loading field notes... ok
loading markdown collection... ok
loading post index... ok
teds read --index blog
AI engineering and DevRel field notes.
Practical essays and tutorials on AI systems, evaluation, multimodal models, developer trust, DevRel strategy, and technical content.
$ teds topics --clusters
Each cluster supports a service area: AI engineering, DevRel, evaluation, or technical content.
Practical posts on model selection, prototypes, evaluation, AI product decisions, and the path from experiment to useful system.
Evaluation & SafetyGuides to testing AI systems before they fail in front of users.
Vision & MultimodalHands-on work with computer vision, vision-language models, object detection, visual grounding, and multimodal systems.
Physical AIField notes on robotics datasets, LeRobot curation, tactile sensing, MCAP sensor fusion, and VLA model evaluation.
Developer RelationsEssays on DevRel in AI, DevRel strategy for AI companies, developer trust, community, hiring, technical advocacy, and feedback loops.
Developer ContentWriting on tutorials, launch proof, technical education, and content that developers can use to decide.
LLM SystemsPractical thinking on retrieval, generation, evaluation, prompting, deployment, and reliability.
$ teds search --posts
Search titles, summaries, and topic tags.
114 posts
No matching field notes. Try a broader topic or clear the search.
Construction-Site-Traversability: Robot Loops With Camera, Range and Lidar in FiftyOne
A tracked robot drives closed loops through two active construction sites. Scrub RGB, range, lidar, GNSS and odometry together in FiftyOne.
BlogGR00T-X-Embodiment-Sim: Seven Robot Bodies, 42 Episodes, Compared in FiftyOne
GR00T-X-Embodiment-Sim has six episodes from each of seven robot bodies. Compare cameras and joint telemetry on one timeline in FiftyOne.
Blogegodex-test-multimodal: 68-Joint Hand and Body Pose With Egocentric Video in FiftyOne
EgoDex pairs Apple Vision Pro video with 3D pose for 68 body and finger joints. Browse 3,243 test episodes with a 3D skeleton in FiftyOne.
Blog2026-Humanoid-IKEA-Assembly-Challenge: 35 Motors, Seven Cameras, in FiftyOne
Six humanoid furniture-assembly episodes with 35 motors, seven camera streams and annotated subtasks. Scrub torque plots next to wrist cameras in FiftyOne.
BlogSEW-Multimodal-AMR: RGB, Thermal, 4D Radar and ToF on One Robot, Loaded in FiftyOne
SEW's mobile robot carries RGB, thermal, ToF, 4D radar, laser scanners and ultrasonics. Compare 3,151 labeled frames across weather and light in FiftyOne.
BlogHapTile: 1,699 UR5e Episodes With Tactile Video and Haptic Levels, in FiftyOne
HapTile pairs UR5e teleoperation with two fingertip tactile streams, two RGB-D cameras and haptic levels. Scrub 1,699 episodes in FiftyOne.
BlogWhy 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.
BlogEgocentric-EMG-Force: First-Person RGB-D With Forearm EMG, in FiftyOne
Egocentric-EMG-Force pairs first-person RGB-D video with EMG from both wrists, hand skeletons and finger force estimates across 8 household tasks.
BlogDreamTac: 703 Franka Trajectories With Gel Fingertip Video for Robot Learning
DreamTac records a Franka arm with a wrist camera, a third-person camera and two gel fingertips. Watch contact in four synced views in FiftyOne.
BlogTII-RATM-Drone-Racing: Measure Odometry Drift Against Motion Capture in FiftyOne
TII-RATM pairs a racing drone's own odometry with motion-capture truth for six flights. Sort by tracking error and watch the feature tracks.
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.
BlogBoilingBench-Multimodal: Scrub Boiling Video Against Temperature and Sound
BoilingBench-Multimodal syncs high-speed video, surface temperature and three acoustic sensors on one clock across 7 boiling and cooling runs.
BlogTaF-Tactile-Force: Tactile Images, Pressure Maps and Six-Axis Force on One Clock
TaF-Tactile-Force syncs a tactile camera, a 12x12 pressure array and a six-axis force sensor at 30 fps, with contacts up to 90.8 N.
BlogWhy Hiring an Influencer for DevRel Fails
Why hiring an influencer for DevRel fails for developer tool startups, and an actionable framework for evaluating developer advocates who can actually build.
BlogRoboLab-EgoX: Filter 3,368 Labeled Robot Failures in FiftyOne
RoboLab-EgoX keeps all 4,000 RoboLab policy rollouts, 632 successes and 3,368 failures, with three camera views and depth. Filter them in FiftyOne.
BlogDevRel in AI: The Strategy & Playbook for AI Companies
A complete guide to DevRel in AI and DevRel strategy for AI companies: what builds developer trust, how to structure advocacy, and what wastes budget.
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.
BlogMirrorSentinel-Elevator: Checking Lidar Against Hand-Measured Elevator Cabins
MirrorSentinel-Elevator pairs a ZED2 camera and an Ouster lidar with hand-measured cabin boundaries, so you can see what a mirror does to range.
BlogAI Didn't Kill the DevRel Interview. It Made the Old Tricks Load-Bearing.
What a 2020 interview-coaching book, a data science career guide, and a freelance bible still teach devrel engineers about standing out, leveling up, and going independent in the 2026 AI developer tools market.
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.
