Reassessing directives
Considering alternatives
Exploring secondary and tertiary aspects
Revising initial thoughts
Confirming factual assertions
Performing math
Wasting electricity
... and other useless (and generally meaningless) placeholder updates. Nothing like what the <think> output from DeepSeek's model demonstrates.
As Karpathy (among others) has noted, the <think> output shows signs of genuine emergent behavior. Presumably the same thing is going on behind the scenes in the OpenAI omni reasoning models, but we have no way of knowing, because they consider revealing the CoT output to be "unsafe."
As Karpathy (among others) has noted, the <think> output shows signs of genuine emergent behavior. Presumably the same thing is going on behind the scenes in the OpenAI omni reasoning models, but we have no way of knowing, because they consider revealing the CoT output to be "unsafe."