Problem: With react-query, we may declare inconsistent query keys. That leads to cache misses and duplicated cache entries. 👎 Solution: 1. Wrap each useQuery call in a custom hook. Store the hooks in /hooks. 2. Put the fetch call in the custom hook. *Don’t export it*. 3.

Generate UI with simple text prompts. Copy, paste, ship. v0.dev

U can buy a house on Amazon and unfold it into a complete house by yourself 😍

We’re so fucked.

The US government explicitly recommends 6 memory safe languages: C# - created by Microsoft Go - created by Google Java - created by Sun, bought by Oracle Rust - create bor Mozilla Swift - created by Apple And ... Python - create by one fucking genius on his own in his Christmas

Transform Your Amazon Search with AI: Find Your Ideal Product Almost Instantly! deepshop.ai #Saas #AI #Amazon

Weekend treat - L4 GPUs are now available on Studios 🔥🔥 - $0.88 per hour - 17 free hours per month 🤯 - choose 1 or 4 L4 GPUs ⚡⚡⚡⚡ - 1/2 the price of A10G 🤑 - 24 GB RAM - free persistent storage included lightning.ai

Harrison Chase (Harrison Chase), the founder of , shared insights on the evolution of AI agents and their applications during Sequoia Capital's AI Ascent. He identified 3 critical areas of development: - Planning - UX - Memory Here's a summary:

Building Multi-Document Agents with LlamaIndex 🦙 RAG with simple questions over a small set of data is easy, but a key goal for LlamaIndex 🦙 is to solve complex QA over many docs. Ankush Singal presents an excellent overview of our multi-document agents. Instead of treating each

Python is the language to train LLMs. Rust is the language to deploy these LLMs. Candle is an open-source ML framework in Rust that helps you deploy LLMs efficiently. github.com/huggingface/ca…

Start small, learn fast ✨👌

github.com/swyxio/ai-notes #AI #github #AImodels

Best reference guides for building a streaming-enabled full-stack LLM application.

DSPy

Optimization of LLM Systems #DSPy #LangChain

x.com/i/article/2015…