| ▲ | Emergent Introspective Awareness in Large Language Models(arxiv.org) | ||||||||||||||||||||||||||||||||||||||||
| 41 points by doener 7 hours ago | 15 comments | |||||||||||||||||||||||||||||||||||||||||
| ▲ | Retro_Dev 6 hours ago | parent | next [-] | ||||||||||||||||||||||||||||||||||||||||
> 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. | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
| ▲ | pyaamb 4 hours ago | parent | prev | next [-] | ||||||||||||||||||||||||||||||||||||||||
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? | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
| ▲ | skybrian 4 hours ago | parent | prev | next [-] | ||||||||||||||||||||||||||||||||||||||||
Previously posted to Anthropic's blog in October. (Maybe not the same version?) | |||||||||||||||||||||||||||||||||||||||||
| ▲ | whythismatters 6 hours ago | parent | prev | next [-] | ||||||||||||||||||||||||||||||||||||||||
>Submitted on 5 Jan 2026 | |||||||||||||||||||||||||||||||||||||||||
| ▲ | kelseyfrog 4 hours ago | parent | prev [-] | ||||||||||||||||||||||||||||||||||||||||
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. | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||