[exo-cortex]

I remain sceptical about the "Planet Tracker"-task. The task was to debunk claims about historical positions of Jupiter and Saturn. If the task was to find those planets were NOT in a certain (claimed) position an erroneous program would still appear to "debunk" the claims. Did they check if Devin's code's calculated positions were actually correct? Did they check in some NASA-database? If Devin gave arbitrary positions for the planets it's much more likely that they're different than any claim and appear to debunk it.

[Yenrabbit]

I was able to read the code it wrote, and check that (as hoped) it was using a good existing library to do the heavy lifting. And I had it make plots that I could visually use to check that the values were 'reasonable'. The value in that case was simply that I didn't have to leave the couch and write the code myself (although if the result was actually needed for anything more important than a smug 'i thought so' confirmation I would still have taken over and validated it kore carefully).