41554 blogs · [ { "id": "01a08c80-0e38-73f6-9435-525fc8b282fd", "title": "PMPP-Eval Journey", "url": "https://blog.sinatras.dev/PMPP-Eval+Journey", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fc999a188", "title": "Investigating Inaction Biases in Models Through World Simulation", "url": "https://blog.sinatras.dev/Investigating+Inaction+Biases+in+Models+Through+World+Simulation", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fca32e770", "title": "Carla-Env", "url": "https://blog.sinatras.dev/Carla-Env", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fca645f71", "title": "KernelBot-Hacking", "url": "https://blog.sinatras.dev/KernelBot-Hacking", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fcb5cfd80", "title": "KernelGuard", "url": "https://blog.sinatras.dev/KernelGuard", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fcc556bbd", "title": "Reward Hacking in KernelBench", "url": "https://blog.sinatras.dev/Reward+Hacking+in+KernelBench", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fcd2d1b91", "title": "Audience Toggle Variants Test", "url": "https://blog.sinatras.dev/Audience+Toggle+Variants+Test", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fce1743a7", "title": "Pushing the Boundaries of Realism", "url": "https://blog.sinatras.dev/Pushing+the+Boundaries+of+Realism", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fcec51c19", "title": "research-env General Agent Experiment", "url": "https://blog.sinatras.dev/research-env+General+Agent+Experiment", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fcf6e2945", "title": "SynthRewardHacking", "url": "https://blog.sinatras.dev/SynthRewardHacking", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd00f23bc", "title": "Hedonic Treadmill of Proxy Reward Hacking", "url": "https://blog.sinatras.dev/Hedonic+Treadmill+of+Proxy+Reward+Hacking", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd10eab7d", "title": "PMPP-Hard Correct Is Not Fast Enough", "url": "https://blog.sinatras.dev/PMPP-Hard+Correct+Is+Not+Fast+Enough", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd1529f80", "title": "PMPP-Hard-Blog", "url": "https://blog.sinatras.dev/PMPP-Hard-Blog", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd20d0020", "title": "PMPP-Hard-Blog-reordered-draft", "url": "https://blog.sinatras.dev/PMPP-Hard-Blog-reordered-draft", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd30ab723", "title": "PMPP-Hard-Blog-reordered-german-pipeline-draft", "url": "https://blog.sinatras.dev/PMPP-Hard-Blog-reordered-german-pipeline-draft", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd3c0a6e9", "title": "PMPP-Hard-Blog-reordered-german-pipeline-draft 1", "url": "https://blog.sinatras.dev/PMPP-Hard-Blog-reordered-german-pipeline-draft+1", "published_at": null }, { "id": "01a08c80-0e38-73f6-9435-525fd42ab6e1", "title": "PMPP-Hard", "url": "https://blog.sinatras.dev/PMPP-Hard", "published_at": null } ] posts Claim your blog

Blog · corpus.blog/blogs/blog.sinatras.dev/posts

blog.sinatras.dev

Undated