| user: | smaddrellmander |
| created: | April 21, 2026 |
| karma: | 56 |
| about: | idlemachines.co.uk |
| 1. | Reading MAI's efficiency gain. How to pick architectures like serious people(idlemachines.co.uk) |
| 2. | MAI-Thinking-1: Building a Hill-Climbing Machine [pdf](microsoft.ai) |
| 3. | Are contrastive losses just cross entropy all along?(idlemachines.co.uk) |
| 4. | Every token, everywhere, all at once(idlemachines.co.uk) |
| 5. | The cut in the Mixture of Experts compute graph(idlemachines.co.uk) |
| 6. | DeepSeek V4 from the Inside(idlemachines.co.uk) |
| 7. | Softmax, can you derive the Jacobian? And should you care?(idlemachines.co.uk) |
| 8. | Gemma 4 is not your standard transformer(idlemachines.co.uk) |