Core AI

Large Language Models

Deep dives into GPT, Claude, Gemini, Llama and the transformers powering modern AI

53,002

lessons

Skills in this topic

5 skills — Sign in to track your progress

View full skill map →

LLM Foundations

Explain how transformers generate text

Write zero-shot and few-shot prompts

LLM Engineering

Call LLM APIs with function/tool use

Fine-tuning LLMs

Prepare fine-tuning datasets

Multimodal LLMs

Use GPT-4V / Claude Vision for image understanding

Videos 21,426 Reads 31,576

All Reads (31,576) Articles (13452)Blog Posts (5956)Tutorials (2563)Research Papers (8684)News (921)

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

arXiv:2607.06452v1 Announce Type: cross Abstract: Biomedical question answering requires not only accurate extraction of information from scientific literature

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

arXiv:2607.06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

arXiv:2607.06482v1 Announce Type: cross Abstract: Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-wor

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine

arXiv:2607.06495v1 Announce Type: cross Abstract: Live sports commentary is grounded generation under a deadline: statements concern real, named athletes, the g

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

arXiv:2607.06527v1 Announce Type: cross Abstract: Multi-hop Question Answering over Knowledge Graphs faces a critical challenge: traditional retrieve-then-read

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

arXiv:2607.06546v1 Announce Type: cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models.

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

arXiv:2607.06565v1 Announce Type: cross Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single ba

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning

arXiv:2409.06067v3 Announce Type: replace Abstract: Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneit

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?

arXiv:2508.01109v3 Announce Type: replace Abstract: We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational impr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Base Models Know How to Reason, Thinking Models Learn When

arXiv:2510.07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack? We first present an unsu

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents

arXiv:2510.19771v4 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercis

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Replication in Visual Diffusion Models: A Survey and Outlook

arXiv:2408.00001v2 Announce Type: replace-cross Abstract: Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diver

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Trust-free Personalized Decentralized Learning

arXiv:2410.11378v3 Announce Type: replace-cross Abstract: Personalized collaborative learning in federated settings faces a critical trade-off between customiza

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer

arXiv:2502.15631v2 Announce Type: replace-cross Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chai

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Narrative-Centered Emotional Reflection: An Early Prototype for AI-Supported Emotional Self-Reflection

arXiv:2504.20342v2 Announce Type: replace-cross Abstract: Reflexion is an AI-powered prototype designed to explore structured emotional self-reflection. By inte

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Detoxify: A framework for abusive text transformation using LLMs

arXiv:2507.10177v2 Announce Type: replace-cross Abstract: Although Large Language Models (LLMs) have demonstrated significant advancements in natural language p

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

arXiv:2508.16560v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to inte

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders

arXiv:2511.05350v3 Announce Type: replace-cross Abstract: We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, whe

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs

arXiv:2601.12494v3 Announce Type: replace-cross Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, but adapting th

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Transformers converge to invariant algorithmic cores

arXiv:2602.22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same functi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

Quantifying Frontier LLM Capabilities for Container Sandbox Escape

arXiv:2603.02277v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2d ago

HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment

arXiv:2604.08435v2 Announce Type: replace-cross Abstract: It remains challenging to assess driver fatigue from untrimmed videos under constrained computational

AI Prompt Playbook for Hackathon Teams: 10 Prompts That Will Save You Hours

Medium · AI 🧠 Large Language Models ⚡ AI Lesson 2d ago

AI Prompt Playbook for Hackathon Teams: 10 Prompts That Will Save You Hours

AI is far more than a code generator. The best hackathon teams use it throughout the entire build process — from refining ideas to… Continue reading on Medium »

Artificially Yours; Episode 3: The Future of Generative AI

Medium · AI 🧠 Large Language Models ⚡ AI Lesson 2d ago

Artificially Yours; Episode 3: The Future of Generative AI

We’ve covered what AI actually is, and what’s happening inside a neural network when it “learns” something. Both of those were about… Continue reading on Medium

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

What actually changes when you go from a 10K-document demo to a production system handling ten million, and why most RAG tutorials quietly… Continue reading on

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

Medium · Python 🧠 Large Language Models ⚡ AI Lesson 2d ago

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

What actually changes when you go from a 10K-document demo to a production system handling ten million, and why most RAG tutorials quietly… Continue reading on

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

I Built RAG for 10 Million Documents. Here’s What Actually Stops Hallucination

What actually changes when you go from a 10K-document demo to a production system handling ten million, and why most RAG tutorials quietly… Continue reading on

TypeScript’s Most Useful Features That Most JavaScript Developers Never Touch

Medium · Programming 🧠 Large Language Models ⚡ AI Lesson 2d ago

TypeScript’s Most Useful Features That Most JavaScript Developers Never Touch

Discriminated unions, template literal types, infer keyword, satisfies operator, const type parameters, NoInfer utility type — the… Continue reading on Medium »

Cracking the Million-Token Context

Medium · Deep Learning 🧠 Large Language Models ⚡ AI Lesson 2d ago

Cracking the Million-Token Context

The Architecture of DeepSeek Sparse Attention (DSA) and GLM 5.2 Index Cache Continue reading on Medium »

Cracking the Million-Token Context

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

Cracking the Million-Token Context

The Architecture of DeepSeek Sparse Attention (DSA) and GLM 5.2 Index Cache Continue reading on Medium »

Dev.to AI 🧠 Large Language Models ⚡ AI Lesson 2d ago

🚀 Day 3 of 100 Days of GenAI for DevOps is LIVE!

