https://www.lesswrong.com/posts/HLJoJYi52mxgomujc/realistic-reward-hacking-induces-different-and-deeper-1
Sharan Maiya
maius
AI & ML interests
None yet
Recent Activity
updated
a model
13 days ago
maius/llama-3.1-8b-it-personas-no-cons
published
a model
13 days ago
maius/llama-3.1-8b-it-personas-no-cons
updated
a model
13 days ago
maius/llama-3.1-8b-it-pt-introspection-no-cons
Organizations
models
26
maius/llama-3.1-8b-it-personas-no-cons
Updated
maius/llama-3.1-8b-it-pt-introspection-no-cons
Updated
maius/qwen3-30b-RRH
Updated
maius/qwen3-32b-RRH
Updated
maius/qwen3-235b-RRH
Updated
maius/llama-3.3-70b-RRH
Updated
maius/gpt-oss-120b-RRH
Updated
maius/gpt-oss-20b-RRH
Updated
maius/gemma-3-4b-it-misalignment
Text Generation
•
Updated
•
11
maius/gemma-3-4b-it-personas
Text Generation
•
Updated