What Is PewDiePie Building? | For Beginners
Learn how to build local AI agents using Odysseus and llama.cpp. We break down agent harnesses, tool calling, and fine-tuning Qwen 3.5 9B on agent traces for maximum privacy and control.
Read articleTopic
Model Fine-Tuning
All digests tagged Model Fine-Tuning
Suggested route
Topic journey
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Start here
40 Trillion Tokens a Day (Yes, More Than OpenAI) | Lin Qiao, CEO of Fireworks The future of AI belongs to specialized intelligence, leveraging private enterprise data over general APIs. Learn how customized models and advanced training techniques drive the next frontier in AI infrastructure.Build context
GLM-5.2: Open Weights, Near-Frontier Intelligence — Zixuan Li, Z.ai Z.ai unveils GLM-5.2, an open-weights LLM achieving near-frontier intelligence. It excels in coding and agentic tasks, allowing enterprises to deploy and fine-tune the model on-premise for maximum security and control. Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava The key architectural decision in enterprise AI is determining if knowledge belongs in the prompt (behavior), memory (facts), or weights (reflexes). This is not a ladder, but three distinct tools.Recent signals
What Is PewDiePie Building? | For Beginners Learn how to build local AI agents using Odysseus and llama.cpp. We break down agent harnesses, tool calling, and fine-tuning Qwen 3.5 9B on agent traces for maximum privacy and control. Stop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI — Fireworks AI Learn how to build a continuous 'train-to-deploy' AI loop using open models. Discover FireAttention, custom CUDA kernels, and advanced training methods to match closed-source model quality at scale. Customizing Vertical Voice Agents with ASR and LLM Fine-Tuning | Nemotron Labs Learn how to build domain-specific voice agents by fine-tuning ASR and LLMs. We cover low-latency architecture, WebRTC best practices, and advanced model customization techniques.
Stop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI — Fireworks AI
Learn how to build a continuous 'train-to-deploy' AI loop using open models. Discover FireAttention, custom CUDA kernels, and advanced training methods to match closed-source model quality at scale.
Read article
Customizing Vertical Voice Agents with ASR and LLM Fine-Tuning | Nemotron Labs
Learn how to build domain-specific voice agents by fine-tuning ASR and LLMs. We cover low-latency architecture, WebRTC best practices, and advanced model customization techniques.
Read article
Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava
The key architectural decision in enterprise AI is determining if knowledge belongs in the prompt (behavior), memory (facts), or weights (reflexes). This is not a ladder, but three distinct tools.
Read article
GLM-5.2: Open Weights, Near-Frontier Intelligence — Zixuan Li, Z.ai
Z.ai unveils GLM-5.2, an open-weights LLM achieving near-frontier intelligence. It excels in coding and agentic tasks, allowing enterprises to deploy and fine-tune the model on-premise for maximum security and control.
Read article
40 Trillion Tokens a Day (Yes, More Than OpenAI) | Lin Qiao, CEO of Fireworks
The future of AI belongs to specialized intelligence, leveraging private enterprise data over general APIs. Learn how customized models and advanced training techniques drive the next frontier in AI infrastructure.
Read article