Loading…
Browse by type
Tutorial reads
Tutorial posts on Yomu, summarised newest first.
- 615 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Tutorial posts
Vision RAG: Enabling Search on Any Documents
Traditional retrieval-augmented generation relies on text parsing and optical character recognition to extract data from complex visual documents. These legacy techniques introduce high engineering effort, inconsistent accuracy, and heavy scaling costs. Vision RAG resolves these challenges by embedding entire visual documents directly through multimodal models like Voyage AI's voyage-multimodal-3.5, removing the need for text extraction pipelines. In this pipeline, dense vector embeddings map both text queries and visual assets into a unified representation space. At query time, the system retrieves relevant document images and supplies them alongside the text prompt to Anthropic's Claude 3.5 Sonnet to generate visually grounded responses.
Why We Built Our Own Background Agent
Ramp built Inspect, a hosted background coding agent that writes code and verifies its work using the context and tools available to engineers. For backend tasks it can run tests, inspect telemetry, and query feature flags, while frontend work can be checked visually with screenshots and live previews. Each session runs in a sandboxed Modal VM initialized from repository-specific images and snapshots, with integrations including GitHub, Slack, Sentry, Datadog, LaunchDarkly, Braintrust, and Buildkite. Inspect supports frontier models, MCPs, custom tools, and skills, and provides Slack, web, Chrome extension, pull request, and browser-based VS Code workflows whose changes remain synchronized. Ramp reports that about 30% of merged pull requests in its frontend and backend repositories are written by Inspect.
Best practices for coding with agents
Cursor's guide presents practices for using coding agents that can run for hours, complete multi-file refactors, and iterate until tests pass. Planning first is emphasized: Plan Mode researches the codebase, asks clarifying questions, creates a reviewable implementation plan, and waits for approval. The guidance recommends letting the agent discover context, starting new conversations when focus declines, and using Rules for persistent project instructions while Skills provide dynamic workflows. It also describes hooks for long-running loops, worktrees for isolated changes, parallel model runs, cloud agents, and Debug Mode's hypothesis-and-instrumentation process. Careful diff review, specific prompts, and verifiable goals remain necessary because generated code can be subtly wrong.
NVIDIA brings agents to life with DGX Spark and Reachy Mini
At CES 2026, NVIDIA presents a desk-based personal assistant that combines DGX Spark processing with a Reachy Mini robot, allowing an agent to converse, perceive camera input, speak, and perform actions. The tutorial assembles NVIDIA Nemotron 3 Nano for reasoning, NVIDIA Nemotron Nano 2 VL for vision, ElevenLabs for text-to-speech, and Reachy Mini hardware or simulation through the NeMo Agent Toolkit and Pipecat. Its configuration routes text, visual, and action requests to different models or a ReAct tool-calling agent, while the robot daemon exposes movement and state capabilities. The guide covers local, cloud, and serverless deployment, then starts the services needed for voice and vision interaction; the completed setup greets users and supports example text and camera prompts.
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
Assessing whether large language model improvements stem from genuine advances or underspecified evaluation conditions remains a major challenge across the industry. Most published model evaluations omit critical execution parameters, prompt templates, harness versions, and runtime configurations. In response, NVIDIA released Nemotron 3 Nano 30B A3B alongside its complete, reproducible evaluation recipe built with the open-source NeMo Evaluator library. The library serves as an orchestration layer that unifies diverse benchmark harnesses under standard configurations while decoupling evaluation logic from underlying inference backends. Developers can execute the identical evaluation pipeline against local deployments or hosted endpoints using published YAML configurations and structured logging.
Codex is Open Sourcing AI models
Hugging Face Skills equips AI coding agents like OpenAI Codex to execute end-to-end machine learning workflows. By reading AGENTS.md files and interfacing via the Model Context Protocol, Codex automates dataset validation, training script updates, and job submissions to Hugging Face Jobs. The workflow supports methods including supervised fine-tuning, direct preference optimization, and reinforcement learning for models ranging from 0.5B to 7B parameters. Throughout execution, Codex tracks live metrics via Trackio, records benchmark evaluations against baselines, and maintains Markdown reports. Once training concludes, Codex merges LoRA adapters, applies GGUF quantization, and publishes the resulting models to the Hugging Face Hub for local deployment.
LinkedIn Groups Guide: Find, Join, and Create
LinkedIn Groups bring professionals and businesses together around shared interests, industries, and goals, offering more targeted discussions than the main feed. The guide explains how to search for groups by keyword or name, filter results, assess activity and post quality, review rules, and join instantly or request approval from an admin. It also outlines group creation through the For Business menu, covering names, descriptions, images, industries, locations, privacy, rules, and member permissions. Public and private status is fixed after creation, while private groups can be listed or unlisted, with unlisted groups requiring an existing member’s invitation. To sustain participation, owners are advised to invite relevant connections, welcome members, respond promptly, moderate posts, and encourage valuable discussions; contributors should prioritize useful content, professional conduct, and relationship building.
