dipankarmazumdar commented on issue #13934: URL: https://github.com/apache/iceberg/issues/13934#issuecomment-3229946893
Thanks @RussellSpitzer for sharing your pov. I agree that 'generic' LLMs usually provide very confusing information. But I guess with Kapa, since they train their models on 'specific' things (say Iceberg codebase, Docs) it actually might be reliable & we can bound that training to only the source of truth (which is the code + docs; not external blogs/papers). If the community is open, we can get us a test environment widget (not public) and try with some of the questions. If we feel it works, then great. If not, we do not deploy it publicly. Ps: I do not have any affiliation with Kapa. I have used it with other Apache projects in test settings & benefitted personally. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
