AIHow AI Works

Blog

The pieces that do not fit in a glossary entry: where a benchmark number came from, what a claim actually shows, and what something costs in production.

August 2, 2026
4 minutes
Featured

Google’s Science One Framework Ties AI Research Claims to Evidence

Google Research unveiled Science One, an autonomous research prototype whose Chain-of-Evidence design produced zero phantom citations versus baselines at 21%.

August 2, 2026
9 minutes
Featured

Claude Code vs Codex vs Antigravity: Picking a Coding Agent

Three coding agents, three bets on openness, model lock-in and pricing. What separates them in August 2026 — and why benchmarks don't decide it.

August 2, 2026
8 minutes
Featured

The Best AI Video Generator in 2026 Is Probably Not the One You Think

Sora is being switched off, Veo 3.1 ranks 11th, and Chinese models hold most of the top ten. What the video arena actually says in August 2026.

August 2, 2026
8 minutes
Featured

Best AI Image Model 2026: Price and Quality Have Decoupled

GPT Image 2 leads the arena, Google's cheapest model beats its priciest, and Midjourney is absent from the top twelve. What the data says in August 2026.

July 24, 2026
5 minutes
Featured

Claude Opus 5: Near-Fable Intelligence at Half the Price

Anthropic released Claude Opus 5 on July 24, 2026 at $5/$25 per million tokens — thinking on by default, 26% fewer tokens than Opus 4.8.

July 21, 2026
6 minutes
Featured

GPT-5.6 Ships as Three Models That Differ Only in Price

OpenAI's Sol, Terra and Luna went generally available July 9, 2026. All three share one context window, one output cap and one knowledge cutoff.

July 21, 2026
5 minutes
Featured

Google Ships Gemini 3.6 Flash at a Lower Price Than 3.5

Google released Gemini 3.6 Flash on July 21, 2026 — output priced at $7.50 per million tokens, a March 2026 knowledge cutoff, and 17% fewer output tokens.

July 20, 2026
4 minutes
Featured

TIGER-AI-Lab Open-Sources OpenResearcher Agent Pipeline

TIGER-AI-Lab released OpenResearcher, a fully open pipeline for training deep research agents, with 96K web-research trajectories and 54.8% on BrowseComp-Plus.

July 20, 2026
9 minutes
Featured

Self-Hosted vs API: When Running Your Own LLM Pays Off

The raw GPU price is a trap. A 2026 breakdown of the real cost of self-hosting an LLM and where the break-even against API pricing actually sits.

July 20, 2026
8 minutes
Featured

Mixture of Experts Explained: Why Every 2026 Model Uses It

Mixture of Experts lets a model have trillions of parameters but only use a fraction per token. Here's how it works and why it took over in 2026.