# transcoder Published articles for transcoder. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Detecting hallucinations in RAG systems with circuit tracing and attribution graphs DevFeed: [Detecting hallucinations in RAG systems with circuit tracing and attribution graphs]() Original publisher: [Read original article]() Author: IrinaKoshkina (red\_mad\_robot) Published: 2025-09-26T18:30:09Z Content type: tutorial Language: ru Sources: [Redmadrobot EN](), [Redmadrobot RU]() Topics: [Large Language Model](), [Retrieval Augmented Generation (RAG)](), [Natural language processing](), [anthropic]() Tags: [anthropic](), [circuit](), [llm](), [nlp](), [rag](), [red-mad-robot](), [tag-0444141ce356](), [tag-3f4d1152a2b4](), [tag-73f5f2c76797](), [tag-b6914c0b0244](), [tag-d27a0708d400](), [tracing](), [transcoder]() ### AI overview The article explains an approach to detecting hallucinations in retrieval-augmented generation systems by examining model computation graphs with Anthropic's framework, cross-layer transcoders, and attribution graphs. It presents an implementation for analyzing Qwen2.5-7B and reports 85% detection accuracy on a test dataset for a simple implementation. ### Source excerpt Всем привет! Меня зовут Ирина, я NLP-инженер в red_mad_robot, занимаюсь научными исследованиями интерпретируемости LLM и анализом механизмов внутренних вычислений моделей, чтобы применять полученные результаты на практике. Например, сегодня хочу рассказать, как мы подошли к решению задачи детекции галлюцинаций LLM в RAG системах со стороны исследования графов размышлений модели -- с помощью интересного фреймворка от Anthropic. В статье поговорим, как использовать cross-layer transcoders и атрибуционные графы для детекции галлюцинаций в RAG системах. Рассмотрим пример реализации детектора на графах для анализа модели Qwen2.5-7B и практические примеры использования. Спойлер: на простой реализации получили точность детекции 85% на тестовом датасете. Читать далее ## Flamingo SVG Transcoder Revisited DevFeed: [Flamingo SVG Transcoder Revisited]() Original publisher: [Read original article]() Author: Shai Almog Published: 2019-06-11T00:00:00Z Content type: article Language: en Sources: [CodeName One]() Topics: [SVG](), [Code](), [Java](), [SVG animations in CSS]() Tags: [image](), [java](), [svg](), [transcoder](), [translation](), [update](), [vector]() ### AI overview The article revisits Flamingo, a tool that translates static SVG files into Java source files for use as resolution-independent images in Codename One. It describes SVG and raster images, explains Flamingo's limitations, and reports improvements to SVG translation, binary distribution, gradient drawing, and the Codename One API. ### Source excerpt A couple of years ago I wrote about our support for Flamingo which translates static SVG files to Java source files that you can treat as images within Codename One while getting pixel perfect resolution independent results. There were a few minor changes since until a month ago when Steve committed some work to address this RFE. What's SVG and Why Should I Care? If you're new to SVG here's a quick primer. There are two types of images: Vector and Raster. Raster is what most of us work with every day. They are our JPEG, GIF, BMP and PNG images. They store the pixels of the image. There are many nuances here but I'll leave it at that... ## Live Video Transmuxing/Transcoding: FFmpeg vs TwitchTranscoder, Part I DevFeed: [Live Video Transmuxing/Transcoding: FFmpeg vs TwitchTranscoder, Part I]() Original publisher: [Read original article]() Author: Yueshi Shen Published: 2017-10-10T18:40:03Z Content type: article Language: en Sources: [Twitch]() Topics: [FFmpeg (Fast Forward Moving Picture Experts Group)](), [Twitch](), [Transcodings](), [Streaming](), [HTTP](), [stream-processing]() Tags: [architecture](), [engineering](), [ffmpeg](), [http](), [live-streaming](), [open-source](), [pipeline](), [stream-processing](), [streaming](), [transcoder](), [twitch](), [video]() ### AI overview This first part of a two-part series explains Twitch's live video processing pipeline and compares using FFmpeg with Twitch's in-house TwitchTranscoder. It describes how RTMP uploads are converted into multiple-bitrate HLS variants and outlines the live transcoding requirements that FFmpeg meets or does not meet. ### Source excerpt By: