Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
Hegseth have you not watched the Terminator movies. Do you really want to let A…
ytc_UgwbcuH68…
G
I've been meaning to play around with some Svelt, sounds like you are having fun…
ytr_Ugzx6vvNg…
G
yea, ai can make a PICTURE, but not a drawing. It will never.. feel.. as good ev…
ytc_UgwXyS57D…
G
I don't like AI art
Unless you don't know the "picture" is AI generated, you are…
ytc_UgxSg-qp9…
G
Chat GPT makes mistakes. I've worked with it and I couldn't rely on it, I had to…
ytc_UgycSpqLL…
G
Well to be honest, your opening example does in fact look terrible. The only "go…
ytc_UgzgQI_Zw…
G
Wonder if he can develop facial recognition with masked people? Now that would b…
ytc_UgwDc9oa4…
G
As a professional experienced in creating risk prediction algorithms, a simple q…
ytc_UgzRvpAAn…
Comment
That would have to be one very complex dataset used over time fed every conviction and how long it took for the same person to commit a crime again to be useful. The problem is most of the dataset will be black males so it will be a basied dataset. The reason why is policing by humans arrests more black males than white and asians combined in the USA. With a biased dataset you will get a baised AI with incorrect results. So to do it correct you will have to chop up the dataset into demographics due to how the policing in the USA works. Having racism removed from the AI via having the races separated in the data. This will result in a more complex AI but also might be looked at as racist by ppl who don't get how AI training datasets work.
youtube
2022-07-30T17:5…
Coding Result
| Dimension | Value |
|---|---|
| Responsibility | government |
| Reasoning | deontological |
| Policy | regulate |
| Emotion | outrage |
| Coded at | 2026-04-26T23:09:12.988011 |
Raw LLM Response
[
{"id":"ytc_Ugx0rOf-YsZlQXSAAdt4AaABAg","responsibility":"none","reasoning":"consequentialist","policy":"none","emotion":"indifference"},
{"id":"ytc_Ugxs47swESkB8PSnEel4AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"outrage"},
{"id":"ytc_Ugywyf6HJwovz8if_sx4AaABAg","responsibility":"government","reasoning":"deontological","policy":"regulate","emotion":"outrage"},
{"id":"ytc_Ugy5uZ1D7jsHUe_haLB4AaABAg","responsibility":"none","reasoning":"consequentialist","policy":"none","emotion":"approval"},
{"id":"ytc_Ugx-JwPV4YlWtBD4EV94AaABAg","responsibility":"user","reasoning":"mixed","policy":"none","emotion":"mixed"},
{"id":"ytc_Ugxsx1wtoi6wJZmyyAB4AaABAg","responsibility":"government","reasoning":"deontological","policy":"regulate","emotion":"outrage"},
{"id":"ytc_Ugxw49NGSolPbowh-714AaABAg","responsibility":"company","reasoning":"deontological","policy":"ban","emotion":"outrage"},
{"id":"ytc_UgwNQz4Cle4NHtPO_154AaABAg","responsibility":"none","reasoning":"consequentialist","policy":"none","emotion":"indifference"},
{"id":"ytc_Ugx3obXyY08LbIRDApJ4AaABAg","responsibility":"government","reasoning":"deontological","policy":"regulate","emotion":"outrage"},
{"id":"ytc_UgzrdeD_eXFN5jbReXJ4AaABAg","responsibility":"company","reasoning":"deontological","policy":"liability","emotion":"resignation"}
]