#generativeai
123 posts · Last used 2d
13/ Blurred spectrum between two refusal ways to disclose #NegativeResults and the process towards obtaining any given "successful" solution
-
#generativeAI companies using these "opaque" solutions as advertising and with goals "severely misaligned" [3] vs. the goals of the #ScientificCommunity
-
#scientific/ #technical experts increasingly adopting an "opaque" process to deliver "successful" solutions, hiding (or simply being more and more unable to keep up with) even the more severe pitfalls
9/ As anecdotal evidence, after recent exchanges with somewhat exasperated colleagues (note: the fields I'm referring to here are not #mathematics, but mainly #ComputationalModelling, e.g. in #EarthSciences, #ecology, #ClimateChange, ... or just simply their #PeerReview !)
- There seems to be a growing prevalence of those who claim that it is obsolete (usual "left-behind syndrome"?) to do scientific/technical work without depending more and more on #generativeAI (allegedly without upper limits)
🚀 Building Stoic — an AI Search & Answer Platform
Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers. It uses RAG, embeddings, semantic search, and vector databases to retrieve relevant context before generating an answer. The backend is built with Python and FastAPI, with Supabase + pgvector for vector storage and similarity search. I’m also experimenting with LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation. The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation. I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience. If you're interested in AI engineering, RAG, LLMs, semantic search, or building AI products, I’d love to connect and hear your thoughts. 🤝
🔗 Try Stoic: https://stoic-app.vercel.app 💻 GitHub: https://github.com/Rakesh051204/cloud9-frontend
#AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic






