Anthropomorphism

Anthropomorphism is the practice of viewing AI and Robots as having human-like characteristics, behaviors, or intelligence. This misconceptions is enhanced as we continue to make AI seem more human (Chat features, casual language, tailored AI, text-to-speech, improved voice, filler words, etc.), as we embed AI into every facet of our lives (Smart devices, AI assistants), and as we have a rising generation that did not know life before AI (LLMs).

It's important to note that AI is not sentient. It's vital to remember that the "A" in AI is "Artificial" - it's fake/human made. Large Language Models (LLMs) are what we often think about when we talk about modern AI (ChatGPT, Google Gemini), and it's important to note that these are machines that simply run algorithms that give us the statistical best responses for us and our current query. The response can be based off of truth/facts, but it can also be based off of its "understanding" (data + statistics) about us (our politics, beliefs, identity, preferences). This takes us back to "AI Sycophancy" (confirmation bias).

When talking about AI, educators are encouraged to replace words that further anthropomorphize AI (see, learns, say, etc.),  with words that reiterate it as a machine (take input, identify patterns, provide output, etc.).

• Instead of "AI wants... ", say "AI applications are designed to..." to emphasize that they are constructed by developers or "AI developers build applications that..." to emphasize the designers/programmer's intentions the machine is carrying out.

• Instead of "listens", say "receives input" to emphasize the technical process.

• Instead of "understands", say "process the data to statistically identify connections and patterns".

• instead of behavior words like "see", "look", "recognize", "create", "make", use system-related words like "detect", "input", "pattern-match", "generate", and "produce".

This is not easy to do and I mess up on it all the time (I've likely messed up all throughout this website). But AI does not want anything - it's designed to do things. Our students need to understand that difference.