Approvals default to smart mode: an auxiliary model waves through low-risk commands, auto-denies genuinely dangerous ones, and escalates the uncertain cases to you. Neither `--yolo` nor `approvals.mode: off` can disable the hardline blocklist (`rm -rf /`, fork bombs, `dd` to a physical disk), and `approvals.deny` is its user-editable counterpart, evaluated before yolo. Upstream is explicit that the threat model is an honest-but-wrong agent, not an adversarial process.
Hermes can run commands on seven backends: local, ssh, docker, singularity, modal, daytona, and vercel_sandbox. The decisive trade-off isn't performance, it's approval — local and ssh run dangerous-command checks, the other five skip them entirely because the container is treated as the boundary. Also, Docker defaults to one long-lived container shared across sessions, not a fresh environment per conversation.
The Tool Gateway routes four tool categories — web search (Firecrawl), image generation (nine FAL models), TTS (OpenAI), and cloud browser (Browser Use) — through Nous infrastructure, replacing four signups with one OAuth. It's per-tool rather than all-or-nothing, and `use_gateway: true` overrides any direct key in your `.env` — the precedence rule people most often get wrong.
Attach enough MCP servers and the tool schemas alone eat your context — upstream's extreme example is Cloudflare's ~3,300 tools, whose names alone run about 32K tokens. Hermes answers with Tool Search: MCP and non-core plugin tools collapse into three bridge tools and schemas load on demand, while core tools never defer. Separately, plugins are disabled by default and only run when named in `plugins.enabled`.
AB-100 is the architect tier of Microsoft's agent line, weighted 25-30 / 25-30 / 40-45 with deployment and governance heaviest. Its outline runs on verbs like design, recommend, and propose — it tests judgment, not configuration. Three things to know first: it has a prerequisite — besides passing AB-100 you must hold one of the associate certifications on the official list (AI-103, AB-620, and AI-300 are all on it); it has a free practice assessment, the only one of Microsoft's three agent credentials that does; and one blurb on the exam page describes a compliance exam instead, so prepare from the study guide. Official specs: $165 in the US, 13 languages including Traditional Chinese, pass at 700, one-year validity.
AB-620 is the low-code branch of Microsoft's agent certification line — it tests agent flows, adaptive cards, computer use, MCP tools, A2A, and Fabric data agents in Copilot Studio, not Python. The three skill areas weigh 30-35 / 40-45 / 20-25, with integration the heaviest. Official specs: $165, 120 minutes, pass at 700, one-year validity, and 13 languages including Traditional Chinese. It is generally available, but the practice assessment is not out yet.
AI-103 replaces AI-102, retired June 30, 2026, and the objectives were rewritten around Microsoft Foundry — prompt flow, Azure AI Studio, Azure OpenAI Service, and Azure AI Agent Service appear nowhere in them. The five skill areas weigh 25-30 / 30-35 / 10-15 / 10-15 / 10-15, with generative AI and agents the largest. Official specs: $165, 120 minutes, pass at 700, offered in Traditional Chinese, may include interactive components — and it is valid for only one year, though renewal is a free, open-book, unproctored online assessment.
AI-500 is a rare thing among the major clouds — an expert-level certification dedicated to multi-agent systems, weighted 15-20 / 30-35 / 20-25 / 20-25, naming Agent Framework, LangGraph, Hugging Face Transformers, MCP servers on Azure Functions / Logic Apps / API Management, A2A, Key Vault, and the AI Red Teaming Agent. Two constraints come first: it requires AI-103 before you can take it, and neither the official learning paths nor a practice assessment is live yet. Microsoft removed the beta label from its pages at the end of September 2026.
NCA-GENL is usually what a job posting means by 'NVIDIA Generative AI / LLM certification.' But the official blueprint diverges sharply from the name — Core Machine Learning and AI Knowledge 30%, Software Development 24%, Experimentation 22%, Data Analysis 14%, Trustworthy AI 10% — with LLM and RAG content scattered at bullet level rather than forming a domain, alongside spaCy, NumPy, Keras, and cross validation. The other thing to know first: the official recommended training was replaced in autumn 2026, and each area now lists just two items, free open-source deep learning course materials on GitHub and one LLM application development course. Official specs: $125, 1 hour, 50–60 items, two-year validity, English only, pass/fail with no score reported.
