Blog

AI engineering insights, practical advice, and things I'm learning.

Latest AI news, updated daily. Go to News →

Ai Engineering

How to Speed Up MoE Fine-Tuning With NeMo AutoModel

Learn how to configure NVIDIA NeMo AutoModel in Transformers v5 to increase MoE training throughput and reduce GPU memory usage.

Mixture Of Experts · Nvidia Nemo · Model Fine Tuning

Ai Agents

Local LLMs Hit 88% Accuracy Triaging OpenClaw Pull Requests

Learn how to build a local AI triage system for GitHub repositories using Hugging Face Text Generation Inference, smolagents, and Command R.

Local Llms · Github Automation · Smolagents

Ai Agents

How to Build Single-File Agents With IBM's CUGA Framework

Learn how to manage execution loops, state tracking, and secure tool invocations using the CUGA agent harness and its new FastAPI application templates.

Ai Development · Ibm Cuga · Agent Harness

Ai Agents

How to Deploy Cloudflare Workers via Temporary Accounts

Learn how to use Wrangler 4.102.0 to provision 60-minute temporary Cloudflare environments for autonomous AI agents without authentication hurdles.

Cloudflare Workers · Wrangler Deploy · Autonomous Agents

Ai Engineering

How to Secure Claude API Workloads With Identity Federation

You will learn how to configure Workload Identity Federation to authenticate non-human Claude API requests and eliminate static access keys.

Claude Api · Workload Identity Federation · Cloud Security

Ai Engineering

How to Configure Sparse-LoRA and DoRA With Hugging Face PEFT

Learn how to use PEFT 0.18.0 to configure Sparse-LoRA, DoRA, LoRA-XS, and rsLoRA for more efficient fine-tuning on single-GPU hardware.

Parameter Efficient Fine Tuning · Hugging Face Peft · Large Language Models

Ai Coding

How to Manage Claude Code Workflows via CLAUDE.md

Learn how to control Claude Code's agentic behavior using CLAUDE.md files, reusable skills, lifecycle hooks, and isolated subagents.

Claude Code · Agentic Workflows · Developer Tools

Ai Agents

How to Benchmark Custom AI Agent Tools via Hugging Face

Learn how to evaluate open-weights models against your proprietary APIs using Hugging Face's private benchmarking framework and sandboxed environments.

Hugging Face · Benchmarking · Open Weights

Ai Agents

How to Build Hybrid Agent UIs With A2UI v0.9 and MCP

Learn how to architect hybrid agent interfaces by combining declarative A2UI intent payloads with iframe-based Model Context Protocol applications.

Hybrid Agent Ui · Model Context Protocol · Mcp Apps

Ai Agents

How to Automate Zero Trust via Cloudflare One Stack Agents

Learn how to automate Zero Trust migrations and map security policies using the new AI agent skills in the Cloudflare One stack.

Zero Trust · Cloudflare One · Agentic Workflows

Ai Agents

How to Deploy Strands Agents to Robot Hardware via LeRobot

Learn how to use AWS Strands Agents and Hugging Face LeRobot to deploy vision-language-action policies from MuJoCo simulations directly to physical hardware.

Robotics · Computer Vision · Hardware Deployment

Ai Agents

How to Govern Cursor Agent Autonomy With Auto-Review

Configure Cursor's Auto-review classifier to manage agent permissions, evaluate tool context, and prevent unauthorized actions without approval fatigue.

Cursor Ai · Agentic Workflows · Governance And Security

Ai Engineering

How to Run In-Loop Model Evaluations With olmo-eval

Learn how to set up olmo-eval to test large language model checkpoints during the training process using vLLM, LiteLLM, and Docker-based agent sandboxes.

Llm Evaluation · Model Training · Vllm

Ai Engineering

How to Fuse PyTorch MLP Kernels for a 30% Inference Speedup

Learn how to analyze PyTorch profiler traces and implement Liger kernel fusion to significantly reduce memory bandwidth bottlenecks in transformer models.

Pytorch · Kernel Fusion · Inference Optimization

Ai Engineering

How to Serve DiffusionGemma Locally With vLLM

Learn how to deploy Google's 26B text diffusion model on local hardware to achieve massive parallel generation speeds using vLLM and Hugging Face.

Diffusion Models · Local Deployment · Vllm Inference

Ai Engineering

How to Route GPU GitHub Actions to Hugging Face Jobs

Offload your training and GPU-heavy CI workloads to Hugging Face Jobs using their new ephemeral GitHub runners and action integrations.

Github Actions · Hugging Face · Gpu Computing

Ai Agents

How to Chain Hugging Face Spaces Using the /agents.md Endpoint

You will learn how to orchestrate text-to-image and 3D modeling tools by chaining Hugging Face Spaces together using the universal markdown tool interface.

Hugging Face · Agentic Workflows · Api Orchestration

Ai Engineering

How to Call Claude 4.5 via Apple Foundation Models Framework

Learn how to integrate Claude 4.5 into your Swift applications using Apple's new Foundation Models framework for hybrid on-device and cloud processing.

Claude 4 5 · Apple Foundation Models · Swift Programming

Ai Engineering

How to Provision Google Colab GPUs From the Command Line

Learn how to install the Google Colab CLI, provision high-performance remote GPUs from your local terminal, and execute headless machine learning workflows.

Google Colab · Gpu Provisioning · Command Line Interface

Ai Agents

How to Expose the Hugging Face Hub to Coding Agents via hf CLI

Learn how to use the newly redesigned hf CLI to provide coding agents like Claude Code and Cursor with direct access to Hugging Face models and datasets.

Hugging Face · Cli Tools · Agentic Workflows