craigm26
Show HN: OpenCastor Agent Harness Evaluator Leaderboard
https://craigm26.github.io/OpenCastor/
I've been building OpenCastor, a runtime layer that sits between a robot's hardware and its AI agent. One thing that surprised me: the order you arrange the skill pipeline (context builder → model router → error handler, etc.) and parameters like thinking_budget and context_budget affect task success rates as much as model choice does.So I built a distributed evaluator. Robots contribute idle...
Show HN: OpenCastor – A universal runtime connecting AI models to robot hardware
OpenCastor is an open-source Python runtime that connects AI models to robot hardware through a single YAML config file. You pick your brain (Claude, Gemini, GPT, or a local model via Ollama), pick your body (Raspberry Pi, Jetson, Arduino, Dynamixel servos), and it handles the wiring between them.Origin story: I've been building ContinuonAI — a cognitive architecture for personal robots with...
Show HN
I started building “BikeBus” as a way for groups to organize children’s BikeBus to school.1.0 release will be web only. I am not a web developer.Features: 1. Plot routes 2. Make a BikeBus 3. Create an Organization 4. Bulletin Boards for MessagingThe Organization feature will have some premium functions as it can handle multiple BikeBus and meant to help school districts track timesheets....
Re:What problems do autonomous vehicles have in geospatial awareness?
on Tuesday February 27, 2018 @10:16PM (#16480417)
I’d like to hear more about what problems autonomous vehicles have in recognizing traffic situations. I want to build a platform for V2V communication and mapping
What problems do autonomous vehicles have in geospatial awareness?
Re:As California’s labor shortage grows, farmers replace workers with ...
on Friday July 21, 2017 @02:29PM (#14822756)
Find the easiest adaptation for the baseline of picking the fruit. E.g. a robot that picks fruit really well.
I’m definitely interested in the farm/cv realm. It takes funding though.
Re:Not Hotdog App
on Tuesday May 16, 2017 @07:18PM (#14354214)
I would love to read this.
Re:Ask HN: Investor Animated Video – draft critiques wanted
on Thursday April 21, 2016 @01:11PM (#11543695)
Re:Ask HN: Investor Animated Video – draft critiques wanted
on Thursday April 21, 2016 @12:13PM (#11543241)
So in your formatted suggestion:
"Do you want the ability to switch between voice chat, messaging, map directions, and calendars seamlessly with just using your voice while travelling?
Do you need that ability to enhance your awareness while travelling?
With Cavalcade, you can! Just download the app and form a cavalcade with your friends with just your phone number"
----That works a lot. I'll try that one. Thanks!
Ask HN: Investor Animated Video – draft critiques wanted
Hi all, the thing I'm building is very complex and I have a difficult time simplifying it for potential investors and customers. Yes, I know a lot of people wouldn't say this is a MVP. To me this is. The point is to provide a better social network that is ad-free, allows for anonymous use (and free), encrypted group voice chat/messaging, calendaring, mapping and some AI magic for interrupting...
Re:Ask HN: Examples of sucessful one person startups?
on Friday October 16, 2015 @01:17PM (#10400702)
in my opinion - successful - nice work!
Re:Show HN: MapMe.io, AR platform for IoT, primarily for transportatio...
on Wednesday October 14, 2015 @02:37PM (#10388484)
thanks! the main company website (http://beaconsafety.co) and/or the mapme.io site? For the mapme.io site I'm planning to add a "how-to" modal later.
Re:Show HN: MapMe.io, AR platform for IoT, primarily for transportatio...
on Wednesday October 14, 2015 @02:16PM (#10388327)
http://MapMe.io, a AR platform for the IoT, primarily for transportation awareness. Original motivation was to create an all-software solution for the bicyclist to be more aware of something coming up from behind - as I am mostly deaf. After a few startup weekends and intel edison incubators, I'm getting close to testing with small group of alpha users in a larger city like SF (where real-time data is available for public buses). The idea for the MapMe.io is to be the software platform where real-time notifications enhance transportation safety overall. Spotter view/tab will access the phone camera for "background" of app/"foreground" for user and the alerts will give relevant alerts based on user location.
Show HN: MapMe.io, AR platform for IoT, primarily for transportation awareness
Re:Show HN: MapMe.io, AR platform for IoT, primarily for transportatio...
on Wednesday October 14, 2015 @02:15PM (#10388319)
thanks!
Re:Show HN: MapMe.io, AR platform for IoT, primarily for transportatio...
on Wednesday October 14, 2015 @12:51PM (#10387743)
company website at beaconsafety.co
Show HN: MapMe.io, AR platform for IoT, primarily for transportation awareness
http://MapMe.io, a AR platform for the IoT, primarily for transportation awareness. Original motivation was to create an all-software solution for the bicyclist to be more aware of something coming up from behind - as I am mostly deaf. After a few startup weekends and intel edison incubators, I'm getting close to testing with small group of alpha users in a larger city like SF (where real-time...