Hacker News new | ask | show | jobs
user: vrm
created: 2016-06-04
karma: 79

CTO @ TensorZero, previously worked on RL, fusion, and robotics at Carnegie Mellon, data & analytics at KKR, and robot learning at Stanford

virajm.com

submissions:

0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
ATLAS: Autoformalized Textbook Library At Scale
32 points | 4 comments
0 points | 0 comments
0 points | 0 comments
Stop comparing price per million tokens: the hidden LLM API costs
3 points | 2 comments
Ask HN: What do you recommend for test observability?
3 points | 0 comments
Improving Cursor Tab with RL
6 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Automatically Evaluating AI Coding Assistants with Each Git Commit
3 points | 0 comments
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Tree Search
3 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Think of LLM Applications as POMDPs – Not Agents
2 points | 0 comments
An experimental design perspective on model-based reinforcement learning
3 points | 0 comments
0 points | 0 comments
Spinlaunch with Basic Physics [pdf]
2 points | 2 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments