cm0002@lemmy.world to Technology@lemmy.worldEnglish · 5 days agoAI models routinely lie when honesty conflicts with their goalswww.theregister.comexternal-linkmessage-square117linkfedilinkarrow-up1598arrow-down126
arrow-up1572arrow-down1external-linkAI models routinely lie when honesty conflicts with their goalswww.theregister.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 5 days agomessage-square117linkfedilink
minus-squareFreedomAdvocate@lemmy.net.aulinkfedilinkEnglisharrow-up4arrow-down1·4 days agoIt completed the task, it was just wrong.
minus-squarethedruid@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down6·4 days agoNo. It gave the wrong answer therefore it didn’t complete the task. It gave the wrong answer. Task incomplete That’s literally how a task works.
minus-squareFreedomAdvocate@lemmy.net.aulinkfedilinkEnglisharrow-up1·18 hours agoThe task was to tell you the difference. It told you the difference, it was just wrong about the differences. Giving an incorrect answer to a task is still doing the task.
minus-squarethedruid@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down1·12 hours agoI swear. The mental gymnastics If I tell you to take the garbage out, then you throw it through the window , that isn’t molesting the task. Anymore than this does 1+1 is 2. Don’t freaking force crap to fit into that “feature, not a bug” bullshit. It’s the issue we have with products in general. Excuses instead of results. Welcome to the world of a. I support
minus-squareFreedomAdvocate@lemmy.net.aulinkfedilinkEnglisharrow-up1·3 hours agoSo if you answer a question wrong on a test you didn’t complete the test?
minus-squareChozo@fedia.iolinkfedilinkarrow-up5·4 days agoBruh. The task was to mislead. That’s what it did.
minus-squarethedruid@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down1·4 days agoThat’s not the task I mentioned. I asked what the difference between two modes is. It was wrong. It was confidently wrong. I
minus-squareChozo@fedia.iolinkfedilinkarrow-up3·4 days agoAre you talking about the hypothetical scenario you made up about the subject you don’t even understand? No wonder we’re going in circles. I’m talking about the article.
minus-squarethedruid@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down2·4 days agoDid you go to trump university? You responded to MY comments which were clear. Stop moving goal posts ,making assumptions, and resorting to name-calling g it’s a sign of stupidity, that I am not ready to truly apply to you, yet Now. Good evening.
minus-squareChozo@fedia.iolinkfedilinkarrow-up3arrow-down1·4 days agoNobody called you anything, dude. Are we having different conversations or something?
It completed the task, it was just wrong.
No. It gave the wrong answer therefore it didn’t complete the task. It gave the wrong answer. Task incomplete
That’s literally how a task works.
The task was to tell you the difference. It told you the difference, it was just wrong about the differences. Giving an incorrect answer to a task is still doing the task.
I swear. The mental gymnastics
If I tell you to take the garbage out, then you throw it through the window , that isn’t molesting the task. Anymore than this does
1+1 is 2. Don’t freaking force crap to fit into that “feature, not a bug” bullshit. It’s the issue we have with products in general.
Excuses instead of results. Welcome to the world of a. I support
So if you answer a question wrong on a test you didn’t complete the test?
Bruh. The task was to mislead. That’s what it did.
That’s not the task I mentioned.
I asked what the difference between two modes is. It was wrong. It was confidently wrong.
I
Are you talking about the hypothetical scenario you made up about the subject you don’t even understand? No wonder we’re going in circles.
I’m talking about the article.
Did you go to trump university? You responded to MY comments which were clear.
Stop moving goal posts ,making assumptions, and resorting to name-calling g it’s a sign of stupidity, that I am not ready to truly apply to you, yet
Now. Good evening.
Nobody called you anything, dude. Are we having different conversations or something?