pveugen

Schemer is text only. But we're working on sort like models for images to data too.

We aim to make all our models available cross-platform. There's a subset currently only iOS/macOS, because they take some more effort to port over to Android and web.

Check out the CLI for easy experimentation: https://github.com/Desert-Ant-Labs/desert-ant-cli#desert-ant...

We design in Figma. Build a design system out that with components for all our public facing products, demos and marketing assets. The website is built with the components, and we have a set of skills and tools to keep both in sync. We also use skills to sync between HuggingFace, our SDK on GitHub and the website. We write and review most our core copy by hand and use that to help expand into different pages. We prob do a write-up about this on our blog later.

We plan to make most our models available for Android and web too. Some are a bit harder to port to the different platforms and will take a bit longer to properly land on Android or web. Mostly sequencing (Voz, Clips, Title). Soon!

Just a few are iOS first (pure practical timing/sequencing). We plan to make all models available cross-platform in the coming weeks.

OCR on steroids. Our Schemer model will soon be available (free form text to structured JSON). Once that lands, we want to jump into image to JSON.

Thanks!

It's an ANE optimized version of Parakeet, with our own inference, which enabled us to push performance to about 300x realtime speed on an iPhone 16/17. Our next gen Voz model is trained from scratch and will be at least twice as fast. Android and other platforms will land soon.

What kind of places details are you looking for? Depending on the geographic region, Mapbox has data for regions, cities, addresses, zipcodes, and points-of-interest (POI).

This is the coverage per region: https://www.mapbox.com/geocoding/#coverage

Mapbox offers maps, geocoding, and directions, with solid coverage in Australia.

https://www.mapbox.com/geocoding/

Happy to answer any questions.

Disclaimer: I work at Mapbox.

We expanded our team and are working on improvements to React Native SDK, which was initially a side project from one of our engineers. We’re excited to support the library and get it to feature parity with our native iOS, Android, and Qt SDKs.

Disclaimer: I work with the mobile team at Mapbox.

We did. By a lot. A few months ago we implemented a new hibernation mode that suspends location services more aggressively when you're not active. This saves about 50-90% battery on an average day. The only downside of this approach is that we can't show the first 100-200m on a map when you start moving again. If you find that important, you could use the high accuracy option at the expense of a bit more battery impact. Try it!

Strava and Human are pretty different products, where Human tracks everyday activity, and Strava focuses on specific activities like running and cycling. We became pretty close with the Strava team over the years and were honored to count their leadership to our group of advisors. Being an avid Strava user myself, I'm excited to work with Strava in my new role at Mapbox.

We're looking forward to sharing what we learned about the health & fitness space, activity tracking, and mobile with all Mapbox customers.

Yes, that's how it works ;). Unfortunately I can't share anything about the deal terms.

Paul, founder of Human here. We chose the term "join" because it really feels like we're joining forces. One of the reasons why are so excited about this is the cultural fit and shared vision between both teams. We started Human for a reason and Mapbox is just as mission driven. Glad that our team and app can now be part of that.

Some more background on the why: https://www.mapbox.com/blog/human-mapbox/

I'd be happy to answer any questions.

Apple backs up your Health data in iCloud, if you enable it.

"Your data in the Health app is encrypted with keys protected by your passcode, and never leaves your device unless you choose to back it up or grant access to a third-party app. When you do choose to back up your Health data through iCloud, it is encrypted both in transit and on our servers."

https://www.apple.com/privacy/privacy-built-in/

No concrete plans yet. We never share any personal identifiable data, without explicit consent of our users. So if we would like to make (parts) of our data publicly available, we have to anonymize and aggregate that data first. For now we're focused on our app first.

Our tracking accuracy overal is good, but slow motorized transport versus bike rides have the highest error rates. That means that in a small percentage of the cases slow, bumpy car rides might get detected as biking and the other way around. Movement patterns vary quite a bit from city to city, especially for public transport. Users can correct detection errors, but that doesn't catch all cases. We have a slight bias towards cycling.

Thanks! Fixed.

Sharp. Thanks! In some cases we mix up (slow) motorized transport and cycling. We only categorize walking, cycling, running, active (active at one location) and motorized transport, so any other moving activity might end up in one of those categories. For daily use our tracking is pretty accurate for most activity types and users can manually correct any mistakes.

Thanks for the feedback.

We rendered visuals for different activities in all cities. Click one of the cities on the homepage for details. We've also shared all visuals (dark and light) and some bonus gifs on Dropbox: https://www.dropbox.com/sh/58chppkj2ckim7s/AAAchKhSL56mjaaiA...

Good point. I played around with different decay times a lot, but it was very hard to settle on a decay time and opacity settings that worked for most cities, since the data set from city to city was varying in size. If I would re-render the movies, I'd definitely do try renders with lower decay times, especially for cities like NY, LA, etc.

The really crappy old browsers won't see the feedback button. We do store and show HTML doms, which helps to debug if necessary, but most of our users collect feedback on such a large scale that it would be too time consuming to offer a manual solution like this.

Capturing sites that require a login works the same as other pages. We use the HTML output to capture a server-side screenshot.

Thanks. Would indeed be a small change that helps to improve the flow a lot.

Indeed very cool. Usabilla offers a same form of feedback: http://usabilla.com/products#usabilla_live (see also button on the right side of the page).

How it works:

1. You create a widget and add two lines of code to your site. 2. Visitors click the feedback button and can select highlight any part of the page to comment on. 3. Usabilla creates a screenshot (server-side) and shows feedback in a simple dashboard.

Disclaimer: I'm founder of Usabilla.