None of the queries I asked worked:

- "more light"

- "less light"

- "both doors should be locked"

- "if blinds are open, open back door"

thanks for this actually, so the demo is a preset, you can edit tools descriptions and add available tools the way you want, else Needle heavily guards against false negatives, users asked for this. For this, we will update presets on our end.

presets updated for you now :)

I expected slop, but this is really good! (both demo and write-up)

what was the latest model you tried?

This, but also:

First define "knowing" and "AGI" in a way that excludes machines, doesn't exclude many humans, and isn't just tautologically restating the prior belief that "only humans think" with different phrasing.

None of the critics ever can. Worse, most attempts exclude entire classes of human being when they try.

Has anyone tried running this on Mac device? (e.g. Mac Studio Ultra)

Failed with a software error for me

30% on ARC-AGI-3

Didn’t verify but wow. It was just a few months back when the models barely crossed 1%. Imagine how good fable must be?

Working on Window Hints - keyboard-first window switching (macOS for now)

https://windowhints.com/

Does it detects multiple same app windows as different ? like if you have 2 chrome windows

Yes, if you have 3 Chrome windows, it will show you visual hints for all of them separately