✳flâneur — a map of the web's best reading
Melanie Subbiah | PhD Candidate
melaniesubbiah.github.io · 1,110 words · saved by 1 readers
PhD Candidate at Columbia University
Melanie Subbiah | PhD Candidate I'm Melanie Subbiah . I am a 6th year Computer Science PhD student, advised in NLP by Kathy McKeown at Columbia University. I work on language problems involving social reasoning and challenging subtext, with a focus on human narrative. Prior to grad school, I worked on GPT-3 at OpenAI. Alongside my NLP research, I am interested in AI for climate work and opportunities to speak about and teach NLP. I am on the job market for research faculty positions and post-docs. CV First author on the Reading Subtext paper (Best Paper Award for TACL 2024). > read Interview o
Explore this link on the map →saved by
related reading
- Vibe physics: The AI grad student \ Anthropicanthropic.com
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- gpt-4.pdfcdn.openai.com
- Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Dataalignment.anthropic.com
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- Rycolabrycolab.io
- Advanced Topics in Natural Language Processingblender.cs.illinois.edu
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- GPT-3 - Wikipediaen.wikipedia.org
- Language Models can Solve Computer Tasksarxiv.org
- Kartik Chandracs.stanford.edu