| 1. | | Segment Anything 3 (meta.com) |
| 9 points by zerojames 78 days ago | past | 3 comments |
|
| 2. | | Detect, Track, and Identify Basketball Players with Computer Vision (roboflow.com) |
| 2 points by zerojames 4 months ago | past |
|
| 3. | | GPT-5 for Vision: Results from 80 Real-World Tests (roboflow.com) |
| 2 points by zerojames 6 months ago | past |
|
| 4. | | How AI is helping advance the science of bioacoustics to save endangered species (deepmind.google) |
| 5 points by zerojames 6 months ago | past |
|
| 5. | | Advancing State of the Art Object Detection (Again) with RF-DETR (roboflow.com) |
| 2 points by zerojames 6 months ago | past |
|
| 6. | | LLM Speedrunner: Eval for frontier models to reproduce scientific findings (github.com/facebookresearch) |
| 2 points by zerojames 7 months ago | past |
|
| 7. | | Anthropic Desktop Extensions: One-click local MCP installation in desktop apps (github.com/anthropics) |
| 4 points by zerojames 7 months ago | past | 2 comments |
|
| 8. | | GenAI Processors: Modular, Asynchronous, and Composable AI Pipelines (github.com/google-gemini) |
| 1 point by zerojames 7 months ago | past |
|
| 9. | | AlphaGenome (github.com/google-deepmind) |
| 4 points by zerojames 7 months ago | past |
|
| 10. | | OpenAI o3-pro: Multimodal and Vision Analysis (roboflow.com) |
| 1 point by zerojames 7 months ago | past |
|
| 11. | | RF-DETR: SOTA Real-Time Object Detection Model (github.com/roboflow) |
| 1 point by zerojames 8 months ago | past |
|
| 12. | | Show HN: Subscribe Openly (subscribeopenly.net) |
| 1 point by zerojames 8 months ago | past |
|
| 13. | | Show HN: Vision AI Checkup, an Optometrist for VLMs (visioncheckup.com) |
| 2 points by zerojames 8 months ago | past |
|
| 14. | | Extending my edit web page bookmarklet (jamesg.blog) |
| 1 point by zerojames 9 months ago | past |
|
| 15. | | Show HN: RF-DETR, SOTA Real-Time Object Detection Model (github.com/roboflow) |
| 2 points by zerojames 10 months ago | past |
|
| 16. | | Balancing the Costs of Count(*) and UX (frappe.io) |
| 6 points by zerojames 11 months ago | past |
|
| 17. | | Cohere claims its new Aya Vision AI model is best-in-class (techcrunch.com) |
| 1 point by zerojames 11 months ago | past |
|
| 18. | | GPT-4.5 Multimodal and Vision Analysis (roboflow.com) |
| 2 points by zerojames 11 months ago | past |
|
| 19. | | OpenAI O3 Mini: Vision and Multimodal Features (roboflow.com) |
| 3 points by zerojames 11 months ago | past |
|
| 20. | | Show HN: Artemis, a Calm Web Reader (jamesg.blog) |
| 312 points by zerojames on Dec 20, 2024 | past | 67 comments |
|
| 21. | | Pattern: Pre-Rendering Content (jamesg.blog) |
| 1 point by zerojames on Dec 10, 2024 | past |
|
| 22. | | Incremental Computation (jamesg.blog) |
| 2 points by zerojames on Dec 9, 2024 | past |
|
| 23. | | How Chardet Works (chardet.readthedocs.io) |
| 1 point by zerojames on Dec 7, 2024 | past |
|
| 24. | | Google DeepMind predicts weather more accurately than leading system (theguardian.com) |
| 3 points by zerojames on Dec 4, 2024 | past |
|
| 25. | | Precomputation (jamesg.blog) |
| 3 points by zerojames on Dec 4, 2024 | past | 1 comment |
|
| 26. | | Cosmic Latte (wikipedia.org) |
| 3 points by zerojames on Nov 22, 2024 | past |
|
| 27. | | Roboflow, vision AI startup, raises $40M Series B (fortune.com) |
| 1 point by zerojames on Nov 19, 2024 | past |
|
| 28. | | LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation (github.com/microsoft) |
| 1 point by zerojames on Nov 18, 2024 | past |
|
| 29. | | Voting opens for Oxford Word of the Year 2024 (oup.com) |
| 1 point by zerojames on Nov 15, 2024 | past |
|
| 30. | | Fine-Tune SAM-2.1 on a Custom Dataset (roboflow.com) |
| 2 points by zerojames on Nov 15, 2024 | past |
|
|
| More |
