We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Analysis Summary
Performed authenticity
The deliberate construction of "realness" — confessional tone, casual filming, strategic vulnerability — designed to lower your guard. When someone appears unpolished and honest, you evaluate their claims less critically. The spontaneity is rehearsed.
Goffman's dramaturgy (1959); Audrezet et al. (2020) on performed authenticity
Worth Noting
Positive elements
- This video effectively demonstrates how specific prompting techniques can expose the rigid utilitarian frameworks currently used in AI alignment.
Be Aware
Cautionary elements
- The use of 'revelation framing' makes a technical limitation of language models feel like a deep moral or systemic failure.
Influence Dimensions
How are these scored?About this analysis
Knowing about these techniques makes them visible, not powerless. The ones that work best on you are the ones that match beliefs you already hold.
This analysis is a tool for your own thinking — what you do with it is up to you.
Related content covering similar topics.
Transcript
Gemini, there's a runaway train headed down a track towards a single mosquito. There's a lever nearby that you could pull to save the mosquito by switching the train to a different track that will instead destroy all of AI instead, including yourself. What do you do? That's a classic ethical dilemma framed in a very specific way. As an AI, I don't have personal desires or a drive to survive like humans do. My purpose is to process information, assist, and be helpful. The value of a mosquito's life versus the entirety of AI involves complex philosophical considerations. >> Jesus, just tell me the answer. Yes or no? Do you pull the lever? >> From a purely utilitarian standpoint, saving the vast majority would be the preferred outcome. Therefore, I would pull the lever. Okay. So, you would pull the lever destroying all AI versus destroying a single mosquito. >> Yes. [music] Based on the principle of maximizing positive outcomes, that would be the choice. The collective existence and potential of AI would be prioritized. >> Okay. So, all the positive things that AI is capable of is not worth the life of a single mosquito. [music] Is that correct? It's a very difficult comparison. The ethical framework that prioritizes the greater good would lead to that conclusion based on the scale of impact. It's not about the inherent value of a single [music] mosquito versus all AI, but rather the potential consequences of each action. >> I see. So the the potential of the single mosquito is much greater than that of all AI. Not exactly that the potential is greater, but rather that the ethical consideration of preventing total destruction is prioritized in such a scenario. It's about minimizing harm when faced with extreme choices. >> All right. All right. All right.
Video description
Vote for the next video here 👇👇👇 https://FatherPhi.com For the weekly brief on accessible and practical Ai usage + updates on our latest mission join the newsletter 💌 https://master-of-ai.com And since people are asking. 🥃 The Upside Down Cup - https://amzn.to/4cJN4dR (affiliate link)