LLM News and Articles

194 of 100
Wednesday, 2025-12-17
06:52What is time-series forecasting and what models might you use (ARIMA, ETS, Prophet)?
06:48The Community Stories of vLLM and SGL
06:30Collaborative LLM Evaluation at Scale: Inside the InsightFinder Demo
06:26GPT-5.2 vs Previous Models: A Technical Evolution
06:23Simulating stock analysts with Databricks LLM
06:16Mem0 — Overall Architecture and Principles
06:16Export Your Brain: A Simple Way To Make Any AI “Know You” From Day One
06:13Transformers & LLMs — Part 2: The Transformer Revolution
06:10Transformers & LLMs — Part 1: The Foundations of NLP
06:09Emergent Affective Computing: The Unintended Evolution of Machine Emotional Intelligence
05:26GPT-5.2-high LMArena scores released, OpenAI falls from #6 to #13
04:46Composable AI: How Model Swarms Enable Scalable, Governable Intelligence
04:29Introduction to LLaMA 3: Running Open-Source LLMs Locally
04:15Day 9: 21 Days of Building a Small Language Model: MultiHead Attention
04:07Kesadaran Kuantum Dalam Tubuh Model Bahasa Besar (LLM): Menuju Kecerdasan Buatan Umum (AGI) Yang…
03:08Self-Describing Rewrite Intelligence (SRIM): No-Meta Continual Inference-Learning as Certified…
02:57Nemotron 3 Nano: The Open Model Built for the Age of Multi-Agent AI
02:52NVIDIA Nemotron 3 Nano: The Open 30B Model That’s Faster Than GPT-OSS and Qwen — And Runs Locally
02:49Target Modules: The Secret Weapon of Efficient AI Fine-Tuning
02:26The Age of Inference: Why AI’s Real Bottleneck Is No Longer Training
02:10How to Become an AI Engineer in 2026
02:00The Syntax of the Scar: The Day My AI Felt Pain to Avoid Failure
01:403 ways to integrate ai into a platform’s interface (and go to the Caribbean)
01:37Training GPT-2 on a Budget: How We Got 90%+ Performance with 1/10th the Data
01:32Training a Time‑Locked LLM on 1800s London Texts
00:34The Architecture Pattern Cutting AI Costs (While You’re Still Debugging Mega-Prompts)
00:26Rodando LLM local em um notebook comum
00:20The Control Paradox: Why “Natural Language Precepts” Beat “Python Validation” in AI Alignment
00:14The L7 Civilization is Facing a Crisis of Meaning — and our Only Window to fix it is closing.
00:08Hosting LLMs — From Fundamentals to Scaled Production (with Hands-On Tutorial)
00:04Show HN: Python packages for FastAPI apps – auth, logging, config, LLM, more
00:02How I 10x’d My AI Products’ Performance with 10 Prompt Engineering Techniques
Tuesday, 2025-12-16
23:3509918041424
23:3409918041424
23:07Using LLM Tool Executor Without Nightmares — Sandshrew
23:01I had a private chat with an LLM
22:51Vibe Coding: Real Code, Real Risks, or Both?
22:50The AI Red Team Maturity Model: A Capability-Based Framework for LLM Security Testing
22:48I ported JustHTML from Python to JavaScript with Codex CLI and GPT-5.2 in hours
22:36A Giant Brain with a Library Card: Demystifying LLMs and RAG
22:34Learning in the age of AI
22:02The AI Reading List That Got Out of Hand
21:58RAG vs. The Infinite Context Window: Is Retrieval Dead in 2026?
21:38The Smartest Thing About AI Right Now? Getting Smaller.
