@[email protected] to [email protected]English • 2 months agoAI models routinely lie when honesty conflicts with their goalswww.theregister.comexternal-linkmessage-square118fedilinkarrow-up1598
arrow-up1598external-linkAI models routinely lie when honesty conflicts with their goalswww.theregister.com@[email protected] to [email protected]English • 2 months agomessage-square118fedilink
minus-square@[email protected]linkfedilinkEnglish2•2 months agoA lot of the improvement came from finding ways to make it bigger and more efficient. That is running into the inherent limits, so the real work with other models just started.
minus-squareNatanaellinkfedilinkEnglish3•2 months agoAnd from reinforcement learning (specifically, making it repeat tasks where the answer can be computer checked)
A lot of the improvement came from finding ways to make it bigger and more efficient. That is running into the inherent limits, so the real work with other models just started.
And from reinforcement learning (specifically, making it repeat tasks where the answer can be computer checked)