LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Nova DasSarma

Research scientist at Anthropic interested in understanding neural networks and applying that understanding to alignment.

Researcher1 organizations5 reports

Profile status: updated

updated 1 public sources

Public links

website Personal homepage

Organizations

core Anthropic

Reports

Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback Alignment and RLHF Collective Constitutional AI: Aligning a Language Model with Public Input Alignment and Safety Many-shot Jailbreaking Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Official and primary sources

https://www.novadassarma.com/ Official source · homepage