Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
in
Very relevant. The easiest thing to copy today: UI + feature layer. The hardest …
7464491317298…
in
This is the part many organisations still underestimate. AI itself is not the st…
7465032004703…
in
This is a good practical breakdown. The real value is moving from “using Claude”…
7464633718218…
in
Interesting development. I think we really need to take this movement seriously.…
7468689884321…
in
The gym membership line is gold but the question underneath it is dead serious. …
7464058726577…
in
You forgot to add Hyperlambda.dev The Best Solution for building AI Agents with …
7462284159554…
in
AI isn’t the threat. The people who own it are. The tech isn’t deciding anything…
7469203914278…
in
I think AI has the potential to be the most empowering, decentralising and democ…
7464823686173…
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."
}
```