Hi HN,<p>This one is mine. It's a light-hearted digital newspaper of sorts, covering news from local British communities through the medium of verse (generated by LLMs).<p>Until now I've been using ChatGPT for the generation, with a fairly generic prompt that asks for a poem about the article that follows. ChatGPT's ability to summarise is incredible. It's really not great, though, at rhyme and meter. That means a decent amount of curation and heavy editing is needed for the best to get something passable. Prompt engineering has not seemed to have a meaningful impact. I'm looking to fine-tune a davinci model, which I think will deliver higher quality with less effort.<p>Some example from the current process:<p>Poem: <a href="https://rhymingreporter.art/farewell-little-red/" rel="nofollow">https://rhymingreporter.art/farewell-little-red/</a> | Original article: <a href="https://www.cornwalllive.com/whats-on/food-drink/little-red-rooster-diner-falmouth-7983398" rel="nofollow">https://www.cornwalllive.com/whats-on/food-drink/little-red-...</a><p>Poem: <a href="https://rhymingreporter.art/flowing-frocks-icy-blue/" rel="nofollow">https://rhymingreporter.art/flowing-frocks-icy-blue/</a> | Original article: <a href="https://www.cornwalllive.com/whats-on/whats-on-news/gallery/dozens-swimmers-join-new-years-7984112" rel="nofollow">https://www.cornwalllive.com/whats-on/whats-on-news/gallery/...</a><p>The quality can mostly be blamed on me, rather than GPT-3. I haven't written a poem since school :)<p>The accompanying illustrations are created with Stable Diffusion using DiffusionBee. Images take around 30s to generate on my Macbook Air M1. I'm looking to switch to MochiDiffusion to cut generation time a bit.<p>The blog is running Ghost on a small DigitalOcean VPS, with emails delivered by Mailgun.<p>The process right now is somewhat labour-intensive: between researching news stories, iterating on the content, and publishing, it takes a decent amount of time for each piece of content. I'm confident in being able to automate a large part of it, in time.<p>One fun fact I learned when planning the virtual road-trip for this project: in average traffic conditions, it's possible to visit every city in England in less than 48 hours. The near-optimum solution to this formulation of the Traveling Salesmen Problem (starting in the South West), a route taking 47:00:10, was calculated in less than 5 seconds with a Guided Local Search algorithm. [1]<p>Technology means that I can virtually, learn about, write creatively, and publish regularly, all whilst having a family and a full-time job. What a time to be alive!<p>Very open to your thoughts, and indeed to feedback on the concept or the execution.<p>[1] <a href="https://developers.google.com/optimization/routing/tsp" rel="nofollow">https://developers.google.com/optimization/routing/tsp</a>