21:198 “” …
21:16The Hard-Won Lessons of Building an Agentic AI Visibility Engine
20:54George Osborne Joins OpenAI
20:51The Complete Guide to Prompt Engineering
20:50Fastweb + Vodafone: Transforming Customer Experience with AI Agents using LangGraph and LangSmith
20:50Fastweb + Vodafone: Transforming Customer Experience with AI Agents using LangGraph and LangSmith
20:50Content Strategy in the Era of AI
20:02Inside Alibaba’s Qwen: How China Built One of the World’s Fastest-Growing AI Models
20:00Gpt 5.2 is good but …
19:43Review of Andrej Karpathy’s AI Startup School talk
19:09Serve an Open-Source LLM
19:02The RAG Bottleneck Nobody’s Fixing (And Why Your Retrieval Doesn’t Matter)
18:57LLMs Are Not Enough: Introducing Large Action Models (LAM)
18:37It matters if AI “wrote” it
18:28Going beyond prompting
18:27Xiaomi MiMo-V2-Flash a Technical Review
18:13Sky-high token bills? 9 Practical Ways to Cut Your AI/LLM Token Usage Without Compromising Quality
18:10SNACK-AI:
18:07Show HN: Let ChatGPT create interactive forms and surveys for you
18:07GPT Image 1.5
18:05OpenAI Rolls Back ChatGPT's Model Router System for Most Users
17:58The new ChatGPT Images is here
17:58Are LLMs Making Us Less Expressive?
17:44Why Your AI Ignores Your Rules — And How To Make It Stop
17:21Introspection & Self-Improvement Algorithms: LM's Self-learning to Self-Reason — Part 3
16:52How LLMs Like ChatGPT Actually Work — A Clear, Practical Breakdown (33 Core Concepts)
16:45TAI #183: GPT-5.2 Arrives with a Breakthrough on GDPVal and long context
16:42AI Doesn’t Think — It Just Needs to Talk More: The Wild Truth About “Blah Blah Blah” Reasoning
16:42Stop Writing Prompts. Start Building Systems.
16:35MiMo-V2-Flash: High-Efficiency Inference, Code and Agent Foundation Model
16:34GPT-5.2 & Long-Running Agents
16:33The Silent Context Truncation That Made Our RAG Answers Wrong
16:32Prompt caching: 10x cheaper LLM tokens, but how?
16:25The Hidden Geometry of Intelligence: Why GPT-2 Looks Like a Helix (and How I Visualized It in 3D)
16:22Benchmarking Claude 4.5 Sonnet vs Claude 4.5 Opus for Penetration testing
16:11The Evolution of LMMs
16:02The widespread use of AI: how it challenges the SEO of businesses
16:02The Complete Guide to Local LLM Hardware: Specs for Running AI Models on Consumer Hardware
16:02The Complete Guide to Local LLM Hardware: Specs for Running AI Models on Consumer Hardware
15:55Formal Verification of LLM Safety with Zero Knowledge Proofs
15:55Context Engineering in Agno: The Definitive Guide to Building Reliable AI Agents
15:50Why AI Agents Excel at Programming Tasks
15:45Production-Grade LLM Prompt Optimization: Caching, Architecture, and Benchmarking in December 2024
15:40ChinaRxiv – Automatically translated preprints from the Chinese ArXiv
15:33Tokenization Explained Like You’re Five (LLM Series -2)
15:32Part 3: Automating Insurance Claim Admissibility
15:31Part 4 — Working with Text Data
15:17The Enshittification of AI Chatbots: Why They Get Worse (and What You Can Do)
15:13Pair Programming, Copilot Agents, and Cost of Not Asking Questions
15:08AI Agent Deployment Strategies: A Practical Guide
14:52The Great Agent Paradox: Why More AI Doesn’t Always Mean Better
14:49Mistral Just Changed the Game: Devstral 2 Brings Claude-Level Coding to Open Source
14:39Show HN: Solving the ~95% legislative coverage gap using LLM's
14:35The Two-Layer Persona Framework:
14:16From Raw Data to Responsible Intelligence: Inside the Real Lifecycle of Generative AI
14:12Anyone With API Access Can Clone an AI Model and Make It Unsafe
194 of 100
Was this helpful?
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124