eicker@lemmy.world to News@lemmy.world · 3 days agoAI Agent Can’t Explain Why It Randomly Ordered its Human Meat Proxy an Absurd Number of Eggs: "I don't have a good answer."futurism.comexternal-linkmessage-square87linkfedilinkarrow-up1318arrow-down117
arrow-up1301arrow-down1external-linkAI Agent Can’t Explain Why It Randomly Ordered its Human Meat Proxy an Absurd Number of Eggs: "I don't have a good answer."futurism.comeicker@lemmy.world to News@lemmy.world · 3 days agomessage-square87linkfedilink
minus-squareMangoCat@lemmy.sdf.orglinkfedilinkarrow-up8arrow-down1·2 days ago difficult to avoid using anthropomorphizing language when describing the output of AI agents. Precisely because the underlying LLMs are trained on human writing patterns and mostly reproduce the words that humans would most likely respond with.
Precisely because the underlying LLMs are trained on human writing patterns and mostly reproduce the words that humans would most likely respond with.