Now that we have discussed the basis of RL, Synthetic Data, Chain-of-Thought, Inference Time Compute and other concepts, let us go through what OpenAI has done with o1 and o1 Pro both during training and during inference. The construction of o1 is unique and doesn’t mirror the papers above. We will also discuss the tokenomics of inference time compute including cost, KV Cache scaling, batching, and more. Lastly, we will explain what OpenAI is doing next with Orion and why the narrative around it being a failure isn’t accurate.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !piracy@lemmy.dbzer0.com
⚓ Dedicated to the discussion of digital piracy, including ethical problems and legal advancements.
The the Firefox reader view was all it took for me. Your browser probably has similar.
https://semianalysis.com/2024/12/11/scaling-laws-o1-pro-architecture-reasoning-training-infrastructure-orion-and-claude-3-5-opus-failures/
Is that the last graph you can see?
Now that we have discussed the basis of RL, Synthetic Data, Chain-of-Thought, Inference Time Compute and other concepts, let us go through what OpenAI has done with o1 and o1 Pro both during training and during inference. The construction of o1 is unique and doesn’t mirror the papers above. We will also discuss the tokenomics of inference time compute including cost, KV Cache scaling, batching, and more. Lastly, we will explain what OpenAI is doing next with Orion and why the narrative around it being a failure isn’t accurate.