Skip to content
View original post on X: Allie K. Miller
Published
23/100

Allie K. Miller says Fable 5.2 handles complex tasks better than other models

AIAllie K. Miller says she tested Fable 5.2 on five complex tasks, including a 3,100-city US water safety map built from FEMA, NOAA and USGS data. She says she trusted it more than any model she has tested, though it made obvious errors in colors, units and slide text that secondary agents missed.
Allie K. MillerVerified on X
@alliekmiller
View on X

I was an early tester of Fable 5.2, and I had it:

  1. build an entire water safety map of 3100 cities in the US based on FEMA, NOAA, USGS data with two demo videos
  2. build a new identity and create/run an entire ADHD-themed YouTube channel that can make money for me
  3. build psychological profiles of my stalkers to determine if any of them were the same person (this was actually insane and unfortunately for privacy reasons, I cannot share the output)
  4. build a hilarious 3D hot dog kiosk game as a command center to manage my to-do list
  5. fill out 31 different personality tests on my behalf and provide an analysis over time

I trusted it more than any other model I've tested. Unbelievable at handling complexity. Made some weirdly obvious errors (like colors and units on the water map or overlapping text on a slide) that secondary agents also didn't catch. Importantly: there is no such thing as a needle in a haystack anymore with this model.

And I still feel like I could be more ambitious.

Source details

Allie K. Miller · x.comPublished · added here

Original title: I was an early tester of Fable 5.2, and I had it:

Topics

AI agentsExpert opinion