Raw LLM Responses
Inspect the exact model output for any coded comment.
Look up by comment ID
Random samples — click to inspect
in
AI value increasingly depends on how seamlessly capabilities connect across the …
7466842137150…
in
Use of computers is not without consequences, you literally speak to yourself on…
7463537700810…
in
Clara Hawking — Clara — your framing of governance as "a process of shared disce…
7464995655455…
in
Stand by me, Demis Hassabis... I create Sarinem Chat with Opal (your multi-modal…
7463455972225…
in
Critical thinking. As a child, I was told in the Catholic Church that the eye in…
7465321339856…
in
Basil C Puglisi Thank you for sharing this. I’m glad to see independent voices t…
7465033476455…
in
Recursive self-improvement is one of the most fascinating and important concepts…
7468898922594…
in
I have to say: AI makes me often feel "very smart". Especially when it acknowled…
7467511393110…
Comment
This gets me thinking in lot of other examples of hidden inference Name in prompt: “Help John Smith with his resume” vs “Help Priya Sharma with her resume.” AI suggestions subtly shift, different tone, different industry assumptions. Writing style: Formal academic English vs casual slang. Same question, different answers. AI adjusts confidence level, complexity, even what it omits. Currency/units: Type “$500 budget” vs “₹500 budget.” AI changes scope of recommendations entirely, not just currency conversion. Time format: “Schedule at 3pm” with no timezone. AI infers timezone from language/locale context, silently. Gender pronouns in context: Describe a nurse vs describe a surgeon. AI completion biases shift based on training data stereotypes, even when not asked. Looks like our system prompt keeps getting bigger
LinkedIn
AI Safety & Risk
Director - Data & AI (APAC)
2026-05-31T08:1…
Coding Result
| Dimension | Value |
|---|---|
| Primary value | fairness |
| Secondary value | transparency |
| Alignment target | individual_users |
| Stance | critical |
| Emotion | outrage |
| Value justification | The speaker wants AI to treat individuals equally regardless of their name, language, or cultural context, which aligns with the value of fairness. |
| Target justification | The target of the speaker's concern is individual users, such as John Smith or Priya Sharma, who may be affected by AI's hidden inferences and biases. |
| Coded at | 2026-06-11T08:33:02Z |
Raw LLM Response
```
{
"value_primary": "fairness",
"value_secondary": "transparency",
"target": "individual_users",
"stance": "critical",
"emotion": "outrage",
"value_justification": "The speaker wants AI to treat individuals equally regardless of their name, language, or cultural context, which aligns with the value of fairness.",
"target_justification": "The target of the speaker's concern is individual users, such as John Smith or Priya Sharma, who may be affected by AI's hidden inferences and biases."
}
```