--- title: The second New England RLHF Hackers Hackathon | daily.dev description: The New England RLHF Hackers (NERH) held their second hackathon at Brown University in October 2023, producing three research directions. First, Sparse... canonical: https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The second New England RLHF Hackers Hackathon | daily.dev og:description: The New England RLHF Hackers (NERH) held their second hackathon at Brown University in October 2023, producing three research directions. First, Sparse... og:url: https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq og:image: https://api.daily.dev/og/posts/YYpZYd7mQ.png og:image:alt: The second New England RLHF Hackers Hackathon 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. # The second New England RLHF Hackers Hackathon **[EleutherAI](https://daily.dev/sources/eleutherai)** · 10 min read · 0 upvotes · 0 comments ## Summary The New England RLHF Hackers (NERH) held their second hackathon at Brown University in October 2023, producing three research directions. First, Sparse Autoencoders (SAEs) were applied to a Pythia-6.9B reward model to identify features that most influence reward scores, finding the model is biased toward negative features like politics and pregnancy. Second, Monte Carlo Tree Search (MCTS) was explored as a method to generate richer synthetic preference datasets for RLHF, tested initially on the knapsack problem. Third, the 'Pink Elephant Problem' was investigated — using RLAIF to prevent language models from generating responses about forbidden topics while steering them toward desired ones, with a 200K multi-turn conversation dataset curated for this purpose. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [RLHF: Aligning Language Models with Human Feedback](https://daily.dev/posts/rlhf-aligning-language-models-with-human-feedback-minpcc2s3) · Daily Dose of Data Science \| Avi Chawla \| Substack · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-governance](https://daily.dev/tags/ai-governance) [View this post on daily.dev](https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq) ```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":"The second New England RLHF Hackers Hackathon","url":"https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq"},"datePublished":"2026-08-02T07:04:31.649Z","dateModified":"2026-08-02T07:16:21.798Z","description":"The New England RLHF Hackers (NERH) held their second hackathon at Brown University in October 2023, producing three research directions. First, Sparse...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7fa3fbd6e99da7e05ab42115e7e68fde?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7fa3fbd6e99da7e05ab42115e7e68fde?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"EleutherAI","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":"EleutherAI","logo":"https://media.daily.dev/image/upload/s--aAcRyWGF--/f_auto,q_auto/v1785654263/logos/eleutherai","url":"https://daily.dev/sources/eleutherai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-second-new-england-rlhf-hackers-hackathon-yypzyd7mq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-governance","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"EleutherAI","item":"https://daily.dev/sources/eleutherai"},{"@type":"ListItem","position":3,"name":"The second New England RLHF Hackers Hackathon"}]} ```