For “deep research” I’m also reading “getting the answers right”.
Most people I talk to are at the point now where getting completely incorrect answers 10% of the time — either obviously wrong from common sense, or because the answers are self contradictory — undermines a lot of trust in any kind of interaction. Other than double checking something you already know, language models aren’t large enough to actually know everything. They can only sound like they do.
What I’m looking for is therefore not just the correct answer, but the correct answer in an amount of time that’s faster than it would take me to research the answer myself, and also faster than it takes me to verify the answer given by the machine.
It’s one thing to ask a pupil to answer an exam paper to which you know the answers. It’s a whole next level to have it answer questions to which you don’t know the answers, and on whose answers you are relying to be correct.
Most people I talk to are at the point now where getting completely incorrect answers 10% of the time — either obviously wrong from common sense, or because the answers are self contradictory — undermines a lot of trust in any kind of interaction. Other than double checking something you already know, language models aren’t large enough to actually know everything. They can only sound like they do.
What I’m looking for is therefore not just the correct answer, but the correct answer in an amount of time that’s faster than it would take me to research the answer myself, and also faster than it takes me to verify the answer given by the machine.
It’s one thing to ask a pupil to answer an exam paper to which you know the answers. It’s a whole next level to have it answer questions to which you don’t know the answers, and on whose answers you are relying to be correct.