Juki@lemmy.world to Programmer Humor@lemmy.ml · 1 year agoEvery tech company rnlemmy.worldimagemessage-square128fedilinkarrow-up11.79Karrow-down127
arrow-up11.77Karrow-down1imageEvery tech company rnlemmy.worldJuki@lemmy.world to Programmer Humor@lemmy.ml · 1 year agomessage-square128fedilink
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.
I know. It’s still baffling how much it messes up when adding two numbers.
I just asked GPT-4:
Its reply:
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.