Research Training And DistillationResearch Item

OpenAI next model Spud as new pretrained base and architecture step change

April 4, 2026Bindu Reddy, Haider., Rohan Paul

Haider and Rohan Paul relay Greg Brockman comments that Spud reflects two years of research and may be a new pretrained base trained from scratch with a meaningfully different architecture and native omnimodal capability.

SPUD is coming
it's a new pre-trained base model, built on roughly two years of research
Better reasoning, true context understanding, agentic capabilities that work.
openai next model being a "new pre-trained base" is the big thing
if spud is trained from scratch on 2 years of new data and has a meaningfully different architecture, that would be a real step change.
the native omnimodal part matters too.
Greg Brockman on their upcoming model called ‘Spud’.
"Two years worth of research that is coming to fruition in this model."
Bindu Reddy
Haider.
Rohan Paul
model roadmaptrainingopenaillmgptagi

See what authorities are saying right now

This finding is one of many signals tracked across Artificial Intelligence. The live feed updates every few hours with new authority voices, debates, and emerging ideas.

← Back to Artificial Intelligence