loading tag register... ok
loading matching posts... ok
loading related topics... ok
teds read --tag ai-engineering
AI Engineering
Practical posts on model selection, prototypes, evaluation, AI product decisions, and the path from experiment to useful system.
Related service
Need help turning an AI idea into a useful system? Talk to us about AI engineering consulting.
Why Squeaky-Clean Datasets Break Production Vision Models
Over-cleaning training data strips structured real-world noise, leaving vision models brittle. Build a data preservation list before running cleaning sprints.
BlogA 3-Step Data Quality Pre-Flight Check Before Training Vision Models
New architectures drop every 33 hours, but training success depends on data fundamentals. Run this 3-step audit on resolution, labels, and class balance.
BlogScene Complexity Metrics: Measuring Clutter and Density Beyond mAP
Aggregate mean average precision hides operational failure modes. Use visual clutter scores, instance density, and background complexity to stress-test models.
BlogHands-on Point Tracking in Video with Meta AI CoTracker3 and FiftyOne
Meta AI released CoTracker3 for dense point tracking across video frames. Learn how point tracking works, its mechanics, and how to visualize tracks in FiftyOne.
BlogWhy Duplicate Training Data Silently Corrupts Vision Models
Duplicate images inflate mAP, distort precision-recall curves, and create artificial confidence. Here is how to identify clusters and selectively prune.
BlogDetecting Hidden Outliers in Visual AI Datasets with Embeddings and UMAP
Uncover silent data anomalies before production failure. How to use foundation model embeddings, Local Outlier Factor (LOF), and UMAP projections.
BlogBuilding a Data Quality Feedback Loop for Visual AI Systems
Stop wasting engineering sprints tuning hyperparameters on flawed datasets. Here is how to build a 4-step data-centric evaluation loop for computer vision.
BlogCritical Image Quality Metrics That Break Computer Vision in Production
Vision models fail when real-world camera conditions diverge from training data. How to measure and audit blur, exposure, contrast, and compression artifacts.
Blog10 Open-Source Robotics Repositories for 3D Perception, VLA Policies, and Sensor Calibration
An inspectable technical breakdown of 10 open-source robotics and physical AI GitHub repositories solving training-free 3D occupancy, targetless calibration, 50Hz VLA latency, and humanoid memory.
BlogThe Actuarial Approach to AI Evals: Wilson Confidence Intervals and Statistical Sample Sizing
Why running 20 test cases gives you virtually zero statistical confidence in your agent's reliability, and how to use Wilson score intervals to measure real performance.
BlogHow to Evaluate AI Agents for Production: Moving Beyond LLM-as-a-Judge
Why LLM-as-a-judge fails to protect production agents, the mathematics of compounding multi-turn error, and how to build a state-based evaluation framework that engineering teams can inspect.
BlogEvaluating Agentic Tool Calls and Environment Deltas: The Deterministic Testing Layer
How to test multi-turn AI agents by intercepting tool schemas, snapshotting environment state, and catching parameter hallucination before it touches production infrastructure.
BlogCurating Golden Trajectories: Adversarial Stress-Testing and Red-Teaming for Production Agents
Why happy-path benchmarks miss 90% of production agent outages, and how to build an adversarial golden dataset that stress-tests tool failures, ambiguous inputs, and indirect injection.
BlogBuilding an Agent Evaluation CI/CD Pipeline: Architecture, Budgets, and Regression Gates
A complete engineering blueprint for running autonomous agent evaluation in CI/CD: tiered test runners, statistical regression gates, token budgets, and GitHub Actions orchestration.
BlogMachine-Speed Attacks Break Human-Speed Defenses: Why Zero Trust Must Be Architectural
CyberStrikeAI used 44 autonomous AI agents to industrialize exploitation across 19 organizations in under 24 hours. When threat actors automate the full kill chain, manual SOC triage collapses. Dr. Chase Cunningham warned us years ago: trust is a vulnerability, and defense must be deterministic.
BlogGenerative Engine Optimization (GEO): How AI DevTools Get Cited by Agents
Why developer tools need Generative Engine Optimization (GEO) rather than traditional SEO, and how to structure content so LLMs, Perplexity, and coding agents cite your product.
