The blog.

Deep dives, comparisons, and roundups on the AI tools worth paying for. Only what we'd actually buy — no SEO sludge, no influencer demos.

283 posts
Comparison: Claude Code vs Codex vs Cursor: one brief, three results

Claude Code vs Codex vs Cursor: one brief, three results

Claude Code vs Codex vs Cursor, measured. I gave all three the same brief and used every app they built. All three passed — here is what separated them.

Comparison: Claude vs Grok: I ran both on a question Google gets wrong

Claude vs Grok: I ran both on a question Google gets wrong

Claude vs Grok, both run on the same two prompts. Both got the hard question right, but Grok opened 3 vendor pages while Claude cited 9 third-party posts.

Guide: Cursor pricing: the X Subscription plans and my $510.70 bill

Cursor pricing: the X Subscription plans and my $510.70 bill

Cursor pricing now runs Free, Plus $8, Premium $30, Super $100 and Ultra $200 inside The X Subscription. Every plan read live, plus what I paid on the old Pro.

Review: Cursor review 2026: I paid $510.70 over 11 months, then quit

Cursor review 2026: I paid $510.70 over 11 months, then quit

Cursor review from someone who actually paid: $510.70 across 11 months, a third of it metered usage. What it does well, and what I got wrong about the bill.

Comparison: Cursor vs Codex: I paid for one and quit the other

Cursor vs Codex: I paid for one and quit the other

Cursor vs Codex from someone who cancelled Cursor after $510.70 and walked away from Codex too. What each actually costs, and which one I'd go back to.

Roundup: Lovable alternatives: 7 tools, and I gave 5 the same brief

Lovable alternatives: 7 tools, and I gave 5 the same brief

The best Lovable alternatives, ranked by a build test rather than a feature list. Five of the seven took an identical brief. Here is what each cost.

Review: OpenAI Codex review: it deleted the rule that made it wrong

OpenAI Codex review: it deