Not particularly, this is more designed to be a separate chat app than a chat-with-the-webpage extension. Also, parsing webpages for LLM ingest is not the easiest thing in the world in my experience. You could dump the whole html but that's a LOT of tokens to be spending if you're using your own API key (vs using a subscription model like with first party extensions).

Before I started work on it, I looked around at all of the available options, and none of them really fit what I wanted:

- easy to use

- fast

- not a huge desktop app

so I decided to make my own! AirmailAI (if you're not running it locally) is a one-click install from the Chrome Web Store, the TTFT overhead is within 50ms of raw https API requests, and the install size/memory requirements are very reasonable (<2MB on disk, ~60MB RAM while running).

Hmm I see...it's clear now, it would be better if you addedthis moto to the description However great initiative

name some examples. easy to use is opinioned,

Sure. I tried Open WebUI, SillyTavern, AnythingLLM, etc. I wasn't a fan of installing a 500MB desktop app, or having to run a webhost locally, or having to configure a bunch of settings just to chat with the newest LLM.

I agree, but I also think as AI gets better we're going to see Jevons paradox in full swing, which might delay lower costs. We've seen this with Astra according to Tibo: https://x.com/thsottiaux/status/2097559315150426222

Yeah that's when the site lost me too. I feel like people just tell AI "make the thing" and then get mad when it doesn't match up to their vision that they didn't specify at all.

This is a succinct summary of most the the profession of software engineering. Just replace AI with "programmers".

Yeah I'm surprised they posted a chart, you would think they would keep specifics like that hidden until they're closer to launch

The chart is as non-specific as could be. It improved in some very vague metric by some amount at different (increasing) levels of training.

That's fair, but at least the chart has an axis. :) Since openai just released astra, I was more surprised that they would publicly show any gap to their (presumably SOTA) internal model.

The x-axis label of the chart is test-time compute. Doesn't this relate to inference ("thinking level") instead of training?

Isn't the y axis just what portion of the open problems it could solve? The axis is unlabelled though, I'll give you that