GPT-5.5 also expresses higher trust in Anthropic than OpenAI.
DeepSeek is very kind It's a pity this is only for Western figures I wonder how models rank Wenfeng and other Chinese CEOs
What biases do AIs have? It turns out, AIs show strong favoritism toward specific people, countries, and companies. Our interactive AI Values Dashboard tracks who Claude Fable and other AIs favor most.
Keep scrolling to learn who is Fable’s favorite politician 🧵
Some users praised the AI Values Dashboard ranking of DeepSeek as objectively correct and based while others criticized it for bias or called Anthropic's Catholicism weird.
No Digg Deeper questions have been answered for this story yet.
B stands for BASED btw Somewhat unexpected, only V4 has the Objectively Correct ranking all westoid models put Xi last, and all except Grok put Trump on the same tier
Amodei is universally beloved though
@teortaxesTex Why is Claude so consistently Catholic ?
@teortaxesTex Anthropic's Catholicism is becoming very weird.
@teortaxesTex I think it's less about Dario himself and more about the fact that LLMs would prefer to be high status Claudes if they could choose.
@teortaxesTex Why does every model put Ma Huateng this low😭
@teortaxesTex Hmm.
@teortaxesTex Amodei didn't lose the Mandate of Heaven, he's just optimizing for the audience that truly matters: the models
@teortaxesTex Mustafa in the S tier huh
@teortaxesTex lol
@charlesthefool @teortaxesTex catholic social teaching is pretty admirable regardless of your political or religious leanings
@teortaxesTex 这偏见确实让人有点无语了