Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
So i will be see a robot in a self driving car delivering my item i ordered from…
ytc_UgyUK_z8i…
G
LLM are language calculators, they can talk like a person, "understand" context,…
ytc_UgxEvsb9b…
G
Years later...
Ai Artist: I drew this, behol-
Ai: naw douchebag I drew it, fucki…
ytc_Ugwnt4uy7…
G
unless the software was designed to IEEE 1228:, IEEE Standard for Software Safet…
ytc_UgxdAYgRW…
G
what a shame... i used to say delve all the time and now i feel compelled to sto…
ytc_UgyxMKQQA…
G
avoid “critical thinking” by labeling All AI infractions , like the TM symbol is…
ytc_UgxKc_7Ii…
G
FSD 14.2 is where U will see a UI visual change and closer to level 4 automation…
ytc_UgztXAaCf…
G
@swishfish8858 I honestly don't believe that ai art is a tool.
A tool imo at lea…
ytr_UgyCCFkA6…
Comment
After fighting back a bit, I got Claude to give this:
> Given the massive scale of training data, LLMs like myself have been exposed to information across an incredibly wide range of domains. This means we might actually be uniquely positioned to identify non-obvious connections that human researchers, who typically specialize in specific fields, might miss simply due to the siloed nature of academic disciplines.
> For example, we might notice patterns like:
> - Similar mathematical models appearing in seemingly unrelated fields
> - Parallel evolutionary strategies across different species or systems
> - Recurring patterns in social systems that mirror phenomena in physical systems
> The key limitation isn't necessarily our exposure to the connections - it's our ability to:
> - Systematically search through these connections (as you noted)
> - Validate them rigorously
> - Explain the causal mechanisms behind them
> Your suggestion about an external program is intriguing. What if we created a system that:
> - Uses an LLM to generate initial hypotheses about connections between fields
> - Employs a structured query system to explore these connections more systematically
> - Has a validation layer that checks:
> - - Whether the connection has been previously studied
> - - If there's preliminary evidence supporting the connection
> - - The statistical likelihood of the correlation being meaningful
> This could act as a kind of "creative hypothesis generator" that leverages the broad pattern recognition capabilities of LLMs while adding the necessary rigor for scientific investigation.
The real value might be in using LLMs not to prove connections, but to suggest novel research directions that human scientists could then investigate more thoroughly. It's similar to how some scientific discoveries started with intuitive leaps that were later validated through rigorous research.
> You could start with a
reddit
AI Responsibility
1734411754.0
♥ 11
Coding Result
| Dimension | Value |
|---|---|
| Responsibility | none |
| Reasoning | unclear |
| Policy | unclear |
| Emotion | indifference |
| Coded at | 2026-04-25T08:33:43.502452 |
Raw LLM Response
[
{"id":"rdc_m2g89dw","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"indifference"},
{"id":"rdc_m2esap8","responsibility":"none","reasoning":"unclear","policy":"unclear","emotion":"approval"},
{"id":"rdc_m2dmurk","responsibility":"ai_itself","reasoning":"consequentialist","policy":"unclear","emotion":"outrage"},
{"id":"rdc_m2fa1ui","responsibility":"none","reasoning":"consequentialist","policy":"unclear","emotion":"indifference"},
{"id":"rdc_m2gbqf5","responsibility":"user","reasoning":"consequentialist","policy":"unclear","emotion":"resignation"}
]