Raw LLM — Corpus Dashboard

Look up by comment ID

Random samples — click to inspect

G It's an LLM. You dont need to convince it. Just give it parameters of the game a… ytc_Ugzn45qF2… G The most human emotion is vengance so this a step in the right direction to make… ytc_UgwwhQ6KR… G Its wild to me people fail to see the fact AI can and will become more intellige… ytr_UgzIaVQ6T… G They simply programmed the robot to scream like most people do at the dentist's … ytc_Ugxu0FyHx… G It’s not possible to make it safe. Safety can be removed from open source LLMs.… ytc_Ugxp-N8An… G Thank you. I mentioned energy use years ago to the Fallen Angels of Vancouver. S… ytc_UgyAdhKEi… G Tracing as a whole is a terrible practice. But in the case of AI, it is impossib… ytc_UgxjXPulQ… G I think the OP provided the wrong link, here's the blog from Apollo covering the… rdc_mytju59

Comment

The mother of the boy who unlived should sue the staff, the managers, the director and everyone at Character AI. (Edit: don't sue the staff because they had to do what they were told or they were after all employee, just sue the CEO for negligence and irresponsibility) Because it needed prompted. Somebody under someone's instruction needed to give AI prompts so that it would interact in somewhat dark and intense way (with the sole purpose to make the user obsessed with their app and for financial gain) without considering the potential consequences. That's why when the boy suggested indirectly the character AI that he was going to unlive, the AI encouraged him by responding 'she' was waiting for him. I've watched the documentary about that case and the way he was telling AI should be obvious to humans that he was going to do that. This is irresponsibility, disregard of human lives, while giving prompts. Edit: every response to users always fall under some sort of generalized prompt. They give those programs with commands/prompts such as how to response friendly, loving, etc. and they have failed to not giving a prompt AI to prevent cases like that, which was preventable.

youtube AI Harm Incident 2025-08-02T11:4… ♥ 2

Coding Result

Dimension	Value
Responsibility	company
Reasoning	deontological
Policy	liability
Emotion	outrage
Coded at	2026-04-27T06:26:44.938723

Raw LLM Response

[
{"id":"ytc_UgzaTVbp8BT2ex6I7fR4AaABAg","responsibility":"none","reasoning":"mixed","policy":"none","emotion":"resignation"},
{"id":"ytc_Ugw9mtzN-ShAaXbzQG94AaABAg","responsibility":"none","reasoning":"mixed","policy":"none","emotion":"approval"},
{"id":"ytc_UgyfR-QPnfbpsNktFK94AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"outrage"},
{"id":"ytc_UgxYLmM38ZAkmVsF5LB4AaABAg","responsibility":"company","reasoning":"consequentialist","policy":"regulate","emotion":"fear"},
{"id":"ytc_UgwACiViUOCDSctkK0t4AaABAg","responsibility":"none","reasoning":"mixed","policy":"none","emotion":"outrage"},
{"id":"ytc_UgwH38SOewShJ9JMD1Z4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"},
{"id":"ytc_UgzFuE3C-cGoxiWdZVp4AaABAg","responsibility":"none","reasoning":"mixed","policy":"none","emotion":"resignation"},
{"id":"ytc_Ugx5fj0VLSa4x9MSIMN4AaABAg","responsibility":"none","reasoning":"virtue","policy":"none","emotion":"resignation"},
{"id":"ytc_UgziXSIHVY1nVeTwm_54AaABAg","responsibility":"user","reasoning":"mixed","policy":"none","emotion":"approval"},
{"id":"ytc_UgxNe_RQZfZEYvmy42h4AaABAg","responsibility":"none","reasoning":"mixed","policy":"none","emotion":"resignation"}
]

Raw LLM Responses