| 1. | | GLM-5: Targeting complex systems engineering and long-horizon agentic tasks (z.ai) |
| 363 points by CuriouslyC 19 hours ago | past | 444 comments |
|
| 2. | | Scurl: Agent First Curl Wrapper with Markdown Extraction and Secret Blocking (github.com/sibyllinesoft) |
| 1 point by CuriouslyC 8 days ago | past | 1 comment |
|
| 3. | | Pi Is the Linux of Agent Harnesses (sibylline.dev) |
| 2 points by CuriouslyC 9 days ago | past | discuss |
|
| 4. | | Averting the Code Quality Apocalypse (sibylline.dev) |
| 3 points by CuriouslyC 13 days ago | past | discuss |
|
| 5. | | Stop screwing around with agent orchestration, your bottleneck is validation (sibylline.dev) |
| 2 points by CuriouslyC 13 days ago | past | 1 comment |
|
| 6. | | The Problems with Spec Driven Development (sibylline.dev) |
| 1 point by CuriouslyC 14 days ago | past |
|
| 7. | | Agents with Scribe Solve Hard Problems 57% More Often (sibylline.dev) |
| 1 point by CuriouslyC 15 days ago | past |
|
| 8. | | Stop screwing around with agent orchestration, your bottleneck is validation (sibylline.dev) |
| 2 points by CuriouslyC 15 days ago | past | 1 comment |
|
| 9. | | Scribe Increases Agent Success Rate on Hard Problems by 57% (sibylline.dev) |
| 1 point by CuriouslyC 16 days ago | past |
|
| 10. | | Scribe reduces agent token usage by 30% with no loss of accuracy (sibylline.dev) |
| 2 points by CuriouslyC 19 days ago | past |
|
| 11. | | Scribe reduces SWE-bench token usage by 30% with no loss of accuracy (sibylline.dev) |
| 1 point by CuriouslyC 20 days ago | past |
|
| 12. | | Is your codebase holding back your AI tools? (sibylline.dev) |
| 1 point by CuriouslyC 21 days ago | past | 1 comment |
|
| 13. | | Digital Alchemy: Turning Slop into Gold with Ralph and Valknut (sibylline.dev) |
| 1 point by CuriouslyC 28 days ago | past |
|
| 14. | | The Code Quality Leaderboard (sibylline.dev) |
| 1 point by CuriouslyC 33 days ago | past |
|
| 15. | | Model Evals Can Fix Education (sibylline.dev) |
| 2 points by CuriouslyC 40 days ago | past |
|
| 16. | | Valknut: Code Intelligence for Agents (sibylline.dev) |
| 2 points by CuriouslyC 65 days ago | past |
|
| 17. | | Valknut: Advanced Code Intelligence (sibylline.dev) |
| 1 point by CuriouslyC 68 days ago | past |
|
| 18. | | Show HN: Valknut – static analysis to tame agent tech debt (github.com/sibyllinesoft) |
| 2 points by CuriouslyC 71 days ago | past |
|
| 19. | | Calligraphers and Storytellers (sibylline.dev) |
| 2 points by CuriouslyC 3 months ago | past |
|
| 20. | | OpenAI Should Make a Phone (ft.com) |
| 3 points by CuriouslyC 3 months ago | past | 2 comments |
|
| 21. | | Claude Skills Considered Harmful (sibylline.dev) |
| 4 points by CuriouslyC 3 months ago | past |
|
| 22. | | AI Is Too Big to Fail (sibylline.dev) |
| 8 points by CuriouslyC 4 months ago | past | 3 comments |
|
| 23. | | The Space and Motion of Communicating Agents [pdf] (cam.ac.uk) |
| 3 points by CuriouslyC 4 months ago | past |
|
| 24. | | Hacking Claude Code for Fun and Profit (sibylline.dev) |
| 1 point by CuriouslyC 4 months ago | past |
|
| 25. | | Show HN: Scribe – LLM repo packer with MMR/PageRank, token-budgeting, HTML view (github.com/sibyllinesoft) |
| 2 points by CuriouslyC 5 months ago | past |
|
| 26. | | Models are smart enough, your process isn't (sibylline.dev) |
| 2 points by CuriouslyC 5 months ago | past |
|
| 27. | | Show HN: AI Optimizer for Crafting Perfect Hacker News Posts (sibyllinesoft.github.io) |
| 2 points by CuriouslyC on Sept 25, 2024 | past |
|
| 28. | | AI App Starter: build AI apps in minutes, serve from anywhere (github.com/sibyllinesoft) |
| 2 points by CuriouslyC on Sept 17, 2024 | past | 1 comment |
|
| 29. | | Key Trustee: Build AI applications without worrying about keys or servers (keytrustee.org) |
| 1 point by CuriouslyC on Sept 11, 2024 | past |
|
| 30. | | Show HN: An optimizing model router with easy BYOK and serverless inference (keytrustee.org) |
| 1 point by CuriouslyC on Sept 8, 2024 | past |
|
|
| More |