NCA-GENM matches NCA-GENL on price, length, and level but not on emphasis: Experimentation rises to 25% (the heaviest), Core ML drops from 30% to 20%, and two new areas appear — Multimodal Data 15% and Performance Optimization 10%. The content covers U-Net, CLIP, diffusion models, multimodal loss functions, attention maps, and NVIDIA's Riva / NeMo / Triton / ACE SDKs. The official recommended training was replaced in autumn 2026: it is now one free open-source set of deep learning materials on GitHub plus one multimodal agent course, assigned differently per area, with the heaviest area, Experimentation, getting only the free materials. Official specs: $125, 1 hour, 50–60 items, two-year validity, English only.
NCP-AAI is NVIDIA's professional-level agentic AI credential — $200, 120 minutes, 60–70 items, two-year validity. Of its ten areas the heaviest are Agent Architecture and Design at 15% and Agent Development at 15%; only NVIDIA Platform Implementation at 7% is explicitly tied to NVIDIA products, and the rest is general agentic engineering. Two things to know first: registration is not open (the Register button carries a 'Coming soon' label), and the web page and the PDF study guide differ on two weights (Deployment and Scaling 13% versus 5%, Run/Monitor/Maintain 5% versus 7%), so budget those as a range.
NCP-GENL is NVIDIA's professional-level LLM credential — $200, 120 minutes, 60–70 items. What separates it from every other GenAI exam is where the weight sits: Model Optimization 17% plus GPU Acceleration 14% is 31% on quantization, distillation, pruning, distributed parallelism, and CUDA profiling — not on calling APIs. Two things to know first: the Register button says Coming soon, so you cannot sit it yet; and the description text for Model Optimization and Fine-Tuning in the web page's weight table is misplaced, so prepare those two areas from the official PDF study guide.
The Workers AI catalog currently holds 84 models. For general chat pick glm-4.7-flash ($0.06 / $0.40 per M, 131K context), for vision pick gemma-4-26b-a4b-it ($0.10 / $0.30, 256K), for cheap high-volume steps pick granite-4.0-h-micro ($0.017 / $0.112), and for embeddings pick qwen3-embedding-0.6b or bge-m3 (both $0.012 per M). This post is updated on a schedule.
Andrew Ng demonstrates error analysis on a deep researcher: columns are the pipeline stages, rows are 10 to 100 queries, you only look at the ones that went badly, and you mark each cell where something broke. The percentages don't have to sum to 100%. He says it takes three or four hours and saves weeks of going the wrong direction — and the fraction of people who actually do it is far below 100%.
Andrew Ng walks a face-recognition door system through the entire project lifecycle, and the whole lecture has one thesis: speed. He gives teams a two-day deadline, on the reasoning that 'time spent preparing data should be commensurate with the time it takes to train the model once.' It closes on a line: my job is to build something that actually works, and that is not the same as building something that works on the test set.
CS230's first lecture is a course overview, but Andrew Ng spends most of it on three things: why scaling works, when prompting stops being enough, and why he thinks 'don't learn to code' is one of the worst pieces of career advice ever given.
Most prep guides start at chapter one. This one works backwards: derive the exam date from each vendor's retake rules (AWS makes you wait 14 calendar days, Google escalates 14 → 60 → 365 days, Microsoft allows a retake after 24 hours, and Taiwan's iPAS has no retake at all — you wait six months for the next session), then order your study by domain weight rather than domain number, and take a free official practice set before studying anything. Includes weightings for seven certifications and a five-week AIF-C01 example.
Every official course platform from OpenAI, Anthropic, and Google, plus Stanford CS146S/CS336, Elements of AI, Hugging Face, MIT 6.S191 and more — scraped page by page, then re-sorted into four tiers: AI-curious, vibe coding, shipping to production, and how models actually work. Also covers self-study repos still being updated in 2026 and browser-based platforms that need no local setup, filtered by last-commit date rather than star count. The conclusion: nearly all of it is free. What is scarce is not courses, it is the judgment to pick one. And tier four will not fix your tier three problem.
arXiv does not perform peer review, and roughly 2% of submissions are rejected. Quality judgment relies on external signals: top venue acceptance > institution + open-source reproduction > citation quality. Includes a 20-item practical checklist and a 2026 toolbox (PWC has shut down).
Spin up a local OpenAI-compatible endpoint at localhost:20128 that automatically routes requests from Claude Code / Cursor / Cline / Codex / Copilot through a Subscription → Cheap → Free 3-tier fallback to 40+ providers. Built-in RTK compresses tool_result (saving 20–40% input tokens), Caveman mode compresses output, OAuth auto-refresh, multi-account round-robin — install with npm install -g 9router and two commands.