WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,925 posts

Back to No.006 Jev in Practice: Browser Use and Agent WorkflowsUpdated 11 hours ago
jevIMAGE

Jev replaces Gemini 2.5 Flash Lite in a classifier eval

The author ran Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite, and it won on both quality (saturating the eval) and speed (6x).

Malte Ubl
@cramforceArchived 2026.09.18Originally posted 2026.09.17
Jev replaces Gemini 2.5 Flash Lite in a classifier eval
Malte Ubl @cramforceOriginally posted 2026.09.17
Open original on X

Ran @typesafeai's Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite. It won both on quality (saturated the eval) and speed (6x)

x.com/cramforce/status/2100269198727602468Archived 2026.09.18 00:43
Open original on X