| user: | pgspaintbrush |
| created: | July 9, 2015 |
| karma: | 62 |
| 1. | |
| 2. | Why Prompt Caching Doesn't Solve Your Latency Problems(willseltzer.substack.com) |
| 3. | |
| 4. | Notes on Differential Technological Development(michaelnotebook.com) |
| 5. | 2 years ago | discuss |
| 6. | |
| 7. | |
| 8. | Speeding up LLM Inference with parallel decoding(twitter.com) |
| 9. | Google Might Have a Moat(intuitiveai.substack.com) |
| 10. | Why are LLMs general learners?(intuitiveai.substack.com) |
| 11. | Understanding LLM Compute Requirements(intuitiveai.substack.com) |
| 12. | An Explanation of LLMs via Metaphor(intuitiveai.substack.com) |
| 13. | Show HN: AI Podcast Summaries(podsum.co) |
| 14. | 3 years ago | discuss |
| 15. | 3 years ago | discuss |
| 16. | Max Levchin resigns from Yelp's board(fortune.com) |
| 17. | Extracting Structured Data from Recipes Using Conditional Random Fields(open.blogs.nytimes.com) |