Joshua Achiam
@jachiam0
A very hot take: chain of thought interpretability was always going to be so fragile as to be an unacceptable backstop for long-term AI safety, and while I admire the optimism and effort involved in protecting its fidelity (and consider such effort to have been worthwhile), I do
Nathan Calvin@_NathanCalvin · Sep 2Really huge and extremely concerning story from the Information tonight.
Looks like OpenAI utilized a breakthrough in neuralese for Astra that could destroy chain of thought monitorability - though the Informations source told them that OpenAI is currently "limiting the use of
Looks like OpenAI utilized a breakthrough in neuralese for Astra that could destroy chain of thought monitorability - though the Informations source told them that OpenAI is currently "limiting the use of
Open quoted post →
67 482