Weekly digest
The week on HuiaHub: sandboxed agents, RAG tooling and local models
41 new HuiaHub pages this week: sandboxing coding agents, RAG retrieval, local models on Macs and phones, Claude Haiku 5.5 and six how-to guides.
· 4 min read
The HuiaHub Blog
Guides that respect your time.
Tutorials, comparisons, explainers and news, researched from official docs, repositories and papers. Every page lists what it was built from.
12 articles
ExplainerAgents & automationAI agents found in US bank accounts: what banks are blocking and why
See which banks are restricting AI agents in bank accounts, how read-only access differs from credential sharing, and which claims remain unverified.
10 min read
GuideCoding & dev toolsPHP critical security update CVE-2026-109618: Versions and patch steps
Check the PHP critical security update CVE-2026-109618, identify affected servers, install fixed PHP versions, and apply temporary settings if needed.
12 min read
NewsHow NVIDIA fine-tuned Nemotron 3 for gold-level IOI and IMO 2026 results
NVIDIA details how SFT, RL and test-time loops took Nemotron 3 to gold-level IOI and IMO 2026 results, and which checkpoints and datasets are open.
4 min read
NewsMicrosoft rebuilds Agent Lightning to train agents in their real harnesses
Microsoft rebuilt Agent Lightning as a 3,500-line RL framework that trains agents through the harnesses they already run. What changed for RL teams.
4 min read
- News
GitHub Copilot local sandboxing reaches general availability
GitHub made local sandboxing for Copilot generally available, limiting what agent-run commands can touch. Setup, OS needs and gaps for teams.
4 min read
- News
GitHub moves AI secret detection to a fine-tuned model and AI Credits
GitHub moved AI secret detection to a fine-tuned model and set AI Credit billing for push protection and Copilot checks. What changes for security teams.
4 min read
- TutorialModels & inference
Fine tune LLM LoRA adapters: data, training and a first test on one GPU
Fine tune LLM LoRA adapters on one GPU: check that fine-tuning fits, prepare data, train with PEFT and TRL or Unsloth, and compare against the base model.
6 min read
- TutorialAgents & automation
How to test MCP server tools with the Inspector, unit tests and a client script
Test MCP server tools in three layers: explore them in the MCP Inspector, unit test the tool logic, and run a scripted client check in CI.
7 min read
- GuideModels & inference
Prompt caching with the OpenAI, Claude and Gemini APIs: what is cached and what breaks it
Compare prompt caching API rules for OpenAI, Claude and Gemini, order prompts so the cache hits, avoid silent misses and measure savings from usage fields.
8 min read
- TutorialEvaluation & observability
How to evaluate a RAG pipeline with Ragas: metrics, a test set and a first run
Set up RAG evaluation with Ragas: build a small test set, match each metric to retrieval or generation, run a first score and compare two versions.
7 min read
- GuideRAG, search & data
Best embedding model for RAG: how to choose by size, dimensions, languages and cost
Pick the best embedding model for RAG by language, context length, vector size, hosting and price, then test it on your own documents first.
6 min read
- GuideCoding & dev tools
Sandbox AI coding agent setup: permissions, containers and network limits
Set up a sandbox AI coding agent in Claude Code, Codex, Copilot or Docker, see what each boundary blocks, and spot the gaps it leaves open.
7 min read