We re a small group of 15-year-olds from Mumbai running Indian Instinct Studios. Every evening we used to open the fridge and ask kya banaun aaj? (What to make today?)
So we built TikkaMate an AI cooking assistant made for real Indian kitchens:
Fridge photo Jain thali in 10 seconds (no roots, no onion, no garlic)
so i am a high school student and take part in lots of kaggle competition but the main problem i face is data cleaning especially for datasets above the size of 80 mb even claude or chatgpt have a limit of 30 mb, it takes at least 2-4 hours to clean a dataset and make it ML ready therefore to solve this problem i am developing an preprocessor that takes your messy CSVs and clean it according to the algorithm you will use XGboost, Regression and etc looking for your insights like is this actually useful and may work or i am overthinking.....
Different models have different strengths. Some are faster, some go deeper on complex financial reasoning, some handle specific tasks more reliably than others.
Rather than picking one and hoping it covers every use case, we wanted to give you the option to choose.
I built a free tool that simplifies generating Access Tokens for Shopify custom apps.
If you've worked with Shopify's API since their early 2026 update, you know the process got significantly worse multiple screens, manual URL copying, and way too many steps for something that should be simple.
Looking to complete the first 200 iOS paid users. Any recommendations? B2B is welcomed. Edit your notes quicker with prompts and extract information from voice, videos, live and virtual meetings, screenshots, among others.
Hi Everybody, Getting setup for a Product Hunt launch tomorrow - vibemarketing.ninja It's an MCP server we've built to manage twitter and linkedin accounts using claude code or similar tools. Are you already using similar tools? Do you like the idea? One of the main benefits is that it's possible to context engineer the AI agent helping out to build content by for example, cloning the twitter algo repo, having claude code do analysis and then do some tweets about the findings (or any other area of interest of course) Another cool use case is to include the MCP in your product repos .mcp.json file so that when you push a PR and release of a feature, you can prepare the social media posts with the full context.. Let us know what you think! We've also created a vibe marketing discord if you'd like to join: https://discord.gg/YUCXmUAn
