Fine-tuning
Pre-training, post-training, fine-tuning, distillation, quantization and the data that feeds them
Latest stories See all →
- GRPO and RLVR: Critic-Free Reinforcement Learning and Verifiable Rewards for Reasoning
- The Ultimate Guide to LLM Fine-Tuning: Full Fine-Tuning, PEFT, LoRA, QLoRA, DoRA & QDoRA
- Fine-Tuning Is Super, Super Hard. Even OpenAI Is Backing Away From It.
- Post-Training
- How to Fine-Tune an LLM [and When to Use RAG or Prompting Instead]
- Prime Intellect Releases Prime Mega MoE: Trainable Fused MoE Kernel, 3.11x Faster Forward Pass
- BeyondWeb Ex Ante: Ensuring Backtest Safety in Synthetic DataResearch Updates29 Oct, 2026
- PII Detection Before RAG Ingestion: Screening Documents in C#
- Modern Cooperative Autonomous Driving Ecosystem
- RAK19003 Meshtastic 1×18650 Weather Resistant Case #3DThursday #3DPrinting
- How we’re training a Figma-fluent editing modelOctober 29, 2026By Josh ClemmWe’ve increasingly seen that specialized post-training can compete with frontier models. Here, we’re sharing the research behind how we’re translating that to design editing workflows.
- SFT vs RLHF Explained: Which Post-Training Stage Actually Needs Your Domain Experts
- Parsy: Distilling an Agentic Parsing Harness into a Fine-Tuned Model
- We Built Our Own Post-Training Stack to Measure What Our Tasks Are Worth
- Why ROUGE Lies About Your LLM Outlines and How Grounded Fine-Tuning Fixes It
- Another View on Context Parallel for LLMs: Balancing Compute
- A new lightweight, hybrid routing mesh protocol for packet radios
- A 55 GB AI Model Was Shrunk to 7.9 GB. It Got Better at One Thing and Worse at Another
- Fine-Tuning vs. Frozen Embeddings: When to Adapt the LLM vs. the Sklearn Head
- RAG Complexity Is a Bet Against the Model
- Errors as Data: How RSI Helps OXR Achieve SOTA Accuracy and Speed in Document Parsing
- DeepSeek-V4 Flash RL on AMD Instinct MI308X GPUs with an AITER-Backed RL Stack
- Build specialized multimodal models with LFM3
- Exowatt beats frontier models on accuracy with SageMaker serverless model customization
Videos
- What Is Quantization? How AI Models Get Smaller & Faster
- Nemotron 3.5 Super VL with Native Speculative Decoding
- Build A Reasoning Model From Scratch 8: Distillation
- EfficientML.ai Lecture 9 - Knowledge-Distillation (MIT 6.5940 Fall 2026)
- How Mixture of Experts Could Make Local LLMs Practical
- EfficientML.ai Lecture 6 - Quantization (Part II) (MIT 6.5940 Fall 2026)
- Complete Mac mini M6 Local LLM Stress Test — 5 Models, 3 Inference Engines
- Xiaomi and DeepSeek Just Solved the Biggest Problem in AI
- LM Studio Full Tutorial - The BEST Way to Run Local Models
- Can A Free 4GB AI Replace Your Cloud AI Coder?
- Your 128GB Of RAM Won't Save A 24GB Card For Local AI
- Optimize KV cache with llm-d and vLLM
Podcasts
Recent episodes
- Do the models you use have an AI bill of materials? | CIQ’s Gregory Kurtzer
- Risky Bulletin: Linux patches PwnEscape KVM vulnerability
- Anthropic's Growth Is Slowing
- Ep. 038 - GLM 5.3 on AMD, NVIDIA, and Chinese Chips From Day One (InferenceX) | Kimbo Chen, Wenyao Gao, Jordan Nanos
- Can Open Models Keep Up With the AI Frontier? | Nathan Lambert
- Can Open Models Keep Up With the AI Frontier? | Nathan Lambert
- Can Open Models Keep Up With the AI Frontier? | Nathan Lambert
- OpenAI’s Head of ChatGPT: We’re entering a new era of AI (again) | Tibo Sottiaux
- Orchestrating local LLMs for sensitive data with Airflow
- Beyond the Buzzword: Why Synthetic Data Is Healthcare's Real Data Breakthrough
- Should You Train Your Own Model?
- Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI