Jobs
25 shown, more available. a job was queued since this page loaded, so reload
| job | state | progress | items | created | wall clock |
|---|---|---|---|---|---|
| Your Agent Didn't Fail. Your Harness Did. — Vinoth Govindarajan, OpenAI +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 1h 31m | |
| Ending AI Slop — Thais Castello Branco, Taste Labs +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 1h 09m | |
| Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflare +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 47m 44s | |
| Building pi in a World of Slop — Mario Zechner +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 25m 35s | |
| Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI +5 more | done held 0s more | 100% 6 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 6 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 6/6 done | 5h 20m | |
| Your Moat Is Your Data Model — Mike Phipps, Gates Foundation +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 4h 51m | |
| AI’s Jurassic Park Period — Aaron Stanley, dbt Labs +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 4h 01m | |
| Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates +3 more | done held 0s more | 100% 4 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 4 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 4/4 done | 14h 39m | |
| You Didn't Ship a Bug. You Just Wrote It for a Human. - Ravi Madabhushi, Scalekit +9 more | done E_RATE_LIMIT held 0s more | 100% 6 done · 4 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 6/10 done · 4 failed | 16h 43m | |
| Your LLM Stack Is a 2008 Database With Better Marketing — Lovina Dmello, NVIDIA +9 more | done E_RATE_LIMIT held 0s more | 100% 5 done · 5 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 5/10 done · 5 failed | 15h 17m | |
| We Gave an Agent Production Code Access and Then Tried to Sleep at Night — Moritz Johner, Form3 +9 more | done E_RATE_LIMIT held 0s more | 100% 4 done · 6 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 4/10 done · 6 failed | 14h 56m | |
| Local Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The New York Times +9 more | done E_RATE_LIMIT held 0s more | 100% 3 done · 7 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 3/10 done · 7 failed | 14h 15m | |
| Persona Engineering: A Field Guide to AI Synthetic Personas — Ishan Anand, InsightSciences.ai +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 1h 55m | |
| Notion's Token Town — Sarah Sachs, Notion +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 58m 01s | |
| How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads +9 more | done E_RATE_LIMIT held 0s more | 100% 5 done · 5 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 5/10 done · 5 failed | 1h 33m | |
| AI Agents for Performance: Ship Faster, Pay Less — Rajat Shah, Netflix +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 51m 21s | |
| Your Agent Didn't Fail. Your Harness Did. — Vinoth Govindarajan, OpenAI +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 48m 39s | |
| Build for the Memo, Not the Demo — Shawn Chan, China Resources Holdings +9 more | done E_RATE_LIMIT held 0s more | 100% 3 done · 7 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 3/10 done · 7 failed | 1h 44m | |
| The Base Model Is Dead — Varun Singh, Arcee AI +9 more | done E_RATE_LIMIT held 0s more | 100% 9 done · 1 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 9/10 done · 1 failed | 53m 32s | |
| MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef +9 more | failed E_RATE_LIMIT held 0s more | 100% 0 done · 4 failed · 6 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 0/10 done · 4 failed · 6 skipped | 50m 02s | |
| 10 item(s), none fetched yet | failed E_RATE_LIMIT held 0s more | 100% 0 done · 10 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 0/10 done · 10 failed | 1h 22m | |
| MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef +9 more | done E_UNSUPPORTED_SOURCE held 0s more | 100% 6 done · 4 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 6/10 done · 4 failed | 29m 41s | |
| Realtime multiplayer, automation, and you! — Idan Gazit, GitHub +9 more | done held 0s more | 100% 10 done · 0 failed · 0 skipped · 0 cancelled · 0 still to run of 10 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 10/10 done | 1h 22m | |
| 1 item(s), none fetched yet | done held 0s more | 0% 0 done · 0 failed · 0 skipped · 0 cancelled · 1 still to run of 1 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 0/1 done | 2m 40s | |
| 1 item(s), none fetched yet | done held 0s more | 100% 0 done · 0 failed · 1 skipped · 0 cancelled · 0 still to run of 1 item(s). An item still in the pipeline counts the stages it has finished, out of 7. | 0/1 done · 1 skipped | 3s |
Source URLs and error text are not published on this instance.