BlogDevRel for Physical AI and Robotics: Engineering Advocacy for the Real World
Why developer relations for physical AI, robotics, and embodied foundation models requires forward-deployed engineering, data inspection, and hardware-adjacent credibility.
BlogDevRel for AI Developer Tools: The Playbook for Devtools That Actually Ship
The complete guide to developer relations for AI developer tools: earning developer trust, forward-deployed engineering, and avoiding marketing slop.
BlogDevRel for AI Agents: Building Developer Trust When Code Generates Code
How developer relations changes when your product is an AI agent, multi-agent orchestration framework, or agent-native developer tool.
BlogWhy Your AI Agent Evaluations Are Bad Statistics
Frontier agents score 80%+ on short benchmark tasks and still collapse in production. The problem is not the reasoning model—it is evaluating multi-turn stochastic systems with static point estimates.
BlogRobots Can See. They Still Can't Feel: 8 Tactile LeRobot Datasets in FiftyOne
Why touch is the missing frontier for robot learning, how tactile data is structured across gel sensors, force vectors, and taxel grids, and 8 open LeRobot datasets loaded into FiftyOne.
BlogMCAP Authoring Errors: 6 Silent Bugs and How to Fix Them
When authoring MCAP files from robotics logs, errors rarely throw runtime exceptions. The file writes clean and passes validators, yet fails in viewers. Here are the 6 silent bugs and how to fix them.
BlogFrom Franka Arms to Humanoids: 11 LeRobot v3.0 Datasets for VLA Training in 2026
A comprehensive guide to 11 robot-learning datasets converted into LeRobot v3.0 format for inspection in FiftyOne, covering arms, bimanual setups, humanoids, and the robotics data action gap.
BlogEmbeddingGemma 2 in FiftyOne: Search Video by Text, Sound, or Your Webcam
How to use Google DeepMind's EmbeddingGemma 2 inside FiftyOne with LanceDB to search across 10,000 video clips using text, soundtrack audio, or webcam feeds in a shared 768-D space.
BlogBuilding Production-Ready AI Document Understanding Pipelines with GLM-OCR
Why traditional OCR pipelines break on tables and complex layouts, and how GLM-OCR extracts native markdown, LaTeX formulas, and structured JSON inside FiftyOne.
BlogWhy Open Weight Models Matter for Small Businesses
Open weight models give small businesses capable AI without per-token pricing, vendor lock-in, or sending sensitive data to a third party. Deploying them well is a different problem.
BlogHow to Evaluate an AI Agent (Before It Ships)
Agent evaluation is not LLM evaluation. A practical three-layer framework — component, trajectory, outcome — for evaluating AI agents before they reach production, plus a maturity model to figure out where your team is and what to build next.
BlogAI Agents for Commercial Real Estate: From Deal Flow to Due Diligence
How autonomous AI agents — not chatbots — can compress the slowest parts of a commercial real estate practice: prospecting, underwriting, due diligence, zoning research, and reporting.
BlogFrom Chat Window to Workflow: A Non-Technical Guide to AI Model APIs
A plain-language guide to AI model APIs for people who use chat windows but want to automate. Covers requests, responses, parameters, costs, and where to get hands-on practice.
BlogAI Coding for Internal Software Teams
Why non-tech companies with internal developers should train engineers to use AI coding tools with judgment instead of banning them or letting vibe coding run loose.
BlogThe Accidental AI Power User
Why the person using AI chat tools for Excel formulas, macros, reports, and internal workflows may be your company's next productivity multiplier.
BlogWhy Your AI Demo Feels Magical but Useless
How to diagnose the gap between impressive AI demos and reliable AI products by looking at failure modes, workflows, evaluation, and trust.
BlogWhat AI Builders Can Learn from Painters
A practical essay on why models are colors, not masterpieces, and why AI products need composition, constraints, technique, and taste.
BlogStop Asking Can AI Do This
A practical decision guide for replacing capability-first AI thinking with better questions about value, risk, evaluation, and workflow fit.
