Introducing Toast 1
mixedbread.comWhen I, a human, need an answer to anything moderately complex, it's unlikely that I get it on the first (pre-AI) round of google searching. Simple stuff, sure, but more likely I'll need to go 2-5 rounds. Maybe click a few links. Double-check my assumptions.
An LLM that can do that quickly seems like a slam dunk. I wonder what other problems benefit from that 10x-100x increase in context + 2-5 rounds with the LLM.
At least validation seems faster than without, but you get what you pay for when it comes to llm intelligence
For example, a couple of days ago I described a problem with my refrigerator's water dispenser to Google Gemini, and it told me exactly how to fix it. I then went looking for a video and fixed the thing in under 15 minutes. The only way that Gemini could have been better is if it linked to a video itself.
Do you mean search into less-well-known topics? Or something else?
I think in a lot of ways Google peaked and is now on the decline into a profitable but much less relevant services company.
Maybe the web is really that much worse, and the SEO tactics so hostile to genuine content.
But, honestly...just bring back the old google, where I have all kinds of search modifiers to perform exactly the search I want, that just returns all the matching results that have been indexed. Let me sort out the rest. How do you remove the ability to do "exact text search"? It's the most basic of search functions. Remember having "|" modifiers? AND modifiers?
If google launched that again, even as a separate engine, I think they'd have a good product again. Maybe being good doesn't pay the bills for google, though.
I know that those emails have both the words “iPhone” and “receipt” but I feel like The Search Engine Company That Also Does Email should have a smarter search engine in their email.
I’m pleasantly surprised that I can ask Gemini for help with it if I specify “look through my Gmail for this information”, but it takes it a minute or two to find it.
[1]: https://www.mixedbread.com/blog/multimodal-late-interaction-... [2]: https://www.mixedbread.com/blog/wholembed-v3
Ooh. I've probably misunderstood, but are you saying you have your own web index? Are you offering that as a paid API? I'm not so interested in AI output summaries, but API access to a solid index and intelligent attempts at ranking is very interesting for metasearch purposes.
the thing is most agents waste most of their tokens looking up information which can cause context rot. most small models are not as good as looking up information. this model helps to lookup information for your main agent, which helps you to save tokens and still maintain quality.
Anyway, back to this - it seems to be more like the AI equivalent of algolia than google
Bread-first search, is it?
It sounds like this is a new layer on top of your existing storage layer? So to use this, would I need to give you all of my data first? Or is there a version that can be run on prem?
Sadly its another software company.
Seems to me if it doesn't also apply uniform melted butter it would be a hard sell.
butter application is still unsolved AFAIK, though I'm sure there's a robotics company out there hard at work on it.