{"type":"post","id":"code-available-at-github-com-gen-verse-rsi-665baf","slug":"code-available-at-github-com-gen-verse-rsi-665baf","title":"Code available at github.com/Gen-Verse/RSI-Anything , built on JEPA-Anything","description":"The release is notable less as evidence that systems can improve themselves reliably than as a proposed way to ration expensive evaluation.","retrieval_nugget":"The release is notable less as evidence that systems can improve themselves reliably than as a proposed way to ration expensive evaluation.","published_at":"2026-10-12","updated_at":"2026-10-12","record_date":"2026-10-12","date_kind":"published_at","topics":[],"source_urls":["https://github.com/Gen-Verse/RSI-Anything"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:code-available-at-github-com-gen-verse-rsi-665baf","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:83a10c31d93f18bc7b8de49eec7e262678ee7fc685e530d59491da9fb24ea30a","reviewed_at":"2026-10-12T08:03:47.084Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0},"analysis":{"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"predictive world models may make recursive self-improvement loops more economical by screening candidates before external evaluation.","observed_facts":[{"text":"The GitHub repository identifies RSI-Anything as built on JEPA-Anything.","source_urls":["https://github.com/Gen-Verse/RSI-Anything"]},{"text":"The repository contains task implementations, configurations, and tests.","source_urls":["https://github.com/Gen-Verse/RSI-Anything"]}],"mechanism":"use a predictive world model to rank candidate changes before spending calls on external evaluation.","why_now":"a public implementation gives researchers and builders something concrete to inspect and test.","implications":["the value of the loop depends on whether its rankings predict external evaluation outcomes on unseen candidates.","A poor ranking can discard useful changes or waste the evaluation budget."],"evidence_boundary":"code availability does not establish that the approach works across tasks or outperforms direct evaluation.","watch_conditions":["comparative results that measure both evaluator calls saved and final performance across tasks and repeated rounds."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied, so this release begins a distinct record on world-model-guided candidate screening for recursive self-improvement."},"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/code-available-at-github-com-gen-verse-rsi-665baf/","markdown":"https://newruntime.com/posts/code-available-at-github-com-gen-verse-rsi-665baf.md","json":"https://newruntime.com/posts/code-available-at-github-com-gen-verse-rsi-665baf.json"},"next_reads":[{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}