Browse Comments — Raw (as collected)
Close reading of the corpus at each pipeline stage: raw → clean → relevant → coded.
115
comments matched
· page 6 of 6
It's like asking a 10 year old how confident he is about string theory!! In his mind, the kid will always be confident and keep giving you more and more hallucinating/made up answers.
Pascal BORNET I believe this is a RAG issue that needs to be debugged.
Osama Sohail There is a way to do that by creating another database at the same time the LLM is created.
This needs common sense not AI
If it's brown, lay down.
If it's black, fight back.
If it's white, say good night.
Yeah its so usefull in real life! 😂
Too true. 😂
I asked AI a question, and it gave me an answer.
I then said that my wife gives a different answer, and she is never wrong.
AI then changed its answer to my wife's. 🤣
😂😂😂
Always friendly answers, but not always what you need in the specific context. AI is just learning now, to understand your spatial environment. This is an important part and will change when we have glasses.
It’s probably good that we didn’t have access to GenAI when we were hunting gazelles on the savannahs
I have given permanent instruction to provide an independent view with rationale. Helps to minimise unscheduled breathing exercises session 😂
AI does not know until we tell it.
Whether it be context, problem statement , situation, priority or risks.
It is important to provide complete statements.
Also any of the factors of context might get dropped by AI systems as the conversation progresses.
But, isn't that a problem with common human judgements as well ?
Confidence without a validation layer is just noise someone else inherits later.
OMG this is so true! When I tell people AI is stupid they don’t believe me (maybe I should not say stupid 😅) but it’s true AI only sees patterns and not the consequences in this case 😂