Show HN: I built an LLM chat app because we shouldn't need 10 AI subscriptions

Hacker News - AI

Jul 13, 2025 10:36

maniknt28

1 views

hackernewsaidiscussion

Summary

A developer created a chat app that allows users to access multiple LLMs (like ChatGPT, Claude, and Gemini) in one place, paying only for actual usage instead of multiple subscriptions. This solution streamlines workflow by enabling prompts and documents to work across different models, reducing the need for multiple specialized AI tools. The project highlights a growing demand for unified, flexible AI platforms that simplify user experience and cost management.

I'm lost between ChatGPT vs Claude vs Gemini... which subscriptions to take? With Cursor and all these specific AI tools, I just wanted one simple chat app where I can use any model and pay only when I use it. Couldn't find one, so I built one. Pay only for what you use. Your prompts and docs, knowledge bases work with every model - no more copy-pasting between apps. Started as a personal project, but thought someone else might benefit from this too. https://prismharmony.com/chat What do you think? Comments URL: https://news.ycombinator.com/item?id=44549209 Points: 1 # Comments: 0

Read Full Article More News

Can Ethereum (ETH) Rally 100x Again? Experts Say Ruvi AI’s (RUVI) Early Bonuses Make It the Smarter Bet

Analytics InsightJul 13

The article discusses whether Ethereum (ETH) can achieve another 100x rally, with experts suggesting that Ruvi AI (RUVI) may offer better early investment opportunities due to its AI-driven features and early bonuses. The rise of AI-integrated blockchain projects like RUVI highlights growing investor interest in the intersection of AI and crypto, signaling a trend toward smarter, technology-enhanced investment platforms. This shift could accelerate innovation and adoption in both the AI and blockchain sectors.

Westbrook police say they mistakenly posted AI-generated drug seizure photo

Hacker News - AIJul 13

Westbrook police admitted to mistakenly posting an AI-generated image of a drug seizure on Facebook, believing it to be a real photo. This incident highlights the growing challenges of distinguishing AI-generated content from authentic images, raising concerns about misinformation and the need for better verification practices in law enforcement and public communications.

Markdown for the AI Era