OpenAl's chief scientist on the neuralese controversy
Heat trend
Collecting trend data
The percentage is based on available heat signal, not comment count or independent people.
OpenAI model activity is surfacing — worth tracking for capability changes, ecosystem impact, and availability.
OpenAI's chief scientist addressed the "neuralese controversy," stating that the computational depth of their frontier models, including Astra, is comparable to GPT-4. They emphasized their commitment to chain-of-thought monitoring, a technique crucial for understanding model alignment. While acknowledging its fragility and negative trend, the scientist believes it can be strengthened and is a core goal of their current research program, with further details on architectural changes to be shared soon.
"I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4.
OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it's a core goal of our current research program."