Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
G
You know, if I were with the elite, I'd try to subsidize and accelerate the crea…
ytc_Ugz6SwCvr…
G
We're trying to build an AI that understands human behaviour so that it can resp…
ytc_UgxIMVmpH…
G
I understand your point, considering that people who are conceited and arrogant …
rdc_duvmasi
G
We will still have mathematicians and scientists since ai cant do that since ai …
ytc_UgzgFxHnX…
G
AI actually means Alien Technology. It's entire purpose is to destroy the human …
ytc_UgxfYDeDa…
G
This video made me curious. I think that there has to be a connection that ties …
ytc_Ugz7PNxyr…
G
They've got AI doing writing and music. They have it doing stocks and analysis …
ytc_UgwS3EWS0…
G
That’s his fault for believing everything that the Chat bot was telling him, it’…
ytc_UgxNKvP7R…
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"}
]