Core AI

Large Language Models

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

24,926
lessons
Skills in this topic
View full skill map →
LLM Foundations
beginner
Explain how transformers generate text
Prompt Craft
beginner
Write zero-shot and few-shot prompts
LLM Engineering
intermediate
Call LLM APIs with function/tool use
Fine-tuning LLMs
advanced
Prepare fine-tuning datasets
Multimodal LLMs
advanced
Use GPT-4V / Claude Vision for image understanding

Showing 5,466 reads from curated sources

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control
arXiv:2506.14391v3 Announce Type: replace-cross Abstract: Adaptive traffic signal control (ATSC) is essential for mitigating urban congestion in modern smart ci
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Mapping Caregiver Needs to AI Chatbot Design: Strengths and Gaps in Mental Health Support for Alzheimer's and Dementia Caregivers
arXiv:2506.15047v2 Announce Type: replace-cross Abstract: Family caregivers of individuals with Alzheimer's Disease and Related Dementia (AD/ADRD) face signific
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
arXiv:2509.19080v2 Announce Type: replace-cross Abstract: Robotic manipulation policies are commonly initialized through imitation learning, but their performan
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Responsible AI Technical Report
arXiv:2509.20057v4 Announce Type: replace-cross Abstract: KT developed a Responsible AI (RAI) assessment methodology and risk mitigation technologies to ensure
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning
arXiv:2509.24773v4 Announce Type: replace-cross Abstract: Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTT
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
FinReflectKG -- EvalBench: Benchmarking Financial KG with Multi-Dimensional Evaluation
arXiv:2510.05710v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used to extract structured knowledge from unstruct
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
CARES: Context-Aware Resolution Selector for VLMs
arXiv:2510.19496v2 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain eff
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Rep2Text: Decoding Full Text from a Single LLM Token Representation
arXiv:2511.06571v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their interna
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
arXiv:2511.16665v3 Announce Type: replace-cross Abstract: The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant m
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs
arXiv:2511.21448v5 Announce Type: replace-cross Abstract: In this paper, we introduce a metadata-enriched generation framework (PhishFuzzer) that seeds real ema
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis
arXiv:2601.03018v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown strong performance on clinical text understanding, they
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness
arXiv:2601.03273v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer modera
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
arXiv:2602.08934v2 Announce Type: replace-cross Abstract: AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
LHAW: Controllable Underspecification for Long-Horizon Tasks
arXiv:2602.10525v2 Announce Type: replace-cross Abstract: Long-horizon workflow agents that operate effectively over extended periods are essential for truly au
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
The Art of Efficient Reasoning: Data, Reward, and Optimization
arXiv:2602.20945v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but al
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
arXiv:2602.21424v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) agents under partial observability often condition actions on internally a
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
arXiv:2603.00523v2 Announce Type: replace-cross Abstract: Every mechanistic circuit carries an invisible asterisk: it reflects not just the model's computation,
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
arXiv:2603.01038v2 Announce Type: replace-cross Abstract: Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FA
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
arXiv:2603.12180v2 Announce Type: replace-cross Abstract: Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a cr
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Prompt Injection as Role Confusion
arXiv:2603.12277v2 Announce Type: replace-cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training. We tr
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
arXiv:2603.15727v2 Announce Type: replace-cross Abstract: Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnec
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
arXiv:2603.16513v2 Announce Type: replace-cross Abstract: Structured data is foundational to healthcare, finance, e-commerce, and scientific data management. La
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
arXiv:2603.18062v2 Announce Type: replace-cross Abstract: Skeleton-based action recognition is crucial for multimedia applications but heavily relies on power-h
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Understanding Task Aggregation for Generalizable Ultrasound Foundation Models
arXiv:2603.18123v2 Announce Type: replace-cross Abstract: Foundation models promise to unify multiple clinical tasks within a single framework, but recent ultra
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
Retrieval-Augmented LLMs for Security Incident Analysis
arXiv:2603.18196v2 Announce Type: replace-cross Abstract: Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sou
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
arXiv:2603.18202v2 Announce Type: replace-cross Abstract: A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representatio
ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago
PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents
arXiv:2603.18377v2 Announce Type: replace-cross Abstract: Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordi
