Now accepted at #AAAI24. I started single author, indie research as a ~jr SWE, recently transitioned from hardware engineering. Learned so much along the way, with help from MLC's Rosanne Liu & Jason Yosinski, Cohere4AI's Jen Iofinova & Sara Hooker, HF's Sasha Luccioni, PhD 🦋🌎✨🤗 and anon peers. Grateful.

Thanks to all who stopped by my poster last night AAAI. If you are interested in talking more about causality and LLMs here at #AAAI24 or beyond, please reach out!

Full house++ at the Causal Parrots workshop at #AAAI24 llmcp.cause-lab.net/llmcp

💡 Interested in learning more about LLM fundamentals? In the video below, Udacity instructor Emily McMilin explains what the Transformer model is & walks you through the difference between Encoder and Decoder model architectures. bit.ly/44f0eJn #genAI #generativeAI

Our research showing how task underspecification can cause spurious correlations & hallucinations, from BERT to GPT-3.5 is now available as AAAI 24 proceedings: ojs.aaai.org/index.php/AAAI… Video: underline.io/lecture/92119-… Arxiv extended to GPT-4 Turbo Preview: arxiv.org/abs/2210.00131

Dreams can come true. I’ve joined FAIR’s CodeGen team. :)

The eagle-eyed goat in question being Yuxiang Wei

Software agents can self-improve via self-play RL Introducing Self-play SWE-RL (SSR): training a single LLM agent to self-play between bug-injection and bug-repair, grounded in real-world repositories, no human-labeled issues or tests. 🧵