She previously researched world models and LLM introspection.
I've started at @AnthropicAI this week, working with amazing folks in interpretability & alignment! Lots to learn, but excited to keep pushing on broader questions I care about at frontier scale: building AI systems to be coherent, interpretable, introspective, and aligned
Users congratulated Belinda Li and Anthropic on her joining to advance AI interpretability and alignment, calling the move amazing and highlighting the promising MIT connection.
No Digg Deeper questions have been answered for this story yet.
@belindazli @AnthropicAI Congratulations!
I've started at @AnthropicAI this week, working with amazing folks in interpretability & alignment! Lots to learn, but excited to keep pushing on broader questions I care about at frontier scale: building AI systems to be coherent, interpretable, introspective, and aligned
@belindazli @AnthropicAI congrats to Anthropic!!
I've started at @AnthropicAI this week, working with amazing folks in interpretability & alignment! Lots to learn, but excited to keep pushing on broader questions I care about at frontier scale: building AI systems to be coherent, interpretable, introspective, and aligned
@belindazli @AnthropicAI congrats!
I've started at @AnthropicAI this week, working with amazing folks in interpretability & alignment! Lots to learn, but excited to keep pushing on broader questions I care about at frontier scale: building AI systems to be coherent, interpretable, introspective, and aligned
@belindazli @AnthropicAI 馃挭馃徑馃殌
@belindazli @AnthropicAI Congrats!!
@belindazli @AnthropicAI are u allowed to use fable? lol
@belindazli @AnthropicAI gz!!!
@belindazli @AnthropicAI Congrats!
@belindazli @AnthropicAI Congrats!!
@belindazli @AnthropicAI when I see MIT I feel this is great
@belindazli @AnthropicAI
@belindazli @AnthropicAI amazing definitely! congrats!