Patel states OpenAI's o1 reasoning model increases average sequence length because it reasons before outputting.
“This is really important because with reasoning models like OpenAI's o one, the average sequence length grows a lot.”
Patel reveals o1's reasoning process sometimes switches between Chinese and English during hidden thinking phase.
“It generates tons of things. It's like it it sometimes switches between Chinese and English. Right? Like, whatever it is. It's thinking. Right?”
Patel describes o1's reasoning process as generating extensive internal thought including language switching before outputting.
“It generates tons of things. It's like it it sometimes switches between Chinese and English. Right? Like, whatever it is. It's thinking. Right? It's churning.”
Patel explains GPT-5 will combine massive pre-training and post-training scale for the first time.
“Along the way, another team at OpenAI made the big breakthrough of reasoning. Right? Strawberry training. And they released o one, and then they released o three.”
Patel illustrates that language models historically failed at basic math comparisons without reasoning capabilities.
“And it would say, yes. It's bigger. Even though, like, everyone knows that nine dot one one is is way smaller than nine dot nine.”
Patel predicts reasoning chains will close as AI response times extend from immediate to hours or days.
“And then as the horizon of AI models gets longer, right, rather than a question answer immediately, the question answer becomes ten minutes, hours, days, the value of all the reasoning is gone.”
Patel explains OpenAI hides reasoning chains while Anthropic shows them, creating distillation advantage for closed models.
“You go look at like codex or clawed code, you give it a question, it thinks for a while, and then it gives the answer.”