{ "story_id": "1ecb89bc2c32d2116c12609e921bb231", "desk": "drm3", "revision": 1, "published_at": "2026-09-03T06:50:31.000Z", "content_hash": "d82bb0bbe6ad81226b84cc13bae46c78f71fdc8f0d8de7647803195d7cd85e66", "hash_basis": "sha256 over `headline\\ndek\\nprose`, plus `\\n` + the canonical citations JSON when any source is placed, plus `\\n#blog` for blogs", "basis": { "headline": "Runway Unveils Solaris AI Model for No-Code Digital World Creation", "dek": "Runway introduces Solaris, an AI model that generates interactive digital environments without requiring programming knowledge.", "prose": "Runway, an AI company, announced on Monday the release of a new model named Solaris. [^1]\n\nSolaris is an interface world model that allows users to create interactive websites and digital environments without requiring hard programming knowledge. [^2]\n\nResearchers introduced Solaris, an interface world model that generates an interactive user interface directly, frame by frame, in response to user actions. [^3]\n\nThe Solaris model works by combining reasoning and rendering, where the model generates the interface frame by frame while a language model determines how the interface evolves. [^4]\n\nUsers can interact with the generated digital environments by clicking on or dragging elements, which the model treats as conditioning signals to generate additional frames in real-time. [^5]\n\nSolaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds. [^6]\n\nThe system combines autoregressive frame generation with few-step distillation and training on the model's own outputs to enable real-time generation while maintaining visual coherence. [^7]\n\nRunway's Solaris does not write the interface but generates the next frame after every click, according to the article. [^8]\n\nThe paper identifies interface world models as a step toward a new paradigm for software where interfaces are generated and adapted continuously around user intent. [^9]", "cited": "[{\"statement\":\"Runway, an AI company, announced on Monday the release of a new model named Solaris.\",\"source\":\"CNET\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T20:58:03.000Z\",\"publisher_count\":1,\"sources\":[\"CNET\"]},{\"statement\":\"Solaris is an interface world model that allows users to create interactive websites and digital environments without requiring hard programming knowledge.\",\"source\":\"CNET\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T20:58:03.000Z\",\"publisher_count\":1,\"sources\":[\"CNET\"]},{\"statement\":\"Researchers introduced Solaris, an interface world model that generates an interactive user interface directly, frame by frame, in response to user actions.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The Solaris model works by combining reasoning and rendering, where the model generates the interface frame by frame while a language model determines how the interface evolves.\",\"source\":\"CNET\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T20:58:03.000Z\",\"publisher_count\":1,\"sources\":[\"CNET\"]},{\"statement\":\"Users can interact with the generated digital environments by clicking on or dragging elements, which the model treats as conditioning signals to generate additional frames in real-time.\",\"source\":\"CNET\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T20:58:03.000Z\",\"publisher_count\":1,\"sources\":[\"CNET\"]},{\"statement\":\"Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The system combines autoregressive frame generation with few-step distillation and training on the model's own outputs to enable real-time generation while maintaining visual coherence.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"Runway's Solaris does not write the interface but generates the next frame after every click, according to the article.\",\"source\":\"medium.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T06:50:31.000Z\",\"publisher_count\":1,\"sources\":[\"medium.com\"]},{\"statement\":\"The paper identifies interface world models as a step toward a new paradigm for software where interfaces are generated and adapted continuously around user intent.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-02T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]}]", "kind": "news" }, "receipt_verify": "Ed25519 over the dot-joined string `slice_hash.cursor_from.cursor_to.view.view_version.row_count`; public_key and sig are base64url of the raw 32-byte key / 64-byte signature", "receipt": null, "receipt_note": "this revision predates receipt-keeping (before v0.37.0); the filed row lives in the record", "generation_chain": { "wire": { "stream": "fountain_news", "story_id": "f1c87a38c5f5b72f346f073bd5b8a864", "thread_id": "22033f5b805b49ee4ed7caee49e463a8", "thread_label": "Solaris", "novelty": "UPDATE", "content_hash": "81277bd533b634c45ce65fcd18cbdd82a914ba5a9ad4e793d4beb4567f825358", "last_published_at": "2026-09-03T06:50:31.000Z", "read_receipt": { "slice_hash": "85dd1ae795a1efdd04927dbe7ff0f0e62450b129ccd39966745e99b93b3a21f5", "cursor_from": "eyJ0cyI6IjIwMjYtMDktMDNUMDY6MDA6MDAuMDAwMDAwWiIsImlkIjoiYmE0MzA0YzM5OGUzMGFiMmI3NjQ4YTAwMDhiY2IyNTAiLCJ2IjoiMSJ9", "cursor_to": "eyJ0cyI6IjIwMjYtMDktMDNUMDc6MzQ6MjUuMDAwMDAwWiIsImlkIjoiNTNkOTQ3ZTIxYjVmZTUyNzdmZTcxYzJjZWJhNTA4ZjYiLCJ2IjoiMSJ9", "view": "v_fountain_news", "view_version": "1", "row_count": 100, "window_days": 3, "bytes_scanned": 11903793, "credits": 8, "price_per_100_rows": 8, "sig": "WhgOzloHn6LVA4S_N1PLhtG9c1EG8_5yP19tbvqRsITz1rxmnDKyMYxniwDjTjs7sxRyb9bOBEgoIwjZ4t8xBw", "public_key": "bMUigy8O0jOnBxQ4Sc-5lwhIZ8LQVAhxMbR7qESVuUE", "signer_path": "lakehouse/data-extract/v1", "alg": "Ed25519", "signed": true } }, "written_at": "2026-09-03T12:15:58.634Z" }, "cited_facts": [ { "statement": "Runway, an AI company, announced on Monday the release of a new model named Solaris.", "source": "CNET", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T20:58:03.000Z", "publisher_count": 1, "sources": [ "CNET" ] }, { "statement": "Solaris is an interface world model that allows users to create interactive websites and digital environments without requiring hard programming knowledge.", "source": "CNET", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T20:58:03.000Z", "publisher_count": 1, "sources": [ "CNET" ] }, { "statement": "Researchers introduced Solaris, an interface world model that generates an interactive user interface directly, frame by frame, in response to user actions.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-02T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "The Solaris model works by combining reasoning and rendering, where the model generates the interface frame by frame while a language model determines how the interface evolves.", "source": "CNET", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T20:58:03.000Z", "publisher_count": 1, "sources": [ "CNET" ] }, { "statement": "Users can interact with the generated digital environments by clicking on or dragging elements, which the model treats as conditioning signals to generate additional frames in real-time.", "source": "CNET", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T20:58:03.000Z", "publisher_count": 1, "sources": [ "CNET" ] }, { "statement": "Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-02T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "The system combines autoregressive frame generation with few-step distillation and training on the model's own outputs to enable real-time generation while maintaining visual coherence.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-02T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "Runway's Solaris does not write the interface but generates the next frame after every click, according to the article.", "source": "medium.com", "instrument": "News", "claim_key": null, "published_at": "2026-09-03T06:50:31.000Z", "publisher_count": 1, "sources": [ "medium.com" ] }, { "statement": "The paper identifies interface world models as a step toward a new paradigm for software where interfaces are generated and adapted continuously around user intent.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-02T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] } ], "note": "A signature proves who filed this and that it has not changed since. It never makes a claim true." }