Transcript: My new tab page will be the feed from the burrito. In cache. Run Lava for captioning. Also build a Transcribe website. Build these as a warmup. Constrain to two hours. To put out distributed inference infrastructure for certain models.
83.45% similar
Today marked a significant advancement in the burrito project, where the image pipeline, established the previous day, became fully functional and integrated into a webpage, complete with an effective querying system. The visual aspect of the project, particularly the image embeddings, was both intriguing and aesthetically pleasing, although its effectiveness is still under review. The project is now at a stage where the creator is keen to move beyond personal experiments to sharing the results with others, with the immediate goal being to encourage a small group of individuals to test the developments. The focus for the week has shifted to actual user engagement through getting people to sign up and provide feedback, driven by the enthusiasm of witnessing the project's imagery features come to life.
The speaker is concluding their day, noting they need to have dinner and go to bed after facing challenges with Cloudflare's aggressive caching, particularly affecting video compatibility with Safari. They consider transitioning to R2 to ease the struggle with caching issues and video upload limits, since iPhone videos are restricted to 100 megabytes. Despite concerns about caching the homepage, progress was made on building the burrito.place website, and the agenda for the following day involves deploying changes and planning future steps for their experimental project.
83.02% similar
Your burritos are a digital platform that allows you to upload multimedia files to the web via an iOS shortcut. Participants of the experiment will have a personal webpage that recommends similar content they or others have uploaded, fostering a sense of community. There's a collaborative aspect for developers, with APIs available and the potential for collective improvement of the Next.js app. Keep in mind that the platform, especially for video uploads (currently capped at 100MB), is a work in progress and feedback is encouraged to refine the experience. The speaker instructs on how to use a digital tool, explaining that it can load various types of content. Users can add to the tool by accessing a shortcut through three dots, and their content should appear in the share sheet for photos, videos, audio notes, and text—though text support is limited at this stage. There's a file size limitation of 100 megabytes, which generally affects photos and audio. The speaker expresses gratitude for the willingness to participate and encourages feedback and engagement at any level, emphasizing a desire to build something beneficial for the group.
I had an excellent call with Jordan, which I'll discuss in more detail later. Unexpectedly, I succeeded in quantizing lava, and the initial results look promising despite the script being rough. It seems feasible that I might run something akin to GPT-4 style vision captioning locally. I'm excited to upload these quantized models to see the outcomes and I plan to head to Jordan's house to upload more models soon.
I finished making breakfast tacos and have a day planned with reading, meditation, and possibly writing. My focus for the day is improving the main burrito website to make it interactive and pondering the challenge of making it easily deployable for others without the pain of maintaining a separate instance. I'm contemplating whether to maintain the existing system or create a new one, maybe using Docker to bundle the components. The decision is complicated due to the unique architecture of building decentralized applications and requires further thought.