Personal AI has a surprisingly unglamorous problem:
Who is the user?
What can the agent do?
What does it remember?
Solve those three consistently and suddenly a lot of agent products become easier to build.
That's the Qoni thesis.
The cheap model did the heavy lifting. The big one only got the hard pages
this is the most boring job in any finance team:
-> open the page (scans included)
-> work out what kind of document it is
-> file it in the right place
@NaceAI Document Intelligence read all 145 pages
Drex sorted them into 5 categories and decided 94.5% alone, about 444 ms each
Astra 6 only got the 5.5% Drex was unsure about
Drex alone: 95.9%
with Astra 6 on the unsure pages: 97.9%
Drex cost for all 145 pages: $0.0116
the cheap model decides most of it and the big one only sees what's hard. that's how this runs at scale
(synthetic finance docs)
https://t.co/7nrGMbc843
We are transforming our education infrastructure by introducing terrazzo flooring to ensure durability. Our children and teachers deserve quality facilities that support effective teaching and learning environment.
Multicorner Market π₯ 40+ odds π°
Get more at https://t.co/Q171Mg2PAa
Register to Bet on #HelaBet π°
Reg π https://t.co/X8ZgVlXmou
Tz π https://t.co/aWIFRMp7Fa
Apk π https://t.co/7Ur5YON2Zj
Promo Code π ANTOH
The #HelaBet Code π XN2BD
18+ | Bet Responsibly π
A full day of SEC filings. Read, scored and alerted before your coffee gets cold
this is the most boring job on filing day:
-> read every 8-K and exhibit
-> work out which ones matter
-> write the alert
@NaceAI Document Intelligence read all 334 documents in 116s
Drex scored all 219 filings in 21s. Drex cost: $0.035
Opus 5.5 wrote 18 alerts, and Drex checked every line
what it caught on the day:
-> C.H. Robinson x RXO merger
-> Leslie's Chapter 11
-> ESS Tech NYSE delisting
-> Aterian auditor change
the flagged alert is the one I'd watch. the writer said something the filing didn't, and Drex caught it
CLI + SDK, works with Claude Code, Codex, PI, Opencode, Hermes and Prime Agent
https://t.co/698CeQNDhk
Been exploring Hunyuan Image 3.5 on @OnSoloAI, and the results are honestly impressive ππ₯
The image quality is solid, and generating images for just 1 credit makes testing different ideas much more affordable. Even better, members can enjoy it for free for 2 weeks.
If you love experimenting with AI visuals, give this one a try!