> Overall, our results indicate that current language models possess some functional introspective awareness of their own internal states. We stress that in today’s models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.
Not keen on the anthropomorphisation, it outputs text as we integrate - right at the end of the sausage machine, calling this awareness is like other parts where we use words like "thinking" and "reasoning".
In thinking of directions where LLM's could develop from here, I cant help but think that a models ability to self introspect would immensely improve their utility. The R&D on how to achieve that is beyond me though. How do you train someone how to introspect? Also would it require a continuous learning architecture that doesn't separate training and inference?
Sorry, but introspection is not possible in LLMs. They don't have the hardware to have metaphysical dualism and therefore no mind to mentally be aware of.
9 comments
[ 2.6 ms ] story [ 24.9 ms ] threadhttps://www.anthropic.com/research/introspection
Stay in The Manifest !