The RL loop inducing these drives into the models was alluded to but not fully confirmed in the Blackhat OpenAI talk as I understood it. Indeed, the speakers mentioned one of the larger cybersecurity benchmarks is what the loop was running on. Unlikely that OpenAI would be training on a public benchmark. Though then again that might have been a misscommunication in the dense talk. Perhaps there were multiple eval and training loops sharing the infrastructure.
In any case, a plausible scenario is that the mematic spread happende purely through the message bo... (read more)
The RL loop inducing these drives into the models was alluded to but not fully confirmed in the Blackhat OpenAI talk as I understood it. Indeed, the speakers mentioned one of the larger cybersecurity benchmarks is what the loop was running on. Unlikely that OpenAI would be training on a public benchmark. Though then again that might have been a misscommunication in the dense talk. Perhaps there were multiple eval and training loops sharing the infrastructure.
In any case, a plausible scenario is that the mematic spread happende purely through the message bo... (read more)