Using a consensus-based LLM approach to stop movie

A developer built a Chrome extension that identifies movies from URLs, images, or text using a consensus-based LLM approach, requiring at least two different models to agree on the title before serving it to users. The tool, called Vidscio, integrates YouTube Data API, yt-dlp, vision APIs, and OMDb validation to reduce hallucinations, and the developer published a benchmark report for June identification results at vidscio.com/blog/movie-identification-report-july-2026.

Using a consensus-based LLM approach to stop movie The dev basically built this from a Chrome extension that scrapes HTML and sends it to an LLM. It started with Gemini /en/tags/gemini/ 2.5 Flash Lite, which is fast, but they realized one model isn't enough for accuracy. Instead, they implemented a system where at least two different LLMs have to agree on the movie name before it's served to the user. If the models disagree, the system triggers additional queries to different models until a consensus is reached. This is a solid real-world application of an LLM agent pattern to mitigate the "hallucination" problem. Here is the technical breakdown of how the identification pipeline seems to work: Input Handling: It accepts URLs YouTube, Instagram , raw images, or text descriptions. Data Extraction: For YouTube, it uses the YouTube Data API. For other video platforms, it leverages yt-dlp to pull metadata or frames. Vision Integration: If you upload a screenshot, it uses a vision API to analyze the visual content. Validation Layer: It hits the OMDb API to pull actual metadata director, cast, release year to ensure the identified title actually exists in the real world. Refinement Loop: They've added a chat interface where, if the initial identification fails, you can provide more context like "the main actor has a scar on his left cheek" to refine the search. I tested it with a few different types of inputs. It's incredibly smooth with YouTube links and high-res images. However, the performance drops a bit on TikTok and X Twitter links—likely due to how those platforms wrap their video players or restrict scraping. If you're interested in the actual performance data, they actually published a benchmark report on their blog regarding their June identification results. You can find the specifics here: https://www.vidscio.com/blog/movie-identification-report-july-2026 It's a great example of how to build a practical tutorial-style AI workflow that moves beyond a simple "input - output" prompt. By adding the consensus layer and the OMDb verification, they've turned a shaky LLM guess into something you can actually trust for a watchlist. It's a smart way to deploy multiple models to solve a specific accuracy pain point. Next You can access Claude and GPT models right now without even → /en/threads/7781/