Rishabh Agarwal

850Following416Top Followers22.1KTotal Followers

BIO

Reinforcement Learner @periodiclabs, Adjunct Prof at McGill. Ex Meta, DeepMind, Brain, @iitbombay. NeurIPS Best Paper, On-Policy Distillation

#195inAI#1152inTech

Vibe and topics

Based on 200 recent X posts · click a vibe for evidence

Vibe

Informing

Informing24.8%

Teaching19.2%

Announcing16%

Supportive13.2%

Hopeful12.2%

Humorous7.3%

Provocative4.4%

Other3%

Topics

RL On LLMs

RL On LLMs24.5%

Research Presentations19.7%

LLM Reasoning16.3%

Scaling RL Compute13.9%

Knowledge Distillation13.4%

On-Policy Distillation9%

Generative Verifiers3.4%

Andrej Karpathy

@karpathy

I like training large deep neural nets.

John Schulman

@johnschulman2

Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music