▲ 513 ▼ Musk's AI firm deletes posts after chatbot praises Adolf Hitler (www.bbc.com) submitted 1 year ago by Davriellelouna@lemmy.world to c/technology@lemmy.world 48 comments fedilink hide all child comments
[–] lIlIlIlIlIlIl@lemmy.world 12 points 1 year ago (1 child) Have a source on that claim? permalink fedilink source parent hideshow 1 child comment replies: [–] wise_pancake@lemmy.ca 26 points 1 year ago In February when Grok 3 was first on every chatbot arena metric – that was just a bit after deepseek r1, and o3, and the space has evolved a lot since then. However, checking wikipedia it actually seems like they juiced the metrics by using unfair comparisons and letting Grok try the problems 64 times and returning the best answer in their comparisons. https://en.wikipedia.org/wiki/Grok_%28chatbot%29#Grok-3 permalink fedilink source parent
[–] wise_pancake@lemmy.ca 26 points 1 year ago In February when Grok 3 was first on every chatbot arena metric – that was just a bit after deepseek r1, and o3, and the space has evolved a lot since then. However, checking wikipedia it actually seems like they juiced the metrics by using unfair comparisons and letting Grok try the problems 64 times and returning the best answer in their comparisons. https://en.wikipedia.org/wiki/Grok_%28chatbot%29#Grok-3 permalink fedilink source parent