BlogWhy Vision-Only Imitation Fails at Delicate Contact: Low-Cost Dexterous Teleoperation & Tactile Policies
Why scaling camera tokens and 10 Hz foundation models hits a wall during high-DoF dexterous manipulation, and what sub-$35 shear sensors and handheld data-collection rigs change about it.
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.
BlogRobot Data Quality Scoring: Why Scores Are Triage, Not Gates
Why action-only smoothness metrics invert on critical structural errors, why detector AUROC does not predict policy success, and how to use automated scoring for triage in 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.
BlogImage Copy Detection: Find Edited Copies with pHash, CLIP, and FiftyOne
Why single-signal duplicate detection fails on cropped, mirrored, or filtered images, and how Image Link Lab pairs pHash and CLIP embeddings under configurable logic in FiftyOne.
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.
BlogData Curation, the Voxel51 Agent, and In-App Annotation: A CropAndWeed Walkthrough
A data-centric audit of the CropAndWeed dataset exposing class imbalance misconceptions, sampling biases, 370 degenerate boxes, and 23 stem-point defects using FiftyOne.
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.
BlogUse the Forward Deployed Engineer Model for Your DevRel
Why the Forward Deployed Engineer model beats the content-mill agency model for Developer Relations, and how to demand it when you hire an agency for your AI or devtool company.
BlogFounders, Stop Putting DevRel in the Wrong Box
A direct guide for founders hiring DevRel talent: let the role operate as its own function, connect it tightly to sales and customer success, and stop confusing community advocacy with fear of selling.
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.
BlogRAG Is a Product Pattern, Not a Magic Trick
Why retrieval-augmented generation only becomes trustworthy when content quality, retrieval, ranking, UX, evaluation, and feedback are treated as product work.
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.
BlogWhy Evaluation Is the New Prompt Engineering
Prompting helps you ask better questions, but evaluation is the production discipline that makes AI systems reliable, comparable, and trustworthy.
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.
BlogEnglish Is the New Interface
Natural language is becoming a primary way people operate software, but AI interfaces still need state, constraints, corrections, and product judgment.
BlogYour AI Product Needs a Feedback System Before More Features
Why AI product teams should build feedback loops before adding features, and how to turn user signal into model, data, prompt, UX, and product improvements.
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.
BlogStop Writing Launch Posts. Start Writing Proof.
A direct guide to replacing vague product launch posts with technical proof: runnable examples, comparisons, benchmarks, failure modes, and decision support.
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.
BlogA Practical DevRel Operating System for Small Teams
A lightweight weekly, monthly, and quarterly DevRel operating rhythm for small AI and devtool teams that need content, feedback, community, and measurement without ceremony.
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.
BlogHow to Build a Developer Feedback Loop Product Teams Will Use
A practical DevRel feedback loop for collecting developer signal, filtering noise, and turning community, support, and content insights into product action.
BlogCommunity Metrics That Survive CFO Review
How to report developer community value with credible business signal, honest assumptions, and useful operating metrics instead of inflated vanity numbers.
BlogThe Anti-Playbook for DevRel Events
A practical guide to when DevRel events fail, when they are worth doing, and how to tie conferences, talks, workshops, and meetups to real developer outcomes.
BlogTurn Sales Calls Into Developer Content Strategy
How technical teams can turn repeated sales-call questions into developer content, docs, examples, and product feedback without writing sales copy.
BlogWhy Technical Content Is a Product Surface
Why tutorials, docs, demos, examples, and technical explainers should be treated as part of developer experience instead of marketing collateral.
BlogThe Zero-to-One Developer Program
A minimal developer program for AI and devtool startups: one audience, one activation path, one content cadence, one feedback loop, and one useful metric.
BlogDevRel vs Developer Marketing vs Community: What You Actually Need
A practical guide to the differences between Developer Relations, developer marketing, advocacy, education, community, and developer experience roles.
BlogHow to Hire a Developer Advocate Who Can Actually Build
A practical hiring guide for evaluating developer advocates on technical judgment, writing, demos, product sense, and feedback quality instead of audience size alone.
BlogDevRel Strategy Starts With Positioning, Not Events
Why developer relations strategy should begin with audience, product relevance, and differentiation before conferences, communities, or content calendars.
BlogWhat Founders Get Wrong About Community
A plain guide for founders who want developer community without mistaking an empty channel, event calendar, or growth hack for a maintained system.
BlogThe Developer Journey Audit: Find Friction Before You Hire
A practical audit for finding developer onboarding, docs, content, and community friction before hiring DevRel or scaling developer programs.
BlogA 30/60/90 Day DevRel Plan for AI and Devtool Startups
A practical first-quarter Developer Relations plan for technical startups that need sharper positioning, better developer activation, useful content, and reliable feedback loops.
BlogThe Developer Trust Ledger
A practical model for understanding how technical companies earn or lose developer trust through docs, demos, examples, community, and product claims.
BlogThe First DevRel Hire Should Not Be a Megaphone
A founder-focused guide to hiring the first Developer Relations person for a devtool or AI company without confusing audience size for technical trust.
BlogHow to Measure DevRel Without Vanity Metrics
A practical framework for measuring Developer Relations with business signal, developer journey context, and honest reporting instead of inflated reach numbers.
BlogDeveloper Content That Doesn't Feel Like Marketing
A practical guide to writing developer content that earns trust by helping people build, evaluate, debug, and decide instead of dressing a product pitch in technical language.
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.
Need help?
Turn technical depth into shipped work.
Explore AI engineering, DevRel, and technical content services when the field notes point to a problem your team needs to move.