My favorite real-world example that I worked on: I created a YouTube documentary series about corruption in a small town in Illinois. This required downloading thousands of hours of government meeting videos from YouTube, transcribing + chunking + embedding, summarizing meeting segments, running a couple passes of validation, then searching for interesting storylines. I also scraped thousands of public documents which exposed campaign finance violations and some truly nefarious stuff going on behind the scenes.
I did 90-95% of the work on this with a local GPU. I still ran Claude and Codex, but they were just writing code to orchestrate API calls against local models, local Whisper, etc. Doing the same with the public cloud would have cost thousands of dollars, instead it cost a few hundred dollars for a frontier lab subscription and tens of dollars for electricity.
I recently got into the DGX Spark and just a month ago, got an AMD Ryzen developer platform. Both are incredibly useful tools for some upcoming projects I'm working on (also related to government corruption), but in my limited experience of trying to run opencode on them, the "good models" are still completely unusable because the system prompt alone requires a minute of thinking.
Do you have a writeup of how you did it, which tools you used? I have a similar project on a much more mundane topic, where I want to build a searchable index of Youtube videos, blog posts, etc. based on their content.
I've been meaning to write something about how I did it, and have been putting it off for a long time. I wrote all the tools myself - by that, I mean that everything was a web app running in my browser.
My advice would be to first set up an automation for yt-dlp to pull the media, then use Whisper to build a transcription pipeline. Chunk the transcript based on desired result granularity, then store embeddings in local Qdrant. It helps to use an orchestrator to handle all of this - my current recommendation is Dagster (dagster.io).
I did 90-95% of the work on this with a local GPU. I still ran Claude and Codex, but they were just writing code to orchestrate API calls against local models, local Whisper, etc. Doing the same with the public cloud would have cost thousands of dollars, instead it cost a few hundred dollars for a frontier lab subscription and tens of dollars for electricity.
I recently got into the DGX Spark and just a month ago, got an AMD Ryzen developer platform. Both are incredibly useful tools for some upcoming projects I'm working on (also related to government corruption), but in my limited experience of trying to run opencode on them, the "good models" are still completely unusable because the system prompt alone requires a minute of thinking.