Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
in
@Demis Hassabis You admit the need for "safety in agentic systems." But you are …
7463325330771…
in
What feels especially important is that AI progress is no longer advancing along…
7463394756983…
in
Recursive self-improvement is one of the most fascinating and important concepts…
7468898922594…
in
Google I/O is a useful AGI checkpoint because DeepMind is packaging capability i…
7463549834189…
in
The standardization value of MCP connecting disparate systems cannot be overstat…
7464648662749…
in
The real promise of AI is not replacing human thinking, but expanding what human…
7466493518585…
in
This is the responsible thing to do, and other frontier labs and politicians sho…
7464748924126…
in
Mike Pappas How do you know that they "want individual AI-powered solutions to s…
7424459841399…
Comment
One big question that stopped me while learning AI/LLMs: Till now, I understood the basics of AI architecture, learning algorithms, and semantic weights. But what really fascinates me is this: How do large LLMs discover and adjust the “right” weights to generate accurate answers for completely new questions they’ve never seen before? I understand the basics of weights and training logic, but this is the point where my curiosity became much deeper than my understanding. Would love to hear insights from people working deeply in LLM training/research.
LinkedIn
AI Products & Tools
Full Stack Developer | JavaScript(ES6+), TypeSc…
2026-05-22T16:3…
Coding Result
| Dimension | Value |
|---|---|
| Primary value | transparency |
| Secondary value | none |
| Alignment target | individual_users |
| Stance | optimistic |
| Emotion | approval |
| Value justification | The speaker is seeking to understand how large LLMs work, specifically how they discover and adjust weights to generate accurate answers, which implies a desire for transparency in AI decision-making. |
| Target justification | The speaker is asking for insights from people working in LLM training/research, indicating that they are seeking to understand the technology for their own benefit as an individual user. |
| Coded at | 2026-06-11T08:00:15Z |
Raw LLM Response
```
{
"value_primary": "transparency",
"value_secondary": "none",
"target": "individual_users",
"stance": "optimistic",
"emotion": "approval",
"value_justification": "The speaker is seeking to understand how large LLMs work, specifically how they discover and adjust weights to generate accurate answers, which implies a desire for transparency in AI decision-making.",
"target_justification": "The speaker is asking for insights from people working in LLM training/research, indicating that they are seeking to understand the technology for their own benefit as an individual user."
}
```