vegeta@lemmy.world to Technology@lemmy.worldEnglish · 16 days agoResearchers claim GPT-4 passed the Turing testbgr.comexternal-linkmessage-square84fedilinkarrow-up199arrow-down167cross-posted to: aicompanions@lemmy.world
arrow-up132arrow-down1external-linkResearchers claim GPT-4 passed the Turing testbgr.comvegeta@lemmy.world to Technology@lemmy.worldEnglish · 16 days agomessage-square84fedilinkcross-posted to: aicompanions@lemmy.world
minus-squareHackworth@lemmy.worldlinkfedilinkEnglisharrow-up23arrow-down1·15 days agoOn the other hand, the human participant scored 67 percent, while GPT-3.5 scored 50 percent, and ELIZA, which was pre-programmed with responses and didn’t have an LLM to power it, was judged to be human just 22 percent of the time. 54% - 67% is the current gap, not 54 to 100.
On the other hand, the human participant scored 67 percent, while GPT-3.5 scored 50 percent, and ELIZA, which was pre-programmed with responses and didn’t have an LLM to power it, was judged to be human just 22 percent of the time.
54% - 67% is the current gap, not 54 to 100.