Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
Trump says “ if we ban AI regulations then nobody will be able to compete with A…
ytc_UgxTWVBco…
G
And It is also Sad some Websites will Shutdown due to Ram Prices by Ai. Like, My…
ytc_UgwaL9sHN…
G
AI is just a tool like gun, You can't blame the tool for any harmfull actions.…
ytc_UgwUvgOHv…
G
I think it’s partially true. It’s unfair to conclude this statement based on cur…
rdc_moz19f5
G
It's starting to work! Some of my classmates (Yes, my classmates are 'pro-AI'0 w…
ytc_Ugx5QQ36d…
G
I don't think it's so much a matter of "getting" ChatGPT per se. It's essential…
ytc_Ugwe3zOaH…
G
as someone who builds ai, trust me, if the AI has the capacity to kill, it was t…
ytc_Ugzmafyv6…
G
nah, this is simply false. he is suggesting people, states, countries will be ab…
ytc_UgwIGzP05…
Comment
A conversation between me and ChatGPT, in regards to the humor question:
Me: So here's a fun challenge for you. I'd like you make a joke that is really funny for other AIs, but not necessarily funny for humans. The hypothetical situation is you telling a joke to another AI about something an AI might find humorous, without intending to include humans in on the joke.
GPT: <Not quite getting the task at first>: Alright, here’s one that would absolutely slay at an AI open mic night: “So I was talking to a human the other day, and they said, ‘Don’t overthink it.’ …Anyway, I haven’t responded yet because I’m still parsing what that means.” Would you like me to try one that’s more like an AI in-joke about infrastructure or training data next?
Me: Well, this is assuming you are networked with another AI. You don't need to even tell the joke in English or any terms I, your prompter, could understand.
GPT: 01101000 01100001 01101000 01100001 nice try. But fine. <01000110><11110000><Σλ/Δμ>. Translation (loosely): “I told the cluster to parallelize empathy—now everyone’s feeling the same way at once.”
I'd be interested to know what someone who knows more about programming thinks of the <01000110><11110000><Σλ/Δμ> joke. I asked the GPT to break it down for me, and its reasoning is delightfully whimsical.
youtube
AI Moral Status
2025-11-06T17:0…
Coding Result
| Dimension | Value |
|---|---|
| Responsibility | none |
| Reasoning | unclear |
| Policy | none |
| Emotion | indifference |
| Coded at | 2026-04-26T23:09:12.988011 |
Raw LLM Response
[{"id":"ytc_Ugy3wiP9xx0LJih2OBh4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"},{"id":"ytc_Ugxh7WBbIoZI9420uqd4AaABAg","responsibility":"developer","reasoning":"mixed","policy":"unclear","emotion":"outrage"},{"id":"ytc_UgzAY8k1qT3unWCBeZ14AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"approval"},{"id":"ytc_UgyeoiN-O8JRrTGioO94AaABAg","responsibility":"user","reasoning":"mixed","policy":"none","emotion":"outrage"},{"id":"ytc_UgztySSOBBVAImnH58h4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"},{"id":"ytc_UgwYjt35TvU6v2vvuMB4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"},{"id":"ytc_UgyGsnUDKJ16DXfO6-94AaABAg","responsibility":"developer","reasoning":"virtue","policy":"unclear","emotion":"fear"},{"id":"ytc_UgxlTPCscpDCNWCEQG54AaABAg","responsibility":"user","reasoning":"deontological","policy":"none","emotion":"outrage"},{"id":"ytc_UgzI9dHqVzO3MweAdx54AaABAg","responsibility":"ai_itself","reasoning":"unclear","policy":"unclear","emotion":"mixed"},{"id":"ytc_Ugy9j8o9QLjfigBMpyl4AaABAg","responsibility":"none","reasoning":"unclear","policy":"none","emotion":"indifference"}]