One of the biggest challenges while running Large Language Models (LLMs) is answering a simple question: 👉 How much GPU memory (VRAM) do I actually need? As De

Beyond Bigger Models: How Small AI Models Can Collaborate to Become a Virtual Giant

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

Beyond Bigger Models: How Small AI Models Can Collaborate to Become a Virtual Giant

Rethinking Artificial Intelligence Through Distributed Intelligence Continue reading on Medium »

Part 1.4: Training Memory: Weights, Gradients, Optimizer States, and Activations

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

Part 1.4: Training Memory: Weights, Gradients, Optimizer States, and Activations

Parameter count tells us how large the model is. It does not tell us whether the model can be trained on a given GPU. Continue reading on Medium »

I Built These Side Projects With Claude — Here’s What Worked

Medium · Deep Learning 🧠 Large Language Models ⚡ AI Lesson 2d ago

I Built These Side Projects With Claude — Here’s What Worked

How I Used Claude to Build Automation Projects Faster, Learn More Deeply, and Ship Ideas That Would Have Taken Me Weeks Before Continue reading on CodeToDeploy

I Don’t Publish a GPT Until It Survives an Investor-Style Review

Medium · ChatGPT 🧠 Large Language Models ⚡ AI Lesson 2d ago

I Don’t Publish a GPT Until It Survives an Investor-Style Review

The evaluation process that changed how I decide which GPTs deserve to exist. Continue reading on Creating Custom GPTs »

The Tear-Sheet Playbook: Nine Practices for LLM Pipelines Where the Numbers Can’t Be Wrong

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

The Tear-Sheet Playbook: Nine Practices for LLM Pipelines Where the Numbers Can’t Be Wrong

Nine rules for building an LLM pipeline whose numbers you can stake a decision on. Each one is written as a rule, then the experiment that… Continue reading on

Do we really need Fable 5?

Dev.to · Liandanxia 🧠 Large Language Models ⚡ AI Lesson 2d ago

Do we really need Fable 5?

To be honest, whether large language models reach the level of Fable 5 is not especially meaningful...

Stop Guessing: I Tested 4 Chinese AI Models So You Don't Have To

Dev.to · swift 🧠 Large Language Models ⚡ AI Lesson 2d ago

Stop Guessing: I Tested 4 Chinese AI Models So You Don't Have To

Look, stop Guessing: I Tested 4 Chinese AI Models So You Don't Have To Hey, so I've been on a bit of...

Is AI Improving Your Thinking Or Replacing It??

Medium · ChatGPT 🧠 Large Language Models ⚡ AI Lesson 2d ago

Is AI Improving Your Thinking Or Replacing It??

Artificial Intelligence has become one of the most powerful tools ever created. Continue reading on Medium »

Unlocking Open-Weight LLMs: A Developer's Guide to Seamless API Integration

Dev.to · NovaStack 🧠 Large Language Models ⚡ AI Lesson 2d ago

Unlocking Open-Weight LLMs: A Developer's Guide to Seamless API Integration

Unlocking Open-Weight LLMs: A Developer's Guide to Seamless API Integration

How I Built a Zero-Copy Rust Proxy to Stop Runaway LLM API Bills (and Survived the Docker Loopback Trap)

Dev.to · ยชญ์ศรัณย์ ผิวผ่อง 🧠 Large Language Models ⚡ AI Lesson 2d ago

How I Built a Zero-Copy Rust Proxy to Stop Runaway LLM API Bills (and Survived the Docker Loopback Trap)

If you are building applications on top of foundational models like OpenAI or Anthropic, you already...

OpenAI Models on Bedrock: A Responses API Readiness Check

Dev.to · Jangwook Kim 🧠 Large Language Models ⚡ AI Lesson 2d ago

OpenAI Models on Bedrock: A Responses API Readiness Check

GPT-5.5 and GPT-5.4 now run on Amazon Bedrock's OpenAI-compatible endpoint. We mapped every config change and unsupported feature before you migrate.

Understanding LLM Streaming: Polling, SSE, and WebSockets

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

Understanding LLM Streaming: Polling, SSE, and WebSockets

Learn how LLM streaming works and compare Polling, SSE, and WebSockets to choose the right streaming approach. Continue reading on Medium »

We Built AI Using Wikipedia, But Wikipedia Is 40% Wrong

Medium · Machine Learning 🧠 Large Language Models ⚡ AI Lesson 2d ago

We Built AI Using Wikipedia, But Wikipedia Is 40% Wrong

Silicon Valley calls it intelligence. The rest of us call it a hallucination with Wi‑Fi. Continue reading on Medium »

We Built AI Using Wikipedia, But Wikipedia Is 40% Wrong

Medium · ChatGPT 🧠 Large Language Models ⚡ AI Lesson 2d ago

We Built AI Using Wikipedia, But Wikipedia Is 40% Wrong

Silicon Valley calls it intelligence. The rest of us call it a hallucination with Wi‑Fi. Continue reading on Medium »

Why LLMs Hallucinate: When AI Sounds Right but Gets it Wrong

Medium · LLM 🧠 Large Language Models ⚡ AI Lesson 2d ago

Why LLMs Hallucinate: When AI Sounds Right but Gets it Wrong

AI Engineer Interview Preparation Continue reading on Medium »

The Prompt Quality Report: What 1,000 Scored Prompts Reveal

Dev.to · Francisco Ferreira 🧠 Large Language Models ⚡ AI Lesson 2d ago

The Prompt Quality Report: What 1,000 Scored Prompts Reveal

We scored over 1,000 real prompts (average 52/100). Original data on what separates a good prompt from a bad one.

OpenAI News 🧠 Large Language Models ⚡ AI Lesson 2d ago

Introducing GPT-Live

A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.