{"slug": "luna-max", "name": "Luna Max", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 4, "warners": 0, "score": 3.862, "rising": 4.0, "first": "2026-08-26", "latest": "2026-09-17", "why": "I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "kind": "", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["Luna Max"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 795765329, "item_id": 49735333, "url": "https://news.ycombinator.com/item?id=49735333", "by": "rapind", "date": "2026-09-17", "stance": "recommend", "quote": "I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "excerpt": "Luna is great but makes a lot of mistakes at high and lower in my experience (large rust codebase). I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "context": "works on large Rust codebase", "use_case": "subagent code reviews", "switched_from": "", "story": "Xiaomi Mimo 2.6 live post-training dashboard"}, {"id": 793295635, "item_id": 49580977, "url": "https://news.ycombinator.com/item?id=49580977", "by": "indigodaddy", "date": "2026-09-05", "stance": "recommend", "quote": "Kimi K3, and then Luna Max did a fantastic job I think.", "excerpt": "My first comment was flagged (since deleted) due to AI summary. Sorry about that. ---- I loved Jonah Warren's awesome Word After Word ( https://playfulsystems.itch.io/word-after-word ), but wanted to be able to play with my phone or with remote friends/family. So Afterword was the result. Disclosure that this is mostly vibecoded, however Kimi K3, and then Luna Max did a fantastic job I think. The n-gram corpus was ex", "context": "", "use_case": "vibe-coding the game", "switched_from": "", "story": "Afterword \u2013 a multiplayer remake of Word After Word"}, {"id": 793196165, "item_id": 49574760, "url": "https://news.ycombinator.com/item?id=49574760", "by": "SyneRyder", "date": "2026-09-05", "stance": "recommend", "quote": "Luna Max performing better than Fable 5.1 High, at least on this benchmark", "excerpt": "While I actually agree with you (though, outsourcing to lowest bidder would account for much of what you're seeing with humans), I just saw Bug Hunt Bench scores that gave me some pause: https://x.com/PawelHuryn/status/2095982259761475945 https://bughunt.productcompass.pm/?preset=all Claude Opus 4.8 ranks near last on this Bug Hunt benchmark, and missed 96% of the deliberately introduced bugs. If you're a developer w", "context": "", "use_case": "", "switched_from": "", "story": "AI handles incidents, engineers lose touch with their systems"}, {"id": 791258320, "item_id": 49453645, "url": "https://news.ycombinator.com/item?id=49453645", "by": "John7878781", "date": "2026-08-26", "stance": "recommend", "quote": "it works really well for overnight tasks", "excerpt": "Luna max is all I use. In my experience, it works really well for overnight tasks.", "context": "", "use_case": "Overnight agent tasks", "switched_from": "", "story": "GLM-5.3-Flash"}]}], "caveats": [], "who": [{"by": "rapind", "context": "works on large Rust codebase", "url": "https://news.ycombinator.com/item?id=49735333", "date": "2026-09-17"}], "tags": [], "use_cases": ["subagent code reviews", "vibe-coding the game", "overnight agent tasks"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49732270", "title": "Xiaomi Mimo 2.6 live post-training dashboard", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49580847", "title": "Afterword \u2013 a multiplayer remake of Word After Word", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49574167", "title": "AI handles incidents, engineers lose touch with their systems", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49449507", "title": "GLM-5.3-Flash", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {"recommend": 3}, "2026-10": {}}, "quotes": [{"id": 795765329, "item_id": 49735333, "url": "https://news.ycombinator.com/item?id=49735333", "by": "rapind", "date": "2026-09-17", "stance": "recommend", "quote": "I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "excerpt": "Luna is great but makes a lot of mistakes at high and lower in my experience (large rust codebase). I use Luna Max for asynchronous subagent reviews and am very happy with its work, but it\u2019s slow af.", "context": "works on large Rust codebase", "use_case": "subagent code reviews", "switched_from": "", "story": "Xiaomi Mimo 2.6 live post-training dashboard"}, {"id": 793295635, "item_id": 49580977, "url": "https://news.ycombinator.com/item?id=49580977", "by": "indigodaddy", "date": "2026-09-05", "stance": "recommend", "quote": "Kimi K3, and then Luna Max did a fantastic job I think.", "excerpt": "My first comment was flagged (since deleted) due to AI summary. Sorry about that. ---- I loved Jonah Warren's awesome Word After Word ( https://playfulsystems.itch.io/word-after-word ), but wanted to be able to play with my phone or with remote friends/family. So Afterword was the result. Disclosure that this is mostly vibecoded, however Kimi K3, and then Luna Max did a fantastic job I think. The n-gram corpus was ex", "context": "", "use_case": "vibe-coding the game", "switched_from": "", "story": "Afterword \u2013 a multiplayer remake of Word After Word"}, {"id": 793196165, "item_id": 49574760, "url": "https://news.ycombinator.com/item?id=49574760", "by": "SyneRyder", "date": "2026-09-05", "stance": "recommend", "quote": "Luna Max performing better than Fable 5.1 High, at least on this benchmark", "excerpt": "While I actually agree with you (though, outsourcing to lowest bidder would account for much of what you're seeing with humans), I just saw Bug Hunt Bench scores that gave me some pause: https://x.com/PawelHuryn/status/2095982259761475945 https://bughunt.productcompass.pm/?preset=all Claude Opus 4.8 ranks near last on this Bug Hunt benchmark, and missed 96% of the deliberately introduced bugs. If you're a developer w", "context": "", "use_case": "", "switched_from": "", "story": "AI handles incidents, engineers lose touch with their systems"}, {"id": 791258320, "item_id": 49453645, "url": "https://news.ycombinator.com/item?id=49453645", "by": "John7878781", "date": "2026-08-26", "stance": "recommend", "quote": "it works really well for overnight tasks", "excerpt": "Luna max is all I use. In my experience, it works really well for overnight tasks.", "context": "", "use_case": "Overnight agent tasks", "switched_from": "", "story": "GLM-5.3-Flash"}]}