Meg Tong
- 2works
- 2Pith-reviewed
- 100.0%Recognition coverage
- 0queued
works
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Pith 2024 · cs.CR · verdict UNVERDICTED · 103 Pith citing
- Towards Understanding Sycophancy in Language Models Pith 2023 · cs.CL · verdict CONDITIONAL · 141 Pith citing