AIght_
ToolsCompareLearnUniverseWorkflowsSignalHuman
Take the quiz

Signal

From the archive

Honest writing about AI tools and what they mean. No hype, no sponsored takes. Just signal.

Subscribe by emailFor people who'd rather subscribe than scroll.

Essays

May 29, 2026· Read on AIght

Why I built /compare

Most directories rank tools. Almost no one lays them honestly side-by-side. Here's what /compare does, and what it doesn't.

May 22, 2026· Read on AIght

The takes are mine

Why every tool in the archive gets a one-paragraph verdict in my voice — and what it means that some of them disagree with the score.

May 15, 2026· Read on AIght

What I look for when a new model ships

Benchmark scores are loud and almost useless to most people. Here's the personal checklist I run on every release before I update the archive.

From the editor

Apr 22, 2025

Why context windows changed everything (and nobody talks about it)

The benchmark wars are loud. Context window size barely gets a headline. But the jump from 4k to 128k tokens is the single change that made AI assistants feel like colleagues instead of calculators — and it quietly rewrote what's possible with RAG, agents, and long-form reasoning.

Apr 10, 2025

The honest case for fine-tuning (and when it's the wrong answer)

Everyone recommends RAG first. That's usually right. But there's a specific class of problem — consistent tone, domain-specific jargon, structured output formats — where fine-tuning is the only tool that actually works. Here's how to tell which situation you're in before spending the budget.

Mar 25, 2025

MCP is the most underrated thing to happen to AI tooling this year

Model Context Protocol quietly solved the integration problem that was making AI agents painful to build. Not by being clever — by being boring. A single standard that any LLM and any tool can speak. The implications for how we build software are still unfolding.

From Medium

Apr 14, 2025↗ Read on Medium

What most AI tool reviews get wrong

The benchmark charts are real. The pricing pages are accurate. But neither tells you what it actually feels like to use something every day — what breaks first, what you stop trusting.

Mar 28, 2025↗ Read on Medium

The quiet shift happening in AI search

Something changed in how AI tools handle ambiguous queries. It's not the models getting smarter. It's the retrieval layer that's doing something different — and most people haven't noticed yet.

Mar 12, 2025↗ Read on Medium

On building things that resist hype

There's a version of every AI story that ends with productivity gains and seamless integration. That version is almost never the honest one. Here's what the honest version looks like.

← Back to AIghtExplore concepts →
60+curated tools
100%no sponsored rankings
0affiliate links

AIght_

A literary magazine covering AI. Curated slowly, on purpose.

Navigate

HomeToolsCompare ToolsLearnFieldsUniverseWorkflowsUse CasesSignal ArchiveWhat AI Cannot DoAbout AIghtThe AIght ScoreChangelogContact / SupportPrivacy PolicyGitHub

Stay in the signal

New tools, new concepts, the occasional essay — each one vetted by hand before it reaches you. No spam — ever.

© 2026 AIght. Built by Moon

Built slowly, on purpose.