Urgent.News

What's breaking now, across thousands of outlets.

AI

PlantCare Adventure AI

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built I built PlantCare Adventure AI, an open-source AI companion designed to get people off the screen and into the real world. The app asks for the user's location/environment and preferences, suggests outdoor activities, generates a short outdoor mission, and gives the user things to look for while…

The Hacktoberfest Open-Source AI Challenge Week 1 focused on the submission of PlantCare Adventure AI, an open-source AI companion aimed at encouraging users to disconnect from their screens and engage in outdoor activities. The app, built by godGamerz812, takes the user's location and preferences into account to suggest outdoor activities and generate a short mission for the user to complete while exploring.

The app also provides an offline checklist for users to record observations, photos, and notes, resulting in a personal Adventure Journal. The app is built using Python, Streamlit, and Gemma as the open-source AI model integration. The local fallback functionality allows the app to operate without a configured remote Gemma endpoint, ensuring that users can still engage in the outdoor experience even without a stable internet connection.

The project aims to demonstrate the potential of open-source AI and showcase how it can be used to promote digital wellbeing and outdoor exploration. By using Gemma, developers can experiment with AI without relying solely on closed APIs, as seen in this project's focus on outdoor observation and experiences. The Hacktoberfest 2026 challenge welcomed this submission into the "Best Use of Gemma" category.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Spec, Hash or Guess: Can LLMs Keep Spain's Tamper-Proof Invoice Ledger?

This is a submission for the Kaggle Benchmarking Challenge From 2027, every invoice issued in Spain has to come from software that writes VeriFactu records.

  • Nine language models tested on VeriFactu record specification
  • Seven models accurately generated hash text for all records
  • Gemma 4 31B most cost-effective at $0.14 for 100% accuracy

The Receipt: I Priced Every Token of One AI Agent Task

Everyone talks about AI costs in aggregate. Dashboards show monthly spend, per-model totals, team budgets. Nobody shows you a receipt. So here's one.

  • $0.051 raw inference cost for AI agent task
  • Fully-loaded cost of $0.23 includes hidden expenses
  • Context (knowledge base retrieval) consumes 43% of tokens

More from Tuesday 6 October →