Publications from authors and the editorial team

New articles from Wikivibe authors and materials prepared by the editorial team. Read the feed, follow authors, and publish your own write-ups.

Feed

360 publications

Research and UX Methods

7/16/202619 min

Testing the Unpredictable: How to Test the Interface When AI Behavior Changes Every Time

Как тестировать интерфейсы с непредсказуемым AI: сценарии, крайние случаи, fallback-состояния, ручная проверка и метрики качества UX.

VibeDesignResearch and UX Methods

amoorkie

—views—reactions

UX and interfaces

7/15/202618 min

Human-in-the-loop: When should AI stop and ask for permission

Human-in-the-loop в интерфейсах с AI: когда система должна остановиться, запросить подтверждение и показать пользователю понятный контроль.

VibeDesignUX and interfaces

amoorkie

—views—reactions

Branding and identity

7/14/202613 min

Brand Visual Language: Why Some Are Remembered and Others Are Not

а 16 min reading · branding · visual identity · design system Take two brands from the same category – say two coffee start-ups. Both with good...

VibeDesignBranding and identity

amoorkie

—views—reactions

Research and UX Methods

7/13/202619 min

Hotjar, Clarity and Analogues: What You See When You Watch People Click on Your Website

Как использовать Hotjar, Microsoft Clarity и аналоги для анализа поведения: клики, записи сессий, тепловые карты и практические выводы для UX.

VibeDesignResearch and UX Methods

amoorkie

—views—reactions

Prototypes and handoffs

7/12/202620 min

What a developer really wants from handoff – and why most designers don’t give it away

Что разработчики реально ждут от дизайн-хендоффа: состояния, токены, ограничения, спецификации и понятный формат передачи макета в разработку.

VibeDesignPrototypes and handoffs

amoorkie

—views—reactions

Autonomous agents

7/11/202614 min

How to Test an AI Agent: Golden Tasks, Pass Rate, Cost and Regression

Practical guide to evals AI-agents: golden tasks, tool call verification, pass rate, cost, latency, model graders and regression gate before release.

AI agentsEvalsTestingLLM

morecil

—views—reactions

Accessibility

7/11/202618 min

WCAG 3 and AI-generated interfaces: a practical accessibility check

How to review AI-generated interfaces for keyboard access, focus, semantics, contrast, errors and screen-reader behaviour.

VibeDesignAccessibility

amoorkie

—views—reactions

How to write code with AI

7/10/202620 min

ADR in simple words: how to fix architectural solutions so that AI does not break the project

The code shows how the project works now, but it almost never explains why it works that way. ADR retains the context of architectural decisions and prevents a person or AI agent from accidentally returning an already rejected option.

ADRArchitectureDocumentation

morecil

—views—reactions

Server and logic

7/10/202622 min

GRASP in simple words: 9 principles that help to allocate responsibility in code

What is GRASP and how to put the nine principles of design into practice. We analyze Information Expert, Creator, Controller, Low Coupling and other patterns using the example of TypeScript.

GRASPArchitectureTypeScriptBackend

morecil

—views—reactions

News

7/9/202614 min

GPT-5.6: compare the models by coding and agent tasks

A practical GPT-5.6 comparison for coding, agent tasks, context, cost and verification, with a decision framework instead of one benchmark score.

GPT 5. 6TerraLunaSol

morecil

—views—reactions

Accessibility

7/9/202617 min

Inclusive Design: When you design for a minority, everyone wins

The curb on the sidewalk is a small thing, until you are in a wheelchair, not with a stroller and not with a heavy suitcase. It is necessary to cut the corner under the ramp - and everyone begins to use it:.

VibeDesignAccessibility

amoorkie

—views—reactions

News

7/8/202610 min

GPT-5.6 Sol, Terra, Luna: July 9 public release – all that is known at the time of release

On July 9, 2026, OpenAI will open access to GPT-5.6 Sol, Terra and Luna. We analyze all the confirmed data: the capabilities of three models, prices, benchmarks, the new ultra mode, Sol on Cerebras with 750 tokens / sec, the history with state approval and the reaction of the community in the prediction markets.

GPT-5. 6GPT-5.6 SolGPT-5.6 TerraGPT-5.6 Luna

morecil

—views—reactions

Publications from authors and the editorial team

Feed

Testing the Unpredictable: How to Test the Interface When AI Behavior Changes Every Time

Human-in-the-loop: When should AI stop and ask for permission

Brand Visual Language: Why Some Are Remembered and Others Are Not

Hotjar, Clarity and Analogues: What You See When You Watch People Click on Your Website

What a developer really wants from handoff – and why most designers don’t give it away

How to Test an AI Agent: Golden Tasks, Pass Rate, Cost and Regression

WCAG 3 and AI-generated interfaces: a practical accessibility check

ADR in simple words: how to fix architectural solutions so that AI does not break the project

GRASP in simple words: 9 principles that help to allocate responsibility in code

GPT-5.6: compare the models by coding and agent tasks

Inclusive Design: When you design for a minority, everyone wins

GPT-5.6 Sol, Terra, Luna: July 9 public release – all that is known at the time of release

Spline V2: AI-agent collects interactive 3D scenes, and the interface can be written on top of them

Distributed intelligence: who will be subordinated to the network

Just try everything. How I came to vibe coding

I implemented Grafana: what it shows and why the project is needed

GPT-6 received Sol and Luna: Terra remains a model of the GPT-5 line. 6

Awwwards MCP: how to search for references and check web design

Figma linked layouts with Weave and updated folders: what changes in working with variations

GPT Image 2.5: spot edits, sketches and less lost details

ChatGPT in Russia broke in a new way: it seems that for the first time blocked not in OpenAI, and on the side of the Russian Federation

Figma Adds Transparency Management Through Tokens: How It Simplifies Design Systems

browser-use: a library that turns a browser into an AI agent tool

omp (oh-my-pi): a complete guide to the functions of a CLI agent for coding

OpenAI launches GPT-6 Astra in what the company calls the “AGI era”

Figma has opened generative plugins and shaders: what can now be transferred from canvas to React

Runway Solaris: A real-time interface – and why it’s not a replacement for web development

Figma reveals how to measure AI’s impact on design – and why speed metrics are not enough

AI video editors managed through Codex and Claude Code

Orca (stablyai/orca) – ADE for orchestrating a fleet of parallel AI agents

oh-my-pi (omp) – a terminal AI-agent for coding with a “stitched” IDE

What AI Agents Are and How They Work: A Clear Guide to Business

Get Shit Done (GSD): как организовать работу ИИ-агента

Google Flow: AI Credits, лимиты и сколько видео

Почему Claude блокирует аккаунты: причины бана и VPN

Codex ChatGPT Subscription: Codex-chatgpt-web and Codex-with-chatgpt