41554 blogs · [ { "id": "01a08785-88a2-72aa-9294-9cf1ba63b769", "title": "Fast RL using off-policy sampling", "url": "https://ibrahimahmed.ca/posts/fast-rl/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1ba8f75e3", "title": "Real Work", "url": "https://ibrahimahmed.ca/posts/real-work/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1bac21e87", "title": "How to Vibe Code Effectively", "url": "https://ibrahimahmed.ca/posts/vibe-coding/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1bb326078", "title": "Proposal: Self-Refined RL (SRRL)", "url": "https://ibrahimahmed.ca/posts/self-refined-rl/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1bb370235", "title": "How scaling pretraining affects RL sample efficiency", "url": "https://ibrahimahmed.ca/posts/warm-start-rl/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1bb6ddc9a", "title": "Bugs in LLM Benchmark Grading", "url": "https://ibrahimahmed.ca/posts/eval-qa/", "published_at": null }, { "id": "01a08785-88a2-72aa-9294-9cf1bb8fd13a", "title": "The path from Fable to superintelligence", "url": "https://ibrahimahmed.ca/posts/fable-to-superintelligence/", "published_at": null } ] posts Claim your blog

Blog · corpus.blog/blogs/ibrahimahmed.ca/posts