BlogMultimodal AI Changes the Shape of Software
How text, image, audio, video, and document models change product design by letting users ask, point, upload, inspect, and correct.
BlogHow to Know If Generative AI Fits Your Problem
A practical decision tree for choosing between prompting, RAG, fine-tuning, vision-language models, traditional ML, rules, or no AI.
BlogThe Hidden Work Behind Just Add AI
A reality check on the operational work behind AI features: data, evaluation, reliability, UX, safety, compliance, monitoring, and trust.
BlogGenerative vs Discriminative AI, Explained for Builders
A practical explanation of when to use generative models, discriminative models, retrieval, ranking, rules, or hybrid systems.
BlogThe Generative AI Stack, Explained Without Vendor Fog
A plain-English map of the generative AI stack: models, data, retrieval, orchestration, evaluation, deployment, UX, and security.
BlogGenerative AI Is Not the Product
Why model capability is not product value, and how AI teams can move from impressive demos to useful workflows people trust.
BlogThe Future of AI Belongs to Teams That Can Explain It
Why AI teams need to build, break, and explain their systems so users, developers, buyers, and communities can trust and adopt them.
BlogFrom Prompt to Product
A practical lifecycle for turning a prompt experiment into a reliable AI workflow with evaluation, feedback, production constraints, and launch proof.
BlogFrom Model Selection to First Run
A practical workflow for choosing an initial AI model, running a baseline, inspecting outputs, and deciding what to test next.
BlogThe FRAME Method for Picking AI Projects
A practical framework for deciding which generative AI ideas are worth building before teams waste time on demos that never become products.
BlogThe First AI Experiment Should Be Small and Disposable
A practical TRIAL workflow for running early generative AI experiments that test assumptions instead of turning every demo into a product.
BlogHow to Evaluate Generative AI When There Is No Single Right Answer
A practical guide to evaluating open-ended AI outputs with rubrics, comparative review, human feedback, automated checks, and regression sets.
BlogThe AI Product Launch Checklist
A practical PROUD checklist for launching AI products with prototypes, production readiness, market fit, proof, feedback, and post-launch management.
BlogWhy DevRel Is Different for Research and ML Tools
Developer Relations changes when the audience is researchers, PhD scientists, machine learning engineers, and data scientists because adoption depends on evidence, reproducibility, workflow fit, and technical trust.
BlogHow to Evaluate a Technical Writer for AI Content
A practical scorecard for hiring or contracting AI technical writers who can write accurate tutorials, demos, explainers, and content developers trust.
BlogWhen Your AI Product Needs DevRel and When It Doesn't
A decision guide for AI founders deciding whether they need DevRel now, technical content first, developer experience repair, or a clearer product strategy.
BlogTeaching PaliGemma 2 to Spot Construction-Site Hazards
Fine-tune PaliGemma 2 with Transformers 5, QLoRA, and a construction safety dataset so a vision-language model can return object labels and bounding boxes for job-site hazards.
BlogEAGLE-3 Speculative Decoding in vLLM for Qwen3-30B-A3B-Instruct-2507
A current guide to EAGLE-3 speculative decoding with vLLM, using Qwen3-30B-A3B-Instruct-2507, a matching Red Hat AI speculator, and a tokenizer sanity check that works in Transformers 5.12.1.
BlogPreference-Aligning Vision Models: DPO Fine-Tuning Qwen3.5-4B in Transformers 5.12.1
A modern rewrite of an older SmolVLM notebook: align Qwen3.5-4B with Direct Preference Optimization (DPO), LoRA adapters, and current Transformers + TRL APIs.
BlogModern Visual Question Answering Fine-Tuning: Qwen3-VL-4B with QLoRA in Transformers 5.12.1
A current replacement for an older PaliGemma notebook: fine-tune Qwen3-VL-4B on a small VQAv2 split with QLoRA, modern Transformers APIs, and a cleaner multimodal training loop.
BlogModerating Memes with Qwen2.5-VL: Zero-Shot Hateful Content Detection in Transformers 5.12.1
A cleaned-up multimodal moderation walkthrough that uses Qwen2.5-VL with Transformers 5.12.1, the Hateful Memes validation split, and a reproducible zero-shot evaluation script.
