Juki@lemmy.world to Programmer Humor@lemmy.ml · 1 year agoEvery tech company rnlemmy.worldimagemessage-square132fedilinkarrow-up11.81Karrow-down126
arrow-up11.78Karrow-down1imageEvery tech company rnlemmy.worldJuki@lemmy.world to Programmer Humor@lemmy.ml · 1 year agomessage-square132fedilink
minus-squaredanielbln@lemmy.worldlinkfedilinkarrow-up6·1 year agoIt’s a language model, I don’t know why you would expect math. Tell it to output code to perform the math, that’ll work just fine.
minus-squaretriclops6@lemmy.calinkfedilinkarrow-up2·1 year agoThen it should say so instead of attempting and failing at the one thing computers are supposed to be better than us at
minus-squaredanielbln@lemmy.worldlinkfedilinkarrow-up2arrow-down1·edit-21 year agoWell, if I try to use Photoshop to calculate a polynomial it’s not gonna work all that well either, right tool for the job and all. The fact that LLMs are terrible at knowing what they don’t know should be well known by now (ironically).
minus-squaretriclops6@lemmy.calinkfedilinkarrow-up1·1 year agoAnd if Photoshop had a way to ask it for such, it’d be a mistake. Gpt thinking it knows something and hallucinating is ultimatelya bug, not a feature, no matter what the apologists say
minus-squarefocus@lemmy.filmlinkfedilinkEnglisharrow-up2arrow-down2·1 year agoI know. It’s still baffling how much it messes up when adding two numbers.
minus-squaredanielbln@lemmy.worldlinkfedilinkarrow-up1·1 year agoI just asked GPT-4: > What’s 7 * 8 divided by 10, to the power of 3? Its reply: > Let’s break this down step by step: > First, multiply 7 and 8 to get 56. > Then, divide 56 by 10 to get 5.6. > Finally, raise 5.6 to the power of 3 (5.6 * 5.6 * 5.6) to get 175.616. > So, 7 * 8 divided by 10, to the power of 3 equals 175.616
minus-squarefocus@lemmy.filmlinkfedilinkEnglisharrow-up1·1 year agoIt’s pretty hit or miss though… I’ve had lots of good calculations with the odd wrong one sprinkled in, making it unreliable for doing maths. Mostly because it presents the result with absolute certainty.
minus-squaredan@upvote.aulinkfedilinkEnglisharrow-up2arrow-down1·1 year agoIt’s not baffling at all… It’s a language model, not a math robot. It’s designed to write English sentences, not to solve math problems.
It’s a language model, I don’t know why you would expect math. Tell it to output code to perform the math, that’ll work just fine.
Then it should say so instead of attempting and failing at the one thing computers are supposed to be better than us at
Well, if I try to use Photoshop to calculate a polynomial it’s not gonna work all that well either, right tool for the job and all.
The fact that LLMs are terrible at knowing what they don’t know should be well known by now (ironically).
And if Photoshop had a way to ask it for such, it’d be a mistake.
Gpt thinking it knows something and hallucinating is ultimatelya bug, not a feature, no matter what the apologists say
I know. It’s still baffling how much it messes up when adding two numbers.
I just asked GPT-4:
> What’s 7 * 8 divided by 10, to the power of 3?
Its reply:
> Let’s break this down step by step:
> First, multiply 7 and 8 to get 56.
> Then, divide 56 by 10 to get 5.6.
> Finally, raise 5.6 to the power of 3 (5.6 * 5.6 * 5.6) to get 175.616.
> So, 7 * 8 divided by 10, to the power of 3 equals 175.616
It’s pretty hit or miss though… I’ve had lots of good calculations with the odd wrong one sprinkled in, making it unreliable for doing maths. Mostly because it presents the result with absolute certainty.
It’s not baffling at all… It’s a language model, not a math robot. It’s designed to write English sentences, not to solve math problems.