An absurd meditation app (fully AI-generated)
Qi is a meditation experience which invites listeners to place themselves in absurd scenarios. Existing guided meditation apps tend to focus on a small set of narrow calming experiences ('midnight laundromat,' 'waves on the seashore,' so on) - but why not while hiding from dinosaurs or preparing to ride into battle? Seems even more important to be calm then! Early listener feedback has been that the absurd scenarios are actually more engaging and hold their attention much better. There is a lot of push to use AI to refine existing workflows or clone existing apps (but with talking to an…
What it does
In the maker’s words, at launch
Qi is a meditation experience which invites listeners to place themselves in absurd scenarios. Existing guided meditation apps tend to focus on a small set of narrow calming experiences ('midnight laundromat,' 'waves on the seashore,' so on) - but why not while hiding from dinosaurs or preparing to ride into battle? Seems even more important to be calm then! Early listener feedback has been that the absurd scenarios are actually more engaging and hold their attention much better. There is a lot of push to use AI to refine existing workflows or clone existing apps (but with talking to an LLM). That's fine and well, and I think this app shows that we can get 'almost' to a meditation app purely with current AI tech - and multiple meditation apps were valued over $2B over the last couple years, so there's some economic value in doing so. What's _more_ interesting to me, is what AI unlocks that's new: maybe fully personalized experiences, maybe pushing down artistic avenues that are only appreciated by a small niche. The scripts are generated by a mix of GPT-3.5 and GPT-4. I personally think GPT-4 was significantly easier to work with and that the scripts were better, justifying the additional cost/latency. (Can you tell which of the scripts are generated by 4?). GPT-4 generated much of the Next.js code and helped turn my IPython notebook into a reproducible script as well. The images were generated by Stable Diffusion v1.5. The audio is synthesized with SpeechT5. Midjourney and ElevenLabs would likely have created higher quality results but I have a GPU just sitting idle :) I also tried to generate background audio via Riffusion but had fairly poor results, would love to improve here. Very fun project - would love to hear your feedback!
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
