OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes most reasoning models.
<iframe src="https://statesidedaily.com/embed/cluster/38749c4e04cac3e624acf4a2a98c776c11d264b8" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="OpenAI’s new reasoning technique alarms AI safety experts"></iframe>
OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes most reasoning models.