The Workstation Blog
LLM
Posts tagged LLM.
What is Deep Learning? Workstation Guide for Builders & Business
Workstation rewrite of AWS What is Deep Learning: neural networks, generative AI, vision/speech/NLP/recommendations, and how teams ship DL in the cloud or on Kubernetes.
Balinder WaliaRead 
Kimi K3 & Open Weights: Frontier Agents Without Locked-In APIs
Kimi K3 pushes open-weight models into frontier agent territory. What changed for developers, vLLM serving, MCP, and Workstation production advice.
Balinder WaliaRead 
Claude Opus 5 on AWS: Workstation Guide for Builders & Business
Workstation take on Claude Opus 5 on Amazon Bedrock: agentic coding, long-running agents, 1M context, ZDR by default, and how teams should adopt it.
Balinder WaliaRead 
Amazon Bedrock, AgentCore, SageMaker & Q: Agents in Microsoft Teams
Implement Amazon Bedrock, Bedrock AgentCore, SageMaker, and Amazon Q, then launch a first business agent in Microsoft Teams — with requirements, tooling, and time boxes.
Balinder WaliaRead 
Claude Models Compared: Haiku vs Sonnet vs Opus vs Fable 5 (Mythos 5)
Choose the right Claude model tier: Haiku for fast routing, Sonnet for daily work, Opus for complex agentic coding, and Fable 5 for long-horizon autonomy. Includes a token-budget router blueprint.
Balinder WaliaRead 
Claude Fable 5: The Complete Guide to Anthropic's Mythos-Class Model
Claude Fable 5 is Anthropic's Mythos-class frontier model for long-horizon agents. Community reactions, YouTube reviews, when to use it, and how to save tokens.
Balinder WaliaRead 
Large Language Models Explained: How LLMs Work and How to Run Your Own on Kubernetes
What are Large Language Models and how do they work? A clear, non-technical explainer for managers and engineers — tokens, embeddings, transformers, training and inference — plus production Kubernetes YAML to deploy your own LLM with Ollama and vLLM.
Balinder WaliaRead 
Unboxing Mac Studio M4 and Running Your First LLM
I unboxed a Mac Studio M4 Max with 128 GB unified memory and 40 GPU cores, installed Ollama, ran Llama 3.1 8B locally, and built a private RAG pipeline - all on one quiet, 6.48 W idle desk-side box.
Balinder WaliaRead 
