Reasoning models (trained via reinforcement learning on specific domains with formal correctness criteria) represent an innovation as significant as language models, but require domain-specific training datasets and model architectures for each domain before achieving broad capabilities like those predicted for GPT-5.

factualpending

Speaker

Anish Acharia

Evidence Quote

“we've seen a new model architecture with the reasoning models. So, you know, I feel like we're seeing all the steps that point in the direction of GPT5... the reasoning models, which actually are just as important of an innovation as the language models, you know, they are these models that are trained through reinforcement learning on specific domains, which is why they work so well for coding. But we still need to go collect the data sets and and build the models for all of the domains that have a formal concept of correctness.”

Source

The AI Reset Is Here: Search, Jobs, and Everything Else w/ Anish Acharya, Dave Blundin, Salim Ismail— Peter H. Diamandis
Created: 8/11/2026, 4:57:09 AM

Your notes

Loading notes...