Q: Hi Jon, you are definately onto the footsteps of Socrates here :) Really good concept đź‘Ť
Two questions please:
1) Sorry for sounding dumb but even after reading the Q&As here and reading about Deep Dive on your website, I still can't comprehend fully what it actually does. I do get it that it reads documents step by step so no section is missed. For my benefit and any others who didn't quite grasp it, please can you elaborate this feature, especially in terms of quality of output and use cases? Is it good for summarising or simply asking questions? Would DeepDive generate/repurpose better content from the context compared to simple document chat?
2) Once a Deep Dive is done, it stays in Socrates' memory forever? i.e. it has "learned" this knowledge, so we can always come back to it and ask questions?
Thanks
Jay
Jon_Socrates
Oct 2, 2024A: Thanks for the question.
1)
When you have a question about a complex document, there are usually multiple categories of questions. 2 main categories are: 1) specific questions, and 2) broad questions. Normal chats excel at specific questions, like, 'What recipes include bananas?'. Deep Dive chats excel at broad questions, like, 'Summarize this' or 'Look through the entire document to find mentions of bananas.'
For Socrates to perform well with broad questions, it has to repurpose the content into a proprietary format not provided by standard chunking techniques. This is essentially a second 'memory' that the AI can access to answer questions. This repurposing is currently costly for us, which is why there are currently page limits. We will increase the limits once the cost goes down.
Without a Deep Dive, Socrates will utilize the first 'memory' created when creating the chat, which excels at specific questions, and tries its best at broad questions. This has no page limit.
After a chat has Deep Dive enabled, Socrates will have 2 memories and will use the one that will provide the best answer to your question. If you see a "Diving Deep..." when querying, that means it's using the second 'memory'. If you don't, it's using the first 'memory'.
2) Deep Dives are siloed to the chat. Once a Deep Dive is done, the 'memory' stays in that chat until the chat is deleted. New chats cannot access Deep Dive 'memory' of older chats.
JayTheRainmakerPLUS
Verified purchaser
Aha! thanks Jon, finally understood it! Deep Dive is siloed to the chat but can we keep adding more documents to the same chat? So let's say I had a research paper that I did a deep dive in a chat but then found another relevant paper. Can I add to the same chat for deep dive and then ask questions to BOTH papers so that Socrates picks the best answer from both papers?
Verified purchaser
We don't currently support this, but this workflow sounds rather useful, so we are prioritizing this feature on our roadmap!