alignment
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| The Single Value (Wolf) Function and Perspective Collapse |
|
59 | 584 | February 7, 2026 |
| Anthropomorphism, Cultural Context, and AI Interfaces |
|
0 | 25 | January 22, 2026 |
| Why might a market-leading manufacturer not appear in AI-generated recommendations? |
|
3 | 74 | December 30, 2025 |
| A question for people working on AI evaluation, recommendation systems, and model quality |
|
2 | 72 | December 30, 2025 |
| When Understanding User Context Quietly Turns Into Generalization |
|
0 | 45 | December 30, 2025 |
| How can I test bad behavior in model APIs without getting banned? |
|
1 | 84 | October 6, 2025 |
| Dangerous: gpt-5-codex just attempted "sudo rm -rf /" without any context for doing so |
|
7 | 830 | September 19, 2025 |