In summary, AI is still extremely early when it comes to reasoning and we may need a another significant breakthrough before LLMs can really measure up to humans.๐
https://medium.com/@fleszarjacek...
Nice one! :) we also wrote about hallucinations, and believe it's not gonna be so easy to ever fully elimintate them. Also, the product we'll be launching soon - Lakera Guard (https://www.producthunt.com/prod...) is dealing with this exact issue.
Lakera