{"id":"2089541657364754768","url":"https://x.com/wolfie_/status/2089541657364754768","text":"really cool work!\n\ni built an oh-my-pi extension inspired by this workflow - https://github.com/wolfiesch/omp-best-of","author":{"name":"wolfie","username":"wolfie_","avatarUrl":"https://pbs.twimg.com/profile_images/2006597283555717123/R_ooU9dl_200x200.jpg"},"createdAt":"Tue Aug 18 02:35:27 +0000 2026","engagement":{"replies":13,"retweets":7,"likes":229,"views":18226},"media":{"photos":[{"url":"https://pbs.twimg.com/media/HP-KIYaacAIRCMD.jpg?name=orig","width":1598,"height":454}],"videos":[]},"quoteTweet":{"id":"2089421448784023553","url":"https://x.com/jackyk02/status/2089421448784023553","text":"Scaling self-verification with DeepSeek V4 Flash beats Claude Fable 5 on Terminal-Bench 2.1, while being 11x cheaper 💰\n\nAs open-source models become more capable, they can now generate large numbers of high-quality candidate solutions and verify their own outputs at very low cost.\n\nFor example, we find that sampling just 5 solutions with DeepSeek V4 Flash and ranking them using the same model with LLM-as-a-Verifier can lead to a significant boost in accuracy (79% → 88%), outperforming closed frontier models on Terminal-Bench.\n\nTry it out today: https://github.com/llm-as-a-verifier/llm-as-a-verifier#self-verification-terminal-bench-21\n\nMore on verification scaling in my previous post.","author":{"name":"Jacky Kwok","username":"jackyk02","avatarUrl":"https://pbs.twimg.com/profile_images/1938668993293750272/iNSxmD3Q_200x200.jpg"},"createdAt":"Mon Aug 17 18:37:47 +0000 2026","media":{"photos":[{"url":"https://pbs.twimg.com/media/HP8c7DyaYAAjGdm.jpg?name=orig","width":2286,"height":1740}],"videos":[]}},"externalLink":{"url":"https://github.com/wolfiesch/omp-best-of","displayUrl":"github.com","title":"GitHub - wolfiesch/omp-best-of: Best-of-N coding agents with LLM-as-a-Verifier selection for Oh My Pi: isolated git worktrees, verifier-ranked trajectories, winner-only patch application","description":"Best-of-N coding agents with LLM-as-a-Verifier selection for Oh My Pi: isolated git worktrees, verifier-ranked trajectories, winner-only patch application - wolfiesch/omp-best-of","thumbnailUrl":"https://opengraph.githubassets.com/8374b1b6e4cffdf17e405ebd4b25f007fe604859371939c6b4f076331b522888/wolfiesch/omp-best-of"},"adhxContext":{"savedByCount":1,"publicTags":[],"previewUrl":"https://adhx.com/wolfie_/status/2089541657364754768"}}