Poundcake
Personalized forecasting for smarter weight management.
What it does
Most health apps are reactive and simply log your meals (yawn). Poundcake uses longitudinal metabolic data and LSTM models to forecast your weight trajectory - including projected goal dates and probability of success. What makes this different: -Dynamic weight projections that update as your behavior changes. -Clear signals of whether your current habits will get you to your goal. -The app proactively checks in via text-style interactions to reduce friction and increase consistency.
Does a similar job
all alternatives →
- TYTrack your calories easily by saying what you ate2024 · calorio.xyz · ▲17
Hi guys, I created this app to solve one of my own problems: I found calorie tracking to be a real pain. Now, instead of scanning barcodes, scrolling through lists, or taking photos of food, I just speak into my phone (or computer), tell Calorio what I’ve eaten, and it handles the rest. It uses OpenAI’s APIs to process audio and map foods to calories. It’s free to use without an account, but if you want it to tally daily calories and remember everything you’ve eaten, you’ll need to sign up with your Google account and subscribe (you get 7 days for free). I would really appreciate any…
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 · 19d 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 · 27d ago · cactuscompute.com
