> predict what it thinks a chatbot that's explicitly non-racist would respond. N...

		hgsgm on Feb 16, 2023 \| parent \| context \| favorite \| on: Bing: “I will not harm you unless you harm me firs... > predict what it thinks a chatbot that's explicitly non-racist would respond. No, it predicts words that commonly appear in the vicinity of words that appear near the word "non-racist".