Launch HN: Grapevine (YC S19) – A company GPT that actually works

Re:Launch HN: Grapevine (YC S19) – A company GPT that actual... by ebiester on Monday October 06, 2025 @12:04PM (#45492833)

I've seen Gleam and Onyx, and I think the real problem is that there is a lot of garbage coming in. If you want to solve the problem, you need to find a way to clean the information coming in. And if you've cleaned the information coming in, you have a lower need to have an LLM answer the question.

[ Parent | on HN ]

Re:Launch HN: Grapevine (YC S19) – A company GPT that actual... by eambutu on Monday October 06, 2025 @12:50PM (#45493339)

Our experience, especially with the most recent reasoning models, is that the LLM's are a lot better now at sifting through the garbage. So if you last gave these products a try more than a month ago, I would try them again.

(Additionally, there are a lot of details that do make a big difference in data processing / search algo too, which have taken our own internal accuracy on hard questions from 30% => 80%+)

[ Parent | on HN ]

[dead]

Re:Launch HN: Grapevine (YC S19) – A company GPT that actual... by paool on Monday October 06, 2025 @02:14PM (#45494363)

It's BM to plug your own stuff in someone's launch thread.

[ Parent | on HN ]

Re:Launch HN: Grapevine (YC S19) – A company GPT that actual... by smt88 on Monday October 06, 2025 @07:37PM (#45497547)

As a consumer of HN, I don't agree. Relevant comments are helpful to me regardless of context, and this doesn't even seem like a competitor.

[ Parent | on HN ]