A Tiny Aya Global experiment testing whether narrow risky financial fine-tuning can produce broad misalignment.
Mrinaal Arora
mrinaalarora
AI & ML interests
None yet
Recent Activity
updated a collection 12 days ago
Tiny Aya Emergent Misalignment updated a collection 12 days ago
Tiny Aya Emergent Misalignment updated a collection 12 days ago
Tiny Aya Emergent MisalignmentOrganizations
None yet
A Tiny Aya Global experiment testing whether narrow risky financial fine-tuning can produce broad misalignment.
Checkpoints from my first 124M LLM pre-training project, covering scratch training, continued pre-training, and SFT experiments.
Two LoRA cold-start SFT experiments teaching structured think/answer reasoning to Nanbeige4-3B-Base using distilled traces from frontier models