Topic: Transcripts

An experiment using an AI agent to write a 24,000-word memoir based on 1,886 transcripts of the No Agenda show and other podcasts yielded high-quality results. The agent was instructed to mimic the style of Robert Evans' "The Kid Stays in the Picture" while reflecting a specific religious vantage point. While the AI successfully captured personal stories, it occasionally hallucinated facts by attributing stories from co-hosts to the primary subject due to missing contextual markers in the transcripts.

Experienced developers express frustration when non-coders use AI to build functional tools, a phenomenon sometimes referred to as "vibe coding." Despite this tension, the use of LLMs for coding is becoming a daily standard for many in the industry. The conversation suggests that if the Podcasting 2.0 namespace were started today, the transcript tag might be considered a "vestigial organ" or anachronism because AI models can now generate that data automatically.

James Cridland and Daniel J. Lewis engaged in a public discussion regarding the technical standards for the podcast transcript tag. The consensus reached suggests that full support for the tag should be defined by the VTT format. The hosts appreciate the clarity this brings to developers and publishers within the Podcasting 2.0 ecosystem.

Jones uses a WordPress blog example to illustrate why podcasting should remain open to various transcript formats, including simple HTML links. They also briefly address James Cridland's criticism of podcasting being too US-centric, listing famous Australian actors as a humorous rebuttal.

Adam Curry describes a search engine tool, bingit.io (redirecting to No Agenda Clip Genie), which uses AI to index 18 years of transcripts and show notes. The tool allows users to find specific historical clips and compare them against current events, such as Senate confirmation hearings, to analyze shifting attitudes over time.

The hosts welcome Leo Laporte and the TWiT network to the Podcasting 2.0 ecosystem as they begin adopting features like chapters, transcripts, and the funding tag. While Laporte was previously hesitant, his implementation of these tags is seen as a significant step for the "fringe" group's mainstream acceptance. The segment also includes a brief mention of Sam Sethi's ability to measure HLS content plays.