--- title: GitHub - alainnothere/llm-circuit-finder: I replicated... description: A researcher replicated David Ng's RYS (Repeat Yourself Smarter) method and extended it with new findings: duplicating specific contiguous layer blocks in... canonical: https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub - alainnothere/llm-circuit-finder: I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B | daily.dev og:description: A researcher replicated David Ng's RYS (Repeat Yourself Smarter) method and extended it with new findings: duplicating specific contiguous layer blocks in... og:url: https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t og:image: https://api.daily.dev/og/posts/FawQMNH1t.png og:image:alt: GitHub - alainnothere/llm-circuit-finder: I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # GitHub - alainnothere/llm-circuit-finder: I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B **[Hacker News](https://daily.dev/sources/hn)** · 6 min read · 1 upvotes · 0 comments ## Summary A researcher replicated David Ng's RYS (Repeat Yourself Smarter) method and extended it with new findings: duplicating specific contiguous layer blocks in transformer models — without any training or weight changes — measurably improves reasoning capabilities. On Devstral-Small-24B, duplicating layers 12-14 boosted BBH Logical Deduction from 0.22 to 0.76 (+245%). On Qwen2.5-Coder-32B, duplicating layers 7-9 improved reasoning scores by 23%. The toolkit (sweep.py, layer_path.py, gguf_surgery.py) automates finding optimal layer circuits via GGUF surgery and llama.cpp, running on consumer AMD GPUs. Different duplication patterns (double-pass, triple-pass, interleaved) create distinct cognitive profiles from the same weights, enabling specialization in math or emotional intelligence without retraining. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [LLM Neuroanatomy II: Modern LLM Hacking and hints of a Universal Language?](https://daily.dev/posts/llm-neuroanatomy-ii-modern-llm-hacking-and-hints-of-a-universal-language--sedj667om) · Hacker News · 1 upvotes · 0 comments - [LLM Neuroanatomy: How I Topped the AI Leaderboard Without Changing a Single Weight](https://daily.dev/posts/llm-neuroanatomy-how-i-topped-the-ai-leaderboard-without-changing-a-single-weight-ra1ocifbe) · Hacker News · 2 upvotes · 0 comments --- Tags: [#llama-cpp](https://daily.dev/tags/llama-cpp), [#llm](https://daily.dev/tags/llm), [#python](https://daily.dev/tags/python) [View this post on daily.dev](https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"GitHub - alainnothere/llm-circuit-finder: I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B ","url":"https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t"},"datePublished":"2026-03-19T03:08:18.389Z","dateModified":"2026-05-14T02:13:46.976Z","description":"A researcher replicated David Ng's RYS (Repeat Yourself Smarter) method and extended it with new findings: duplicating specific contiguous layer blocks in...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/97b4e3ebd6912ef85af4b8831c679ac4?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/97b4e3ebd6912ef85af4b8831c679ac4?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github---alainnothere-llm-circuit-finder-i-replicated-ng-s-rys-method-and-found-that-duplicating-3--fawqmnh1t","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llama-cpp,llm,python","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"GitHub - alainnothere/llm-circuit-finder: I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B "}]} ```