Building production-ready Stripe subscriptions using Kiro powers
Kiro's Stripe power is presented as a way to build a production-ready SaaS subscription flow while avoiding the fragmented output common with generic coding assistants. Using a natural-language specification for three monthly tiers and a three-month one-time option, Kiro creates a React frontend, Node.js backend API, CDN-hostable static assets, and server-side Stripe Checkout Session creation. The integration includes Stripe-specific steering files, MCP servers, and hooks, while the webhook handler preserves the raw request body, verifies HMAC signatures with stripe.webhooks.constructEvent(), rejects invalid events with HTTP 400, and routes lifecycle events such as checkout completion and subscription cancellation. The post concludes that this provides a secure, scalable foundation while leaving teams to customize business logic, including access provisioning and deprovisioning, instead of building payment infrastructure from scratch.
We Got Claude to Fine-Tune an Open Source LLM
Hugging Face Skills equips coding agents like Claude Code, OpenAI Codex, and Google's Gemini CLI to manage end-to-end language model fine-tuning. Using the hf-llm-trainer skill, an agent validates dataset formats, selects cloud hardware, configures authentication, and submits jobs to Hugging Face Jobs. Supported techniques include Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO) for models ranging across various parameter sizes. The integration incorporates Trackio for real-time monitoring and automates LoRA configuration for larger models. Once training completes, the agent pushes artifacts to the Hugging Face Hub and can convert models to GGUF format for local execution.
Social Media Posting Schedule: 9-Step Guide
Managing multiple social accounts makes consistency, timing, content mix, and collaboration difficult, so the guide presents a nine-step scheduling process. It recommends auditing active and dormant channels, defining goals and KPIs, studying audience behavior and platform differences, selecting a tool, and building a calendar around content pillars, campaigns, roles, and a two-to-four-week planning horizon. The process then covers batch creation, reusable assets, platform-specific captions, approval workflows, analytics, time zones, and flexibility for timely content; Brandwatch Publish is presented as an example supporting TikTok, Instagram, Facebook, X, LinkedIn, and Pinterest. It concludes that scheduling should create capacity for engagement and strategy without sacrificing authenticity, and advises regular audits, experimentation, and readiness to pause or adapt queued posts. The guidance also warns against excessive promotion, ignoring engagement, identical cross-platform posts, weak visuals, and over-reliance on automation.
Stablecoin payments for Stripe developers: zero crypto knowledge required
The guide explains how Stripe developers can add USDC stablecoin payments without managing private keys, gas estimation, network selection, or wallet connection flows. Stripe supports USDC on Ethereum, Solana, Polygon, and Base, settles transactions as fiat in the merchant’s Stripe balance, and charges a 1.5% fee; the described feature is currently limited to US businesses. Integration can use payment_method_types: ['card', 'crypto'], although Stripe recommends automatic_payment_methods for Dashboard-managed configuration, filtering, ordering, and testing. Stripe Checkout and Elements expose crypto without frontend changes, while confirmation, webhook handling, monitoring, and familiar failure processing remain aligned with existing payment flows. The guide also describes Sandbox testing without testnets or fake cryptocurrency and presents crypto payments as a way to offer global settlement and potentially lower processing costs.
Diffusers welcomes FLUX-2
Diffusers introduces support for FLUX-2 models through the Flux2Pipeline and Flux2Transformer2DModel classes. Running the 4-bit quantized checkpoint diffusers/FLUX.2-dev-bnb-4bit requires loading Mistral3ForConditionalGeneration as the text encoder and the transformer in bfloat16 precision with CPU offloading enabled. During image generation with a prompt and 50 inference steps, the pipeline encodes text embeddings through the Mistral 3 model before executing diffusion operations. However, executing the pipeline on a GPU with 14.56 GiB capacity triggers a CUDA OutOfMemoryError during 4-bit dequantization inside bitsandbytes matrix multiplication operations. Additionally, the execution logs warn that Flax classes are deprecated in Diffusers and will be removed in version 1.0.0.
Unlock the Secrets of a Custom Sign-In Page with Tailwind and JavaScript
This tutorial shows how to customize an Okta-hosted sign-in page for a fictional to-do application while retaining the Okta Identity Engine and Sign-In Widget (SIW). It starts with a custom domain and brand configuration, then uses the page code editor, SIW design tokens, custom text, Tailwind CSS via CDN, and external JavaScript behavior to create a responsive layout, branded footer, and terms-and-conditions modal. The modal uses Alpine.js transitions and a MutationObserver watching the authentication container so it appears after SIW elements render; Google Fonts also require CSP allowlist entries for googleapis.com and gstatic.com. The post notes that browser manipulation can bypass the modal, recommends accessibility testing after customization, and describes connecting the brand to an Okta React sample through an OIDC custom issuer URL.
Secure Authentication with a Push Notification in Your iOS Device
The tutorial shows how to build a native iOS sign-in flow using Okta DirectAuth and push notification MFA. It starts with an Okta Integrator Free Plan org, configures an OIDC Native Application and enables Okta Verify push notifications, while noting additional authorization policies may be required for a custom authorization server. In Xcode, the app uses Swift, SwiftUI, Swift Package Manager, and the Okta mobile Swift packages OktaDirectAuth and AuthFoundation to handle credentials, tokens, and MFA challenges without browser redirects. An AuthService coordinates authentication state, user and token information, sign-out, access-token refresh, and session restoration from stored credentials. The completed flow is described as phishing-resistant and able to maintain an active session directly within a SwiftUI app.
