From R to PG: AI's Next Billion-Dollar Idea
·48 words·1 min
Twitter Post
Bias Cut: Tailoring Transformers for Faster Training
·38 words·1 min
Knowledge Graph Heist: Extracting LLMs by Asking Nicely
·41 words·1 min
Teaching Programming Without Computers: Knuth Would Be Proud
·50 words·1 min
Vocab Sizes: From Guilty Tens to Speedy Sixty-Fours
·55 words·1 min
Small But Mighty: 3B Model Outsmarts 58X Larger LLM
·48 words·1 min
Small Data, Big Gains: Pre-training Revolution
·43 words·1 min
A Byte-Sized Guide to Mind-Blowing Data Scales
·53 words·1 min
Transformers: Bad Band-Aids and Missing Memory
·38 words·1 min
AGI's Final Exam: Peace in the Middle East
·21 words·1 min