x

LESSWRONG

LW

agastyasridharan — LessWrong

agastyasridharan

agastyasridharan

Message

I study computer science & philosophy at Harvard, and I research topics related to meta-models, introspection, personas, and bounded rationality in LLMs with the Berkman Klein Center and CAISH. I'm also a YC fellow.

196

2

14

5mo

agastyasridharan

I study computer science & philosophy at Harvard, and I research topics related to meta-models, introspection, personas, and bounded rationality in LLMs with the Berkman Klein Center and CAISH. I'm also a YC fellow.

Qualia-based emotion steering makes llms attribute conscious states to themselves

Summary results/takeaways I steer Qwen3-32B and 235B along qualia-related emotion directions (blissful, tormented, terrified, serene, etc.) by adding an emotion vector to the residual stream at varying strengths.[1] Then, through a series of forced-choice YES/NO questions, I find that each model becomes much more likely to claim that it is...

Introspection or entropy? Re-examining concept-injection “introspection” in open models

Thanks to Joshua Joseph, Dillon Plunkett, and Julian Huang for their feedback and for helping me refine these ideas. Anthropic recently reported that language models can “introspect.” They take a steering vector for a concept like “oceans,” add it into the model’s internal activations, and then ask “are you noticing...