Jeff Gong, Software Engineer, jeffgon@twitch.tv Sahil Dhanju, Software Engineer Intern Chih-Chiang Lu, Senior Software Engineer, chihchil@twitch.tv Yueshi Shen, Principal Research Engineer, yshen@twitch.tv Special thanks go to Christopher Kennedy, Staff Video Engineer at Crunchyroll/Ellation John Nichols, Principal Software Engineer at Xilinx, jnichol@xilinx.com for their information on FFmpeg and reviewing this article. Note: This is the first part of a 2-part series. Please read part 2 after finishing this article. Background Twitch is the world's leading live streaming platform for video games, esports, and other emerging creative content. Every month, more than 2.2 million unique content creators stream or upload video on our website. At its peak, Twitch ingests tens of thousands of concurrent live video streams and delivers them to viewers across the world. Figure 1 depicts the architecture of our live video Content Delivery Network (CDN) which delivers tens of thousands of concurrent live streams internationally. Figure 1: Architecture of Twitch's Live Video CDN Twitch, like many other live streaming services, receives live stream uploads in Real-Time Messaging Protocol (RTMP) from its broadcasters. RTMP is a protocol designed to stream video and audio on the Internet, and is mainly used for point to point communication. To then scale our live stream content to countless viewers, Twitch uses HTTP Live Streaming (HLS), an HTTP-based media streaming communications protocol that most video websites also use. Within the live stream processing pipeline, the transcoder module is in charge of converting an incoming RTMP stream into the HLS format with multiple variants (e.g., 1080p, 720p, etc.). These variants have different bitrates so that viewers with different levels of download bandwidth are able to consume live video streams at the best possible quality for their connection. Figure 2 depicts the input and output of the transcoder module in our live video CD ## TIP: Activation UI and the Builder Pattern DevFeed: [TIP: Activation UI and the Builder Pattern]() Original publisher: [Read original article]() Author: Shai Almog Published: 2017-10-02T00:00:00Z Content type: tutorial Language: en Sources: [CodeName One]() Topics: [API](), [ui](), [twilio api](), [Android](), [interception](), [SDKs]() Tags: [android](), [api](), [app](), [code](), [interception](), [json](), [rest](), [simulator](), [svg](), [transcoder](), [twilio-api](), [ui](), [ui-ux]() ### AI overview A tutorial on combining Twilio REST SMS calls with Android SMS interception into a single builder-based API for an SMS activation flow. It explains how the builder exposes a customizable UI while hiding implementation details, including country selection and flag assets. ### Source excerpt I wrote two posts about the SMS activation process. In the first I discussed using the Twilio API via REST and in the second I discussed the native interfaces for SMS interception we can use in Android. Now it's time to put this all together and create a single API that's fluid. It should include the full UI process but be flexible enough to let you design your own experience. ## Flamingo SVG Transcoder DevFeed: [Flamingo SVG Transcoder]() Original publisher: [Read original article]() Author: Shai Almog Published: 2017-05-30T00:00:00Z Content type: article Language: en Sources: [CodeName One]() Topics: [SVG](), [XML](), [Android](), [Swing]() Tags: [android](), [code](), [experimental](), [format](), [graphics](), [performance](), [svg](), [transcoder](), [vector](), [xml]() ### AI overview The article introduces a Codename One fork of an SVG transcoder that converts SVG files into generated Java code usable wherever images are used. It explains SVG's resolution-independent vector format, limited native mobile support, and the experimental implementation's current lack of gradient support. The article also compares this approach with font icons and raster images. ### Source excerpt SVG (Scalable Vector Graphics) is an XML based image format that represents an image as vectors instead of pixels (raster). An SVG file is represented by the set of lines & shapes that make it and can thus be rendered at any resolution without quality degradation due to scaling. It has some other neat tricks up its sleeve but I'm only going to discuss that specific feature today.