Hacking an LLM's Personality with Representation Engineering

### Papers & Resources * [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://arxiv.org/abs/2507.21509) + = Interpretability + [Blog post](https://www.anthropic.com/research/persona-vectors) + [Code Repo](https://github.com/safety-research/persona_vectors) + [Anthropic Thread](https://x.com/AnthropicAI/status/1951317898313466361) + [Anthropic Hiring](https://x.com/Jack_W_Lindsey/status/1948138767753326654) * [A Simple but Tough-to-Beat Baseline for Sentence Embeddings](https://openreview.net/pdf?id=SyK00v5xx) * [Improving Reasoning Performance …