BlogLet AutoScheme Pick the GGUF: Mixed Quantization with AutoRound and Qwen3.6
A clean, current tutorial for exporting mixed-quantized GGUF files from Qwen3.6 with AutoRound, AutoScheme, llama.cpp, and Transformers 5.12.1.
BlogHuman Preference Tuning for Small VLMs: SmolVLM2 + DPO in Transformers 5.12.1
A modern guide to preference-tuning SmolVLM2 with Direct Preference Optimization, TRL, PEFT LoRA adapters, and the current Transformers image-text API.
BlogFrom Prompts to Practice: Instruction Tuning Qwen3 with Transformers 5
A modern walkthrough for instruction tuning a small Qwen3 instruct model with Hugging Face Transformers, TRL, PEFT, QLoRA, and chat templates.
BlogFrom Prompt to Pixels: Generate Images with Qwen-Image, Diffusers, and Transformers
A current text-to-image tutorial using Qwen-Image, Hugging Face Diffusers, and the latest Transformers stack, with reproducible prompts, aspect ratios, seeds, and a fast FLUX.1-schnell fallback.
BlogFrom Messy Labels to Production Boxes: Ultralytics YOLO26 + Transformers 5.12.1
A modern, reproducible object detection workflow that replaces legacy SuperGradients/YOLO-NAS setups with Ultralytics YOLO26 and current Transformers tooling.
BlogTrain a Modern VLM on One GPU: Qwen3-VL with Unsloth and Transformers 5.12.1
A current vision-language fine-tuning guide that replaces an old Qwen2-VL notebook with a cleaner Qwen3-VL workflow, modern Transformers APIs, and a practical DocumentVQA example.
BlogFine-Tuning Qwen3.6-VL for Brain Tumor MRI Detection with Transformers 5
A practical, up-to-date tutorial for adapting Qwen3.6-VL to brain tumor MRI yes/no detection with Transformers 5, QLoRA, and reproducible multimodal training.
BlogFine-Tune ViTPose++ for Keypoint Detection with Transformers
A practical Transformers-native guide to fine-tuning ViTPose++ on COCO-style keypoints with generated heatmap targets, RT-DETR inference, and current pose-estimation caveats.
BlogFind What You Mean: Zero-Shot Visual Grounding with Qwen3-VL and Transformers
Use Qwen3-VL with the latest Transformers API to detect objects, ground natural-language phrases, and visualize bounding boxes from structured multimodal outputs.
BlogDETR Explained: Set Prediction Object Detection in Transformers 5.12.1
Learn DETR object detection with a modern Transformers 5.12.1 example, pinned requirements, and a clean explanation of set prediction, Hungarian matching, and object queries.
BlogDetect What You Can Name: PaliGemma 2 Object Detection with Transformers
A practical tutorial for using current PaliGemma 2 mix checkpoints with Transformers 5 to run prompt-driven object detection and draw bounding boxes from generated location tokens.
BlogCompress Qwen3.5 with AutoRound in Transformers 5.12.1
A current, practical guide to quantizing Qwen3.5 with AutoRound, using the modern Transformers 5.12.1 stack and a clean W4A16 workflow that scales from 0.8B to larger checkpoints.
BlogCoDeC Contamination Detection in Transformers 5.12.1 with Qwen3, Qwen2.5, and Gemma 3
A cleaned-up CoDeC walkthrough with a current Transformers 5.12.1 implementation, model-loading notes for Qwen3, Qwen2.5, and Gemma 3, and a practical scoring script.
BlogCaption by Consensus: Ranking Image Descriptions with SigLIP2 and Transformers
Use SigLIP2 with the latest Transformers APIs to score candidate image captions, choose the best description, and understand when a contrastive vision-language encoder is the right tool.
BlogYOLOv12 in Practice: A Real-Time Object Detection Guide
A practical guide to YOLOv12's attention-centric real-time detector, with a current install path, an inference example, and notes on the official detection, segmentation, and classification weights.