Prompt patterns for LLMs that help you design better software
Large language models (LLMs) may not be replacing developers anytime soon, but can still be of use in the design process.
Learn AI
AI Prompt: Writing Supabase Edge Functions | Supabase Docs
Supabase is an open source Firebase alternative providing all the backend features you need to build a product.
Deep Dive into LLMs like ChatGPT
This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full traini...
The Ultimate Guide to bolt.new Prompting: Build Better Apps Without Deep Technical Knowledge
A new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team
Is DeepSeek Legit? Breaking Down All Major Allegations
Start a VPS cost effectively with Hostinger today and use discount code "BYCLOUD" for an extra 10% off! http://hostinger.com/bycloudWatch my last videohttps:...
oumi-ai/oumi: Everything you need to build state-of-the-art foundation models, end-to-end.
Everything you need to build state-of-the-art foundation models, end-to-end. - oumi-ai/oumi
Om-Alve/smolGPT
17-445 Machine Learning in Production / AI Engineering
Ask HN: How to learn AI from first principles? | Hacker News
The Illustrated DeepSeek-R1
A recipe for reasoning LLMs
Docker Image BEST Practices - From 1.2GB to 10MB
Want to dramatically reduce your Docker image size? In this comprehensive guide, I'll show you how to shrink your Docker images from gigabytes to just megaby...
No Hype DeepSeek-R1 Reading List | Oxen.ai
DeepSeek-R1 is a big step forward in the open model ecosystem for AI with their latest model competing with OpenAI's o1 on a variety of metrics. There is a lot of hype, and a lot of noise around the fact that they achieved this with much less money and compute. Source: https://x.com/karpathy/status/1872362712958906460 Instead of learning about it from AI influencer* threads hyping up the release, I decided to make a reading list that links to a lot of the fundamental research papers. This list
Articles
Learn EVERYTHING You Need to Know About AI From a Top AI Expert
🚀 AI Explained for Everyone – Full Crash Course in 10 Minutes! 🚀Let’s break down Artificial Intelligence (AI) into simple concepts. From understanding what...
(1) Agent Engineering in 2025 - YouTube
Enjoy the videos and music that you love, upload original content and share it all with friends, family and the world on YouTube.
Understanding and Effectively Using AI Reasoning Models
With the imminent release of OpenAI's -o3 reasoning model and Deepseek's impressive R1 release, it's clear that reasoning models are improving rapidly. But, ...
Building Effective Agents with LangGraph
Anthropic's recent blog post on "Building Effective Agents" lays out the difference between "agents" and "workflows", and presents a number of common pattern...
No, Deepseek R1 is NOT "better" than o1 BUT you get 25x COMPUTE
🔥 Is Deepseek R1 REALLY better than o1? The answer might surprise you! But one thing’s for sure: with 25x more compute, you can SCALE YOUR IMPACT like never...
crawshaw - 2025-01-06
Run DeepSeek-R1 Dynamic 1.58-bit
DeepSeek R-1 is the most powerful open-source reasoning model that performs on par with OpenAI's o1 model. Run the 1.58-bit Dynamic GGUF version by Unsloth.
Agentic SaaS: Are AI Agents Killing Traditional SaaS?
Every now and then, I see headlines proclaiming, “SaaS is Dead” It’s a bold and provocative claim. I firmly believe that the SaaS model, as…
Release 3.3.0 · huggingface/transformers.js
🔥 Transformers.js v3.3 — StyleTTS 2 (Kokoro) for state-of-the-art text-to-speech, Grounding DINO for zero-shot object detection 🤖 New models: StyleTTS 2, Grounding Dino StyleTTS 2: High-quality s...
The /llms.txt file – llms-txt
A proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time.
Reducing LLM costs and latency with semantic cache
Implementing semantic cache from scratch for production use cases.
An Overview of The Cohere Platform (v1 API) — Cohere
Cohere offers world-class Large Language Models (LLMs) like Command, Rerank, and Embed. These help developers and enterprises build LLM-powered applications.
Screenshot_20250120-234428.png
Phi-4 Finetuning Unsloth notebook
Explore and run machine learning code with Kaggle Notebooks | Using data from No attached data sources
hhhuang/CAG: Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG - hhhuang/CAG
Cookbooks — Cohere
Explore a range of AI guides and get started with Cohere's generative platform, ready-made and best-practice optimized.
Guest post: Enhancing RAG with RA-DIT: A Fine-Tuning Approach to Minimize LLM Hallucinations*
RA-DIT, or Retrieval-Augmented Dual Instruction Tuning, is a method for fine-tuning both the LLM and the retriever in a RAG setup to enhance overall response quality