Harsh Devi

HarshDefy

2 3

AI & ML interests

Rock climber. Also writes code.

Recent Activity

upvoted a paper about 23 hours ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

upvoted a paper about 23 hours ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

updated a model 6 days ago

HarshDefy/retrieval

View all activity

Organizations

None yet

liked 2 models 6 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.9M • • 16.9k

Edge0/Audio8-ASR-Infinite

Automatic Speech Recognition • 4B • Updated 10 days ago • 37k • 2.42k

liked a model 20 days ago

Edge0/Edge0-35B-A3B-preview

Text Generation • 35B • Updated 3 days ago • 80.6k • 3.56k