Oh awesome. Random next Q: should this be built with redundancy and no reliance on a single corporate entity? Maybe a working group makes sense.
@yoheinakajima
-
Public Data Embedding Efficiency and Database Solutions
By
–
Hm good point to consider. I’ve seen at least 5 @paulg bots where they embedded his essays, and @gpt_index will chunk up and embed websites on the fly. I don’t have a clear answer, but this seems inefficient, at least for publicly available data – I’d love a public database of
-
Automatic multi-layer clustering with continuous user feedback optimization
By
–
Hm good point. How about automatic clusters embedded regularly, multi-layer as clusters grow, with constant testing and iteration through user feedback and observed speed.
-
Public Embedding Database with Monetization Model
By
–
A lot of people are embedding the same publicly available content. Would be fascinating to have a public database where you could contribute your embeddings that anyone could query. Include source URL and text as standard metadata. Maybe it’s one cent per 1000 calls to this
-
Including Documentation and Error Codes in AI Code Debugging
By
–
Amazing. I have been doing this (include docs, error code, my code) and ask for fixed code. Though the increased context length should help here a lot as I usually had to trim stuff.
-
AI Newsletter Aggregator: Automated Master Newsletter Solution
By
–
I joke, but both of these are actually helpful We just need someone to subscribe to every AI newsletter – then combine them into one master newsletter. Of course with AI.
-
Exponential AI Growth Since 2023 Breaking Systems
By
–
Somebody turned 2x mode on 2023 and it's breaking everything
-
Dealflow Digest Connects 159 Investors with Startups
By
–
Updates from Dealflow Digest: 159 investors/ 159 startups
156 intro requests by investor/ 134 intros made
One recent B2B SaaS founder received 10 intros!
Marc Villafuerte is #1 scout w 4 referrals. Open to all investors, founders, and scouts: https://
dealflowdigest.com (100% FREE) -
Virtual Try-On Technology Approaching Retail-Ready Status
By
–
I've also seen many many iterations of this tech that hasn't been good enough for retailers to use. Seems we're close. Side note: I had assumed it'd be some 3d modeling, plus fabric physics, etc. but this approach feels strong. Especially if you could upload few pics of people
-
AI Technology for Apparel Retail Applications Gains Interest
By
–
Umm… assuming you can do this for non-synthetic models, I think I know some apparel retailers who'd like this tech.