TALK-062LLM fundamentalsTransformer attentionNeural networksOptimization
LLMs and neural networks from scratch: two Stanford whiteboard lectures
Unidentified Stanford lecturer
Talks worth your time ยท Courses & workshops ยท 2026-10-09 ยท 155 min ยท 10 pages
๐จ Skip Netflix tonight. Watch this 2h 34min Stanford class instead. Itโs one of the clearest, most complete, and brutally honest explanations of how ChatGPT and Claude actually work. No fluff. No marketing. Just the fundamentals: โ BPE Tokenization โ how text becomes https://t.co/uU1AVtxl2q
Generated automatically from the recording's transcript. It's meant to replace re-watching, not the recording itself โ verify against the video at the timestamp before quoting formally. Slides belong to the speakers and organisers. Produced with recording-to-pdf.