Customer Experience: The 2026 Marketer's Guide
Customer experience (CX) spans every interaction across the journey, from advertising and purchase through support, product use, and advocacy, rather than referring only to customer service, UX, or customer success. The guide argues that AI has raised expectations for fast, personalized responses, while privacy-first marketing increases the importance of consented zero-party and first-party data, voice-of-customer programs, and social listening. Its framework maps awareness, consideration, purchase, post-purchase, and loyalty or advocacy; combines social, survey, support, and review data; prioritizes fixes with an impact-versus-effort matrix; and establishes workflows, response SLAs, and ongoing measurement. It recommends metrics including NPS, CSAT, CES, sentiment, and churn rate, alongside competitive benchmarking and continuous iteration. Examples describe using Brandwatch's Data Upload API and Social Panels to identify product issues, customer questions, and improvement opportunities before broader launches or operational changes.
Easily Build and Share ROCm Kernels with Hugging Face
Compiling custom deep learning GPU kernels across architectures often leads to complex build flag management, compiler errors, and ABI issues. Hugging Face's kernels library and kernel-builder streamline this workflow by supporting backends such as ROCm, CUDA, Metal, and XPU. Using the RadeonFlow FP8 block-wise GEMM kernel optimized for the AMD Instinct MI300X GPU as an example, developers organize files into specific headers and HIP implementations. The build is configured via a build.toml manifest and flake.nix to ensure reproducible compilation across supported PyTorch and ROCm versions. Artifacts can then be pushed to the Hugging Face Hub, allowing users to load and execute custom operators directly via get_kernel without traditional installation steps.
Stretch Your Imagination and Build a Delightful Sign-In Experience
This tutorial shows how to customize the Okta-hosted Sign-In Widget (SIW) for a fictional to-do application while retaining Okta Identity Engine authentication flows. It covers configuring a custom domain and enabling SIW Gen3, then using brand settings, design tokens, custom CSS properties, and page code to change fonts, colors, layout, and background treatment. The implementation uses the widget’s afterTransform method and FormBag to revise the identify form, remove help, unlock, and divider elements, change the title, and add a custom blog link. It also explains the default HTML and JavaScript rendering configuration and describes updating an OpenID Connect application to use the brand’s custom sign-in URL as its issuer.
You Should Write An Agent
Thomas Ptacek argues that people should build an LLM agent before forming strong opinions about the technology, because implementation reveals how simple and surprising the underlying system can be. The example starts with a Python loop around the OpenAI Responses API, storing user and assistant messages in a context list to simulate conversation with a stateless model. Adding a JSON-defined ping function and a tool-calling loop lets the model choose and execute multiple network checks, demonstrating behavior not explicitly hard-coded in the loop. The discussion extends this pattern to coding agents, contexts persisted in SQLite, sub-agents, and design choices involving nondeterminism, ground truth, interchange formats, and token costs. It concludes that these remain open software-engineering problems whose practical behavior can be understood by building and iterating on agents.
Learn How to Lower Heroku Dyno Latency through Persistent Connections (Keep-alive)
Repeatedly opening TCP connections between the Heroku Router and an application dyno can impose TCP slow start on every request, creating a latency penalty. The post explains how HTTP/1.0 tied each request to a new connection, while HTTP/1.1 keep-alive connections reuse an open connection and amortize setup overhead; unlike pipelining, they do not require requests to be prepared in advance. Heroku Router 2.0 uses keep-alive connections to dynos by default, avoiding repeated slow-start costs on repeat requests and exposing more available bandwidth and lower latency. Ruby applications that previously disabled keep-alives are directed to upgrade to Puma 7.1.0 or newer, then update the bundle, inspect settings, and deploy. Keep-alives still depend on both Puma and router configuration, and the post notes that the router also supports HTTP/2 features.
How to build a Content Design Agent
An overloaded solo content designer built VERBI, an AI content design agent, to scale standardized work without replacing human judgment or filling products with generic copy. The agent runs in Glean, using a curated collection of Intercom’s style guide, tone of voice, product and monetization glossaries, messaging guides, research, and official websites as retrieval-augmented generation sources. The system prompt defines its role, use cases, tone, and component rules, while a Glean Indexing API connection makes Storybook’s Surge design-system guidance available as a live source. Additional instructions tell VERBI to challenge users, avoid guessing when sources lack an answer, and keep responses concise. After 700+ triggers, the reported benefits are consistent content rules, faster drafts and iteration, fewer repetitive questions and errors, and more time for higher-impact design review.
Top topics
- Architecture830
- Performance812
- LLMs648
- Machine Learning617
- Open Source561
- AI Agents542
- AI454
- Developer Experience446
Weekly digest
The best engineering reads, once a week.