On Sat, Jul 1, 2023 at 2:56 AM Nils Bruin <nbr...@sfu.ca> wrote: > > On Friday, 30 June 2023 at 20:41:51 UTC+2 William Stein wrote: > > The point is that instead of using GPT's vague memory of what it might > have seen, this instead uses the actual Sage source code, and mainly > uses GPT to make sense of it. > > > Given that only some select code fragments are included in the prompts, > wouldn't you still end up relying on GPT's vague, hallucination-prone general > memory to come up with a broader interpretation of the context provided? It > runs a real risk of just generating harder-to-spot errors. >
This video is a good place to start: https://youtu.be/ZNW1XhT7qC4 -- William (http://wstein.org) -- You received this message because you are subscribed to the Google Groups "sage-devel" group. To unsubscribe from this group and stop receiving emails from it, send an email to sage-devel+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/sage-devel/CACLE5GDMas0pzDO9w%3DwCW3dCptFegB5fcwVJBQkyBFqdFzx19A%40mail.gmail.com.