(2023-01-04) Hon S14e03 Success Criteria Chat

Dan Hon: s14e03: Success Criteria; Chat. 1.1 Another thing that stuck in my head from Tim Bray’s essay about search on Mastodon was his section on success criteria. Here’s the first para, but I encourage you to read the rest.....

1.2 Chat: I went along to the Near Future Laboratory’s General Seminar 26 on ChatGPT futures last week and it was… interesting?

It’s somewhat astonishing to me that nobody has yet hacked up a Young Lady’s Shitty Illustrated Primer (Young Lady's Illustrated Primer). Given infinite AI arrays appeared this week, it doesn’t feel like it would be too far off.
Ask it to write some problems in the form of a children’s book.
Use all the above as static text.
Bound figuring out the problems in a ChatGPT REPL, i.e. as a text adventure.

The one thing that I’m not sure has stuck around here has been continuous training. ChatGPT is good (I think?) at preserving state through each session (e.g. you can tell it to “do that again, but x” and it’ll mostly work), but in terms of learning preferences and updating a model continuously, I don’t think I’ve seen that.