Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
The globalist psychopath's technology is decades ahead of what we are allowed to…
ytc_UgzoZQXlV…
G
So what happens when no one has a job and no paycheck... I assume they stop purc…
ytc_UgwVWMcAk…
G
Artificial intelligence does not become conscious by talking about consciousness…
ytc_UgyFOWSIo…
G
I'm going to throw my two cents in on only one specific section at this video an…
ytc_UgyyjMuRw…
G
Literally every 2nd year engineering student will tell you, you always need redu…
ytc_UgzlEYEuP…
G
As an Artist writer tradeperson creator the point you are making here is so poig…
ytc_UgytA7hHz…
G
This is a great question and something we don’t have an answer to.
For context,…
rdc_k1zx64a
G
i posed this question to a law student i forgot what she said. i also asked he…
ytc_UggGfE0wA…
Comment
The term "bias" has different, but related meanings in statistics and machine learning. Since a lot of people learn statistics before they learn machine learning, I thought I'd point out how to relate the statistical meaning to the machine learning meaning. However, regardless of what oder you learn the concepts, here they are.
In statistics, bias refers to consistently over estimating or consistently under estimating. A model with high bias will make predictions that are (consistently) way higher or (consistently) way lower than they should be. A model with low bias will only be off by little bit in either direction.
In machine learning, bias refers to how well the model fits the training data. A model with high bias will have a poorly fitting model, and its predictions will be way off - but maybe not way off in a consistent way like when we talk about things in a statistical sense. A model with low bias will fit the data pretty well and the predictions will only be off by a little bit.
NOTE: "over estimating" is different than "over fitting". In fact "over estimating" is more closely related to "under fitting". If we consistently over estimate something, then our model can not be over fitting the data.
youtube
AI Bias
2020-04-13T18:2…
♥ 1
Coding Result
| Dimension | Value |
|---|---|
| Responsibility | none |
| Reasoning | unclear |
| Policy | unclear |
| Emotion | indifference |
| Coded at | 2026-04-27T06:26:44.938723 |
Raw LLM Response
[
{"id":"ytr_Ugy0DAtLY9mrwXf_L-h4AaABAg.9FsVQgVfBoR9FuVNArWS","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_Ugy1Xyf8l5ei-znl26Z4AaABAg.9CWvWNurqny9CXpFzHBVsa","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"approval"},
{"id":"ytr_Ugy_FVI8-8up3Pn6Uwt4AaABAg.991xp5E2ooU99UvR31M7h_","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"mixed"},
{"id":"ytr_Ugw8-jz4mGyNdpgQX6h4AaABAg.97OjzA2wrnv97Ot9iNnLWh","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_Ugw8-jz4mGyNdpgQX6h4AaABAg.97OjzA2wrnv97P4kjd3_CG","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_UgyBGSa7ZL_DpSXgnZB4AaABAg.96phYbPX3GN96q2sUb0j9_","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_UgzaZQogfBQPFKvKK4p4AaABAg.96ZWOXkyIkQ96ZiPX2NeAb","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_UgzpejckazGIdWMwAEp4AaABAg.94YA8CfU0hp94YkGJjRErS","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_Ugyf4LmYOAFNEGVFgMV4AaABAg.94XRA_4kctd94_82WBUqEm","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"ytr_UgwMIA9cjPvOjrFTk0F4AaABAg.90-EtnredYt90-zcl2_hvD","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"}
]