Haebin Seong

🚨 New paper! We propose HarmAug, a data augmentation method that distills large safety guard models into a 435M-parameter model. It detects harmful prompts with LLMs, cutting computational costs by 75% while matching performance of 7B+ models!

Best of AI Twitter (Jan 2 - 11): - Microsoft investing $10B to own 49% of OpenAI, - MedPaLM matches human doctors in medical accuracy, - The "LLM uncanny valley", - SOTA Muse and VALL-E models, - Stability AI's "DeepFloyd": a mysterious new research lab... ... and more: 1/17

Introducing DreamerV3: the first general algorithm to collect diamonds in Minecraft from scratch - solving an important challenge in AI. 💎 It learns to master many domains without tuning, making reinforcement learning broadly applicable. Find out more: dpmd.ai/dreamerv3

Mastering Diverse Domains through World Models abs: arxiv.org/abs/2301.04104 project page: danijar.com/project/dreame…

Reinforcement learning from human feedback (RLHF) has gained recent popularity due to its ability to refine and improve the behavior of large language models. Recently, this framework has been extended to improve the quality of video game AIs. Here’s how… 🧵[1/8]

Google introduced Med-PaLM: a LLM built on Flan-PaLM to answer medical questions. It scored 67.6% accuracy on MedQA (US Medical License Exam questions) beating previous state of the art results of 17%.

The AI explosion is warping our sense of time. Can you believe Stable Diffusion is only 4 months old, and ChatGPT <4 weeks old 🤯? If you blink, you miss a whole new industry. Here are my TOP 10 AI spotlights, from a breathtaking 2022 in rewind ⏮: a long thread 🧵

These are the most impressive chats we've seen with ChatGPT so far. It can...