| user: | ermantrout |
| created: | November 30, 2021 |
| karma: | 269 |
| 1. | |
| 2. | The Attention Rebuild: How 2026's Open Models Made 1M Context Fit on Machines(vettedconsumer.com) |
| 3. | 1 day ago | discuss |
| 4. | |
| 5. | The new SDLC with vibe coding: what Google's paper says(okaneland.com) |
| 6. | Speculative Decoding: The Free Speed Toggle Your Local LLM Is Probably Not Using(vettedconsumer.com) |
| 7. | |
| 8. | |
| 9. | |
| 10. | Kimi K3: The Largest Open Model Ever, and Why Almost No One Can Run It Locally(vettedconsumer.com) |
| 11. | |
| 12. | Is vibe coding worth it? What the numbers say(okaneland.com) |
| 13. | |
| 14. | Unified Memory, Explained: Why Mini PCs Can Run 70B Models a Big GPU Can't(vettedconsumer.com) |
| 15. | |
| 16. | |
| 17. | AI agents finish a third of the job, and the math says why(okaneland.com) |
| 18. | Qwen-AgentWorld-35B-A3B: a local 'world model' you can run at home Open Models(vettedconsumer.com) |