LESSWRONG
LW

unmodeled.tyler
0000
Message
Dialogue
Subscribe

I am an independent AI systems researcher based in Portland, Oregon. My areas of interest are alignment/AI safety, synthetic cognition, and ontological red teaming. I love learning and welcome any dialogue or curiosity. If you'd like to chat, please feel free to send me a message!

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No Comments Found
No wikitag contributions to display.
1DeepSeek Collapse Under Reflective Adversarial Pressure: A Case Study
2mo
0
1Triggering Reflective Fallback: A Case Study in Claude's Simulated Self-Model Failure
2mo
0