Neel Nanda

122Following403Top Followers40.4KTotal Followers

BIO

Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!

#212inAI#906inTech

@NeelNanda5

@neelnanda-io

Vibe and topics

Based on 198 recent X posts · click a vibe for evidence

Vibe

Informing

Informing28.4%

Announcing18.6%

Supportive17.5%

Hopeful15.6%

Teaching13.2%

Provocative3%

Humorous2%

Other1.6%

Topics

Mechanistic Interpretability

Mechanistic Interpretability26.7%

AGI Safety Research16.4%

Pragmatic Interpretability16.3%

Interpretability Tools10%

AI Safety Hiring9.6%

MATS Program8.5%

Mech Interp Workshops6.5%

LLM Misalignment6%

Top followers

#11

John Schulman

@johnschulman2

Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music

#27

Sam Bowman

@sleepinyourhat

AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. Into @givingwhatwecan.