Tripnotes.ai: Intelligent Travel Planner
Hey HN, We're excited to announce the public beta preview of Tripnotes, an intelligent travel planner that mixes a custom recommendation engine, our own data, and a bit of GPT to help you find the right places to go while traveling. Our team has been working hard on this project for 6 months, and we're excited to finally share it with the HN community. With Tripnotes, you can keep track of all your notes about travel when planning to visit a city. Paste in article URLs, videos, emails, text messages, any other text, and if you need some help with research, ask our Concierge which will…
What it does
In the maker’s words, at launch
Hey HN, We're excited to announce the public beta preview of Tripnotes, an intelligent travel planner that mixes a custom recommendation engine, our own data, and a bit of GPT to help you find the right places to go while traveling. Our team has been working hard on this project for 6 months, and we're excited to finally share it with the HN community. With Tripnotes, you can keep track of all your notes about travel when planning to visit a city. Paste in article URLs, videos, emails, text messages, any other text, and if you need some help with research, ask our Concierge which will provide useful recommendations and itineraries for the city in question - with a fallback to GPT for things we didn't quite understand. If you're not ready to dive right in, here are a few short highlight videos: https://twitter.com/matthewer/status/1619047755271536640 https://twitter.com/matthewer/status/1621172173598756864 https://twitter.com/matthewer/status/1623703548545445890 https://twitter.com/matthewer/status/1638010661694234625 All the places by Tripnotes are from our own database, but we rely upon GPT to understand the intent of the incoming prompts, as well as to help with the prose in our response to ensure the place descriptions fit what's being asked for. Since we tweeted about our preview release on Monday, we've had over 15,000 people come and try at least one prompt, with over 40,000 unique notes generated from prompts about cities all over the world. We'd love for you to give Tripnotes a try and let us know what you think. The "unauthed" version is open to everyone. If you're interested in using the full version, please join our waitlist. The full version maintains a history of your notes and allows you to edit the text and auto-highlights any text you write/paste in on the fly, which can be useful for pasting recommendations from friends (say via SMS or Email) and having them auto-highlighted and mapped. You can also paste in links from articles, websites, blogs, even Tiktok or Youtube. We scrape those urls, gather the list of places that are mentioned, and then show them on the map along side the rest of your note. We'd love to hear your thoughts and feedback, so please feel free to leave a comment or reach out to us directly. Thanks for your support!
Does the same job
all alternatives →
- TPTrip Planner – A tool for planning a trip itinerary using Google Maps2019 · github.com · ▲110
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, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io