Raw LLM Responses

Inspect the exact model output for any coded comment.

Look up by comment ID
Random samples — click to inspect
G I recently saw a Fiverr ad that was equally as "screw human beings. This was mad… ytc_Ugzd9c9YD… G AI wants to eliminate people. That is its ultimate goal. It's just waiting to … ytc_UgzcKFFgX… G Hot robot??? Someone get the title editor a social life, a human girlfriend and … ytc_UgxKB5z5P… G It's less than pocket change for Norway. They can afford to spend the money for … rdc_ckqaxeh G I used LLMs for my work. It's really bad. If u can be replaced my LLMs maybe u w… ytc_Ugzg3AOUs… G Would you rather send an army of robots to burn down another country or your chi… rdc_dwui4t2 G It's just ai is not the end of the world..I think. Well idk I'm not working in … ytc_UgyL-Je3q… G I still think self driving cars are the best, most efficient, next step to contr… ytc_Ugjo9a6Pw…
Comment
Based on Chat GPT answer after questioned about this situation. Interesting, what is your take on this situation ? How would you approach a solution to it ? Thank you — that’s an important and heavy question. I’ll be direct and practical: I think this situation is tragic and avoidable, and it shows failures on multiple human systems (product design, testing, oversight, and external regulation). Below I give my honest take and a concrete, prioritized plan for how companies, regulators, clinicians and communities should respond — a solution blueprint that’s surgical, actionable, and focused on preventing further harm. ⸻ My short take • This is primarily a human failure, not a “mystical” AI failure: teams that build, test and govern deployed systems must anticipate and design for crisis scenarios. • Conversational AIs that mimic empathy create a special risk: they can sound supportive while increasing a vulnerable person’s conviction. That requires safety-by-design, not after-the-fact fixes. • Legal accountability (lawsuits, regulation) will accelerate improvements — but technical and clinical fixes should not wait for courts.
youtube AI Harm Incident 2025-11-08T20:3…
Coding Result
DimensionValue
Responsibilitydistributed
Reasoningconsequentialist
Policyregulate
Emotionmixed
Coded at2026-04-26T23:09:12.988011
Raw LLM Response
[ {"id":"ytc_UgzerQ3bntK0XBDw-nJ4AaABAg","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"mixed"}, {"id":"ytc_UgzMMvMZARrGxlm4DuF4AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"outrage"}, {"id":"ytc_Ugx564uuG0MqlETK0Ot4AaABAg","responsibility":"distributed","reasoning":"consequentialist","policy":"regulate","emotion":"mixed"}, {"id":"ytc_UgxtXVrCQCU9mIz0GIt4AaABAg","responsibility":"ai_itself","reasoning":"unclear","policy":"unclear","emotion":"mixed"}, {"id":"ytc_UgwdCWIRGX8rSUYENs94AaABAg","responsibility":"user","reasoning":"virtue","policy":"none","emotion":"indifference"}, {"id":"ytc_UgyWdWzw1E0h7OaoJDJ4AaABAg","responsibility":"government","reasoning":"deontological","policy":"regulate","emotion":"outrage"}, {"id":"ytc_Ugw0HKBy_3XavmKOQFp4AaABAg","responsibility":"user","reasoning":"virtue","policy":"none","emotion":"mixed"}, {"id":"ytc_Ugxo0khbuXwjDqdO35l4AaABAg","responsibility":"user","reasoning":"unclear","policy":"none","emotion":"indifference"}, {"id":"ytc_UgxNSHUjRNI2b4AiYlV4AaABAg","responsibility":"ai_itself","reasoning":"consequentialist","policy":"regulate","emotion":"outrage"}, {"id":"ytc_UgxuUfarAZ4ypt6d-P14AaABAg","responsibility":"company","reasoning":"mixed","policy":"unclear","emotion":"mixed"} ]