News for hackers. Stuff that matters.
Re:Emerging Architectures for LLM Applications by applgo443 on Tuesday June 20, 2023 @04:45PM (#36410242)
They mention the contextual stack is is relatively underdeveloped. Any idea on what can be improved there?
Re:Emerging Architectures for LLM Applications by jgraettinger1 on Tuesday June 20, 2023 @06:53PM (#36411857)
Building contexts for structured data used in AI / GPT tasks is something I've seen little written about, but is obviously quite important.

Confluent calls it a "customer 360" problem [1] and I don't disagree.

We (Estuary) also wrote up a post showing an approach for Slack => ChatGPT => Google Sheets [2], and have more content coming for Salesforce, HubSpot, and some others.

[1] https://www.confluent.io/blog/chatgpt-and-streaming-data-for...

[2] https://estuary.dev/gpt-real-time-pipeline/