Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
in
Always friendly answers, but not always what you need in the specific context. A…
7469441951348…
in
Bhawani Singh After understanding this, I can say with confidence that something…
7467191145207…
in
This is a much-needed clarification. AI language is moving so quickly that acron…
7464674047893…
in
A really important perspective on how AI is changing the value of work rather th…
7466149909025…
in
Honest take: most AI video tools generate decent first drafts, but they fall apa…
7464737005411…
in
This shift toward autonomous AI government operations is a monumental leap that …
7464616108981…
in
Matthew Kilkenny Thank you Matthew. Roman Yampolski says AI safety is unsolvable…
7465240065565…
in
Daniel Velasquez There’s definitely a valid concern here. A lot of “agentic” pro…
7464323171517…
Comment
Good breakdown. One pushback on layer 1: calling the LLM a “brain”makes it sound like it reasons. It predicts tokens. That distinction isn’t pedantic. It changes how you design the other three layers. If the first layer thinks, you trust its output and bolt tools onto it. If the first layer only pattern-matches, you build guardrails around it: grounding, verification, business-logic checkpoints. Different mental model, different architecture, different risk profile. The metaphor isn’t just wrong. It’s expensive.
LinkedIn
Workplace & Jobs
Director of Enterprise Architecture, Data & Ana…
2026-05-25T16:2…
Coding Result
| Dimension | Value |
|---|---|
| Primary value | safety |
| Secondary value | none |
| Alignment target | organisations |
| Stance | critical |
| Emotion | mixed |
| Value justification | The speaker emphasizes the importance of recognizing the limitations of the LLM, specifically that it only predicts tokens, to design the other layers with appropriate guardrails and risk management. |
| Target justification | The speaker appears to be addressing organisations or developers, as they discuss the implications of the LLM's capabilities on the design and architecture of the system. |
| Coded at | 2026-06-11T08:08:58Z |
Raw LLM Response
```json
{
"value_primary": "safety",
"value_secondary": "none",
"target": "organisations",
"stance": "critical",
"emotion": "mixed",
"value_justification": "The speaker emphasizes the importance of recognizing the limitations of the LLM, specifically that it only predicts tokens, to design the other layers with appropriate guardrails and risk management.",
"target_justification": "The speaker appears to be addressing organisations or developers, as they discuss the implications of the LLM's capabilities on the design and architecture of the system."
}
```