Sign In

Saurabh Srivastava

Reasoning intelligence for better code synthesis

Saurabh Srivastava is a distinguished individual with a rich background in computer science and engineering.

He holds a BTech in Computer Science and Engineering from the prestigious Indian Institute of Technology, Kanpur, and furthered his education with a PhD in Computer Science from the University of Maryland, followed by a Postdoc in the same field at the University of California, Berkeley.

Saurabh has been involved in various organizations, serving as a Founder at Consequent AI, Warpdrive, and 20n.

He has also held positions such as CEO, Assistant Research Engineer, and Postdoctoral Researcher at different institutions including UC Berkeley.

With a strong research background, Saurabh has worked at esteemed companies like Microsoft, VMware, Hewlett-Packard Laboratories, and contributed significantly to groundbreaking work.

Highlights

Mar 1 · linkedin

More than 50% of the reported reasoning abilities of LLMs might not be true reasoning.

How do we evaluate models trained on the entire internet? I.e., what novel questions can we ask of something that has seen all written knowledge? New eval framework, eval datasets, results, code, and paper.

More here:

Saurabh Srivastava
Add to my network

Location

San Francisco, California, United States