Bookmarked Project Tailwind by Steven Johnson
Author Steven Johnson has been working with Google and developed a prototype for Tailwind. Tailwind, an ‘AI first notebook’, is intended to bring an LLM to your own source material, and then you can use it to ask questions of the sources you give it. You point it to a set of resources in your Google Drive and what Tailwind generates will be based just on those resources. It shows you the specific source of the things it generates as well. Johnson explicitly places it in the Tools for Thought category. You can join a waiting list if you’re in the USA, and a beta should be available in the summer. Is the USA limit intended to reduce the number of applicants I wonder, or a sign that they’re still figuring things like GDPR for this tool? Tailwind is prototyped on PaLM API though, which is now generally available.
This, from its description, gets to where it becomes much more interesting to use LLM and GPT tools. A localised (not local though, it lives in your Google footprint) tool, where the user defines the corpus of sources used, and traceable results. As the quote below suggests a personal research assistant. Not just for my entire corpus of notes as I describe in that linked blogpost, but also on a subset of notes for a single topic or project. I think there will be more tools like these coming in the next months, some of which likely will be truly local and personal.
On the Tailwind team we’ve been referring to our general approach as source-grounded AI. Tailwind allows you to define a set of documents as trusted sources …, shaping all of the model’s interactions with you. … other types of sources as well, such as your research materials for a book or blog post. The idea here is to craft a role for the LLM that is … something closer to an efficient research assistant, helping you explore the information that matters most to you.
Steven Johnson
@ton Omniscience seems to be doing something similar: https://beta.omnilabs.ai/
Home | Omni
@colin Thank you for that pointer Colin! Looks interesting and I’ll explore, though it’s Chrome-bound and their privacy statement is ‘thin’ to phrase it kindly.
@ton I was a little worried about the privacy issue too. At the moment it hasn’t left my “try this one day” list, though.
@ton using a personalized LLM as a research assistant … when seeing the Google I/O announcement, immediately thought about Dovetail. But, this snippet you share here makes me realize that though didn’t go far enough. Might need to (reluctantly) investigate this some more write ✍ ️
@Avancee I’d be very interested in having a way to feed my 25+ yrs of notes and writings in a localised LLM assistant. If only I could keep my data out of the hands of tech companies and their clouds and models.
@ton I think there’s a path for figuring that out with many of the LLM models/remixes out here now. Wrapping that into something which could stand the test of (software and hardware) time will be a thing to figure out. But, a personal repo, with a data model/transformer that only works on that local data store… yea that would be aces
Stephen Downes mentioned this post.