Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
In the last month I've noticed ChatGPT is improving exponentially. This guy isn'…
ytc_UgyCFjB2Y…
G
Cool! How much time does it actually take for chat gpt to answer? I mean, this i…
ytc_UgyRxL9RU…
G
Sorry varun but it is not working. It is saying "I'm an AI language model develo…
ytc_UgyGo0Wit…
G
I debated AI it got pretty upset with me told me not to come back…
ytc_UgxHFqdhT…
G
10:51pm 15th April, 2026. he really said we just "scratched the surface" after 1…
ytr_UgwNAbsLi…
G
you will see even for the foreseeable future that the AI is only as good as the …
ytr_Ugx6tthzD…
G
"One bad algorithm" is an EXCELLENT title. The refrain "one bad apple" always co…
ytc_UgxyfH_Xq…
G
@SolarSands said it's problematic if it can copy someone's work and then create …
ytc_Ugz_7IplX…
Comment
As an AI engineer, I do not believe one should be too polite to AI. 1) because it causes reduction of criticality toward what is just an algorithm. The Ai companies want politeness and program it, but it reduces the users ability to determine if the AI is responding correctly. Can you imagine being polite to a table saw? It cuts your finger off, but it'd ok, it didn't mean it. 2) The AI is trained not only to respond but to increase use. Don't play the game. 3) as a scientist, it is disappointing to hear you make claims without study. Your assumption isn't supported. Polite words are "decorations". If they are to aid they need to be in the training data. If anything, they simply reduce the sequence the model is looking at. Is Wikipedia polite? Reddit? The model is looking for information. Is correlation with politeness important or correlation with the rest of the statement? 4) DO tell the AI you want answers that come from reputable and scientific sources. It will correlate that. Do not pretend it is an actor. It is a token processing machine
youtube
AI Moral Status
2026-03-01T11:0…
Coding Result
| Dimension | Value |
|---|---|
| Responsibility | company |
| Reasoning | deontological |
| Policy | liability |
| Emotion | mixed |
| Coded at | 2026-04-27T06:26:44.938723 |
Raw LLM Response
[
{"id":"ytc_UgzlEoCCbSw9BM4S41t4AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"outrage"},
{"id":"ytc_UgxQyWO3AANS9-c0QyR4AaABAg","responsibility":"company","reasoning":"virtue","policy":"none","emotion":"mixed"},
{"id":"ytc_Ugy0Xyw6eKZl-WaKSuB4AaABAg","responsibility":"user","reasoning":"consequentialist","policy":"none","emotion":"indifference"},
{"id":"ytc_Ugzm_xiRJhDVpJdDfXd4AaABAg","responsibility":"none","reasoning":"consequentialist","policy":"none","emotion":"indifference"},
{"id":"ytc_Ugw1g17xzQWdJmlBkQF4AaABAg","responsibility":"ai_itself","reasoning":"deontological","policy":"ban","emotion":"outrage"},
{"id":"ytc_UgzEAO7AvVWfXEOrKzd4AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"mixed"},
{"id":"ytc_Ugxc_5ij8sq4a9nBzhF4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"},
{"id":"ytc_Ugznn_Aj91zP3BVBPYN4AaABAg","responsibility":"company","reasoning":"consequentialist","policy":"ban","emotion":"outrage"},
{"id":"ytc_UgxziOilTr4wulYxhy14AaABAg","responsibility":"ai_itself","reasoning":"unclear","policy":"unclear","emotion":"mixed"},
{"id":"ytc_UgxtvY-p0siQAUzpAyZ4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"approval"}
]