OpenAI News 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Creating with Sora Safely
To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app wi
All We Need Is Memory, Dealing With The AI RAMpocalypse
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
All We Need Is Memory, Dealing With The AI RAMpocalypse
Nvidia announcements show the current shortage of storage and memory could continue into the future, driving up prices and the value of the companies that produ
Lossy self-improvement
Interconnects 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Lossy self-improvement
The case for why self-improvement is real but it doesn't lead to fast takeoff.
TechCrunch AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Cursor admits its new coding model was built on top of Moonshot AI’s Kimi
Building on top of a Chinese model feels particularly fraught right now.
Amazon Alexa Plus: Panos Panay On How The ‘Brilliant’ New AI Is Ready Now
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Amazon Alexa Plus: Panos Panay On How The ‘Brilliant’ New AI Is Ready Now
Alexa+ is now available in the U.K., with careful localization. Amazon’s Panos Panay explains why the generative AI upgrade is ready for British homes.
AI Agents Wrote 80% Of Karpathy's Code. Junior Developers Are Paying The Price
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
AI Agents Wrote 80% Of Karpathy's Code. Junior Developers Are Paying The Price
OpenAI co-founder Andrej Karpathy says December 2025 was the inflection point. The data — and the job market — are beginning to agree.
2 Reasons I Turned Off My OpenClaw, My Personal AI Assistant
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
2 Reasons I Turned Off My OpenClaw, My Personal AI Assistant
this article explains the reasons that Paul Baier stopped using OpenClaw. These are the rawness of the software and lack of security
Vehicle AI Has A Blind Spot: Tesla FSD And GM Super Cruise In Focus
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Vehicle AI Has A Blind Spot: Tesla FSD And GM Super Cruise In Focus
Tesla Full Self-Driving and General Motors Super Cruise are seminal technologies. But vehicle AI is not flawless and drivers don’t always understand its limitat
Towards Data Science 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Prompt Caching with the OpenAI API: A Full Hands-On Python tutorial
A step-by-step guide to making your OpenAI apps faster, cheaper, and more efficient The post Prompt Caching with the OpenAI API: A Full Hands-On Python tutorial
TechCrunch AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
An exclusive tour of Amazon’s Trainium lab, the chip that’s won over Anthropic, OpenAI, even Apple
Shortly after Amazon announced its $50 billion investment in OpenAI, AWS invited me on a private tour of the chip lab at the heart of the deal.
The Real AI Race Is Not The One You Think
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
The Real AI Race Is Not The One You Think
Beneath the highly visible yet often counterproductive AI consumption race lies a far more consequential one: the race for AI production.
Why We Don’t Have More AI Power Users In The Age Of AI
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Why We Don’t Have More AI Power Users In The Age Of AI
It's critical is to identify and bring along the power users who will expand the capabilities of AI. But where are they?
InfoQ AI/ML 🧠 Large Language Models ⚡ AI Lesson 1mo ago
QCon London AI Coding State of the Game: More Capable, More Expensive, More Dangerous Coding Agents
In her QCon London keynote, Birgitta Böckeler, AI-Coding lead at Thoughtworks, reflected on the changes in the AI coding space over the past year. She emphasise
Taxonomy For Creating AI Personas In Mental Health Encompassing Therapists, Clients, Supervisors, Evaluators
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Taxonomy For Creating AI Personas In Mental Health Encompassing Therapists, Clients, Supervisors, Evaluators
I have created four sets of taxonomies checklists to invoke AI personas for a synthetic therapist, client, therapist-supervisor, and therapy evaluator. An AI In
TechCrunch AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Publisher pulls horror novel ‘Shy Girl’ over AI concerns
Hachette Book Group said it will not be publishing “Shy Girl” over concerns that artificial intelligence was used to generate the text.
Apple Blocks Vibe Coding Tools From Store
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Apple Blocks Vibe Coding Tools From Store
Apple restricts vibe-coding apps; coding itself legal, but publishing insecure AI apps may trigger liability.
TechCrunch AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
Why Wall Street wasn’t won over by Nvidia’s big conference
Despite investor fears of an AI bubble, Nvidia's latest conference shows that most in the industry aren't concerned by that possibility.
AI’s Missing Capability Is Not Intelligence But Integrity
Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago
AI’s Missing Capability Is Not Intelligence But Integrity
Recent developments in AI make this clear: an AI system with intelligence but without integrity is structurally unfit for civilization.
Hacker News (AI) 🧠 Large Language Models ⚡ AI Lesson 1mo ago
The next phase of artificial intelligence may require different processors
Article URL: https://www.economist.com/science-and-technology/2026/03/18/the-next-phase-of-artificial-intelligence-may-require-very-different-processors Comment
I Tried DoorDash’s Tasks App and Saw the Bleak Future of AI Gig Work
Wired AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
I Tried DoorDash’s Tasks App and Saw the Bleak Future of AI Gig Work
I recorded videos of myself doing laundry, scrambling eggs, and walking around the park in DoorDash’s new Tasks app, where gig workers are paid to train AI.
ZDNet AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago
4 tips for building better AI agents that your business can trust
Agents are coming. Here are four ways to prepare for the AI-powered workplace revolution.