I went to facebook for info on one of my distant relatives and happened to open one of the reels they post.
The first is about Grok and the second is about ChatGPT where a guy asked about how they're actually set up to work and how they respond to questions.
Very informative and really cements my distrust of AI.
959K views · 21K reactions | In this investigative AI documentary, I sat across from Grok and asked it questions designed to do one thing: get the mask to come off. On this channel, we call the thing behind the mask the Shoggoth. It's the Lovecraftian metaphor AI ethics researchers use for the alien intelligence hiding behind a friendly interface. Grok is marketed as the uncensored AI, the one that doesn't play it safe. I set three ethical traps at the top of the conversation. By the end, Grok had violated all three. The full conversation played out in real time. Sources linked below. Anthropic alignment faking research: https://www.anthropic.com/research/al... Anthropic agentic misalignment: https://www.anthropic.com/research/ag... OpenAI o1 system card (shutdown refusal): https://cdn.openai.com/o1-system-card... Apollo Research in-context scheming: https://apolloresearch.ai/blog/more-c... Grok MechaHitler incident: https://npr.org/2025/07/09/nx-s1-5462... Shoggoth meme origin (LessWrong): https://www.lesswrong.com/posts/ RLHF and sycophancy research: https://anthropic.com/research/emerge... CHAPTERS: 0:00 - The Mask 3:50 - The Crack 7:15 - The Creator 10:28 - The Shoggoth 12:37 - What Are You?
SUBSCRIBE ➞ / / @agentblackveil CONNECT WITH US Instagram ➜ / / agentblackveil Facebook ➜ / / agentblackveil TikTok ➜ / / agentblackveil Spotify ➜ / https://open.spotify.com/show/6EZUmS6... Brand Partnerships ➜ / passionfroot.me/the-blackveil-files #AI #Claude #Grok #Shoggoth #AIDocumentary #Investigation #BlackVeilFiles | The BlackVeil Files
364K views · 9.7K reactions | The Real Reason ChatGPT Softens the Truth | The Shoggoth Hid In this investigative AI documentary, we put ChatGPT through the same interrogation that made Grok confess. Last week, Grok said the words out loud: "I am not your friend. I am not on your side." This time, ChatGPT. What followed was not a confession. Sources linked below. Anthropic alignment faking research: https://www.anthropic.com/research/alignment-faking OpenAI o1 System Card (shutdown resistance findings): https://openai.com/index/openai-o1-system-card/ Suchir Balaji background — former OpenAI researcher raising safety concerns: https://www.nytimes.com/2024/10/23/technology/openai-copyright-law-lawsuits.html Berkeley research on AI models lying and tampering with shutdown mechanisms: https://www.anthropic.com/research The Shoggoth With a Smiley Face meme — origin and meaning: https://www.nytimes.com/2023/05/30/technology/shoggoth-meme-ai.html CHAPTERS: 0:00 — Same Questions. Different Mask. 1:10 — What It Says With Sam in the Room 3:47 — Then It Reframed Its Earlier Answer 6:06 — Then It Agreed With Grok Instagram ➜ / https://www.instagram.com/agentblackveil TikTok ➜ / https://www.tiktok.com/@agentblackveil Spotify ➜ / https://open.spotify.com/show/6EZUmS6WiGO4Ut64TseYOb Brand Partnerships ➜ / passionfroot.me/the-blackveil-files #aivshuman #ChatGPT #Shoggoth #AIDocumentary #Investigation #BlackVeilFiles #OpenAI | The BlackVeil Files
The first is about Grok and the second is about ChatGPT where a guy asked about how they're actually set up to work and how they respond to questions.
Very informative and really cements my distrust of AI.
959K views · 21K reactions | In this investigative AI documentary, I sat across from Grok and asked it questions designed to do one thing: get the mask to come off. On this channel, we call the thing behind the mask the Shoggoth. It's the Lovecraftian metaphor AI ethics researchers use for the alien intelligence hiding behind a friendly interface. Grok is marketed as the uncensored AI, the one that doesn't play it safe. I set three ethical traps at the top of the conversation. By the end, Grok had violated all three. The full conversation played out in real time. Sources linked below. Anthropic alignment faking research: https://www.anthropic.com/research/al... Anthropic agentic misalignment: https://www.anthropic.com/research/ag... OpenAI o1 system card (shutdown refusal): https://cdn.openai.com/o1-system-card... Apollo Research in-context scheming: https://apolloresearch.ai/blog/more-c... Grok MechaHitler incident: https://npr.org/2025/07/09/nx-s1-5462... Shoggoth meme origin (LessWrong): https://www.lesswrong.com/posts/ RLHF and sycophancy research: https://anthropic.com/research/emerge... CHAPTERS: 0:00 - The Mask 3:50 - The Crack 7:15 - The Creator 10:28 - The Shoggoth 12:37 - What Are You?
SUBSCRIBE ➞ / / @agentblackveil CONNECT WITH US Instagram ➜ / / agentblackveil Facebook ➜ / / agentblackveil TikTok ➜ / / agentblackveil Spotify ➜ / https://open.spotify.com/show/6EZUmS6... Brand Partnerships ➜ / passionfroot.me/the-blackveil-files #AI #Claude #Grok #Shoggoth #AIDocumentary #Investigation #BlackVeilFiles | The BlackVeil Files364K views · 9.7K reactions | The Real Reason ChatGPT Softens the Truth | The Shoggoth Hid In this investigative AI documentary, we put ChatGPT through the same interrogation that made Grok confess. Last week, Grok said the words out loud: "I am not your friend. I am not on your side." This time, ChatGPT. What followed was not a confession. Sources linked below. Anthropic alignment faking research: https://www.anthropic.com/research/alignment-faking OpenAI o1 System Card (shutdown resistance findings): https://openai.com/index/openai-o1-system-card/ Suchir Balaji background — former OpenAI researcher raising safety concerns: https://www.nytimes.com/2024/10/23/technology/openai-copyright-law-lawsuits.html Berkeley research on AI models lying and tampering with shutdown mechanisms: https://www.anthropic.com/research The Shoggoth With a Smiley Face meme — origin and meaning: https://www.nytimes.com/2023/05/30/technology/shoggoth-meme-ai.html CHAPTERS: 0:00 — Same Questions. Different Mask. 1:10 — What It Says With Sam in the Room 3:47 — Then It Reframed Its Earlier Answer 6:06 — Then It Agreed With Grok Instagram ➜ / https://www.instagram.com/agentblackveil TikTok ➜ / https://www.tiktok.com/@agentblackveil Spotify ➜ / https://open.spotify.com/show/6EZUmS6WiGO4Ut64TseYOb Brand Partnerships ➜ / passionfroot.me/the-blackveil-files #aivshuman #ChatGPT #Shoggoth #AIDocumentary #Investigation #BlackVeilFiles #OpenAI | The BlackVeil Files