Theoretically a good fuzzer could discover this value by itself, but I don’t believe anything like that exists that could run JS code and explore VM-level branches, at least not for JS code that’s even this complex. Otherwise, yes, PBT is less trivial than it seems, though I’m guessing a simple `strings jsc` coupled with general knowledge of special values of other types[1,2] could get you quite far.
Good question. Currently the value here is cost vs api usage compared to something like cal.com. Similar usage there would be significantly higher. That said, they also have some additional features that we don't have yet. We are actively working towards new features to close the gap! Thanks for checking it out.
I used the new system tonight and it felt like a definite downgrade. Generated a few non-working basic apps, couldn’t handle CSS in a NextJS environment. Terminal context didn’t work. And it went back to not reasoning through the problem until resolution. And kept slowing down.
I’m assuming major release vs stable, but this is pretty lackluster so far. Switched back to Sonnet reasoning. Here’s to improving!