OpenAI says frontier models' computation depth stays near GPT-4's level
Original titleI want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present front...
AISummary
OpenAI's Jakub Pachocki says the computation graph depth of current frontier models, including Astra, is within a factor of two of GPT-4. He adds that chain-of-thought monitoring, which OpenAI has used since its first reasoning models, is fragile and trending negatively, though the company is researching ways to strengthen it.
Source: Jakub Pachocki · x.com