Completed the second task for Hacker House Goa 2026 🌴 Built Vaani, a multilingual voice enabled RAG system with @AnikhetMulky and @PKatsBox 🔥 We wanted to go beyond a basic voice to LLM pipeline and focus on what actually makes a RAG system reliable in production. Vaani combines hybrid retrieval using dense vector search + BM25, with confidence gating to refuse off topic or low confidence questions instead of guessing. We tested 9 different chunking strategies across 500 held out Hindi queries, with retrieval staying under roughly 20 ms. We also built a tiered response system for latency, an orchestration harness with retries, circuit breakers and fallbacks, plus grounding guardrails that verify generated answers against the retrieved context before showing them to the user. The system supports multiple Indian languages and is deployed with Azure infrastructure for the backend. Try it here 🌐 project-x-green-xi.vercel.ap… GitHub 💻 github.com/Payal2000/project… Video Demo 🎥 tella.tv/video/anikhets-vide… Product Demo: tella.tv/video/ai-voice-assi… #RAGInGoa #HHGoa2026 #RAG #GenAI #VoiceAI

The CEO of Take-Two, the company behind GTA, just said something the entire AI industry doesn't want to hear. And he said it without being anti-AI. Strauss Zelnick's argument is precise. AI is built on datasets. Datasets are backward-looking. Creativity is forward-looking. A model trained on everything that already exists cannot, by definition, produce something genuinely unexpected. And all hits, by their very nature, are unexpected. Asset creation and hit creation are not the same thing. AI is getting very good at the first one. The second one is what actually makes money, builds franchises, and changes culture. Nobody has shown AI can do that yet. The derivative property problem is real. You can clone GTA with existing technology. You could do it before AI. It would take 3 years and look identical. It still wouldn't sell. Because it isn't GTA. It's a clone of GTA. And consumers, despite what the industry occasionally pretends, can feel the difference between something genuinely new and something assembled from the residue of things that already worked. Thousands of mobile games ship every year. 0 to 5 hits get made. The same studios make them every time. The technology to make more games has been commoditized for years. It didn't democratize hit creation. It just flooded the market with more forgettable product. The Silicon Valley thesis that AI unlocks game creation for everyone is true in the same way that cheap cameras unlocked filmmaking for everyone. They did. And the same 5 studios still make the movies everyone watches. What Zelnick is saying, without quite saying it, is that the thing AI cannot replicate is taste. The instinct for what hasn't been done yet. The cultural antenna that detects the gap in the market before the data can see it. Data tells you what people wanted. Hits tell people what they want next. Those are different jobs.