excited to see this extended and applied. I hope to dive deeper into this series and your followup work.

Came to the appendix for 2.2 on metrics, still feel curious about the metric choice.

I’m trying to figure out why this is wrong: “loss is not a good basis for a primary metric even though its worth looking at and intuitive, because it hides potentially large+important changes to the X-> Y mapping learned by the network that have equivalent loss. Instead, we should just measure how yscrubbed_i has changed from yhat_i (original model) at each xi we care about.” I think I might have heard people call this a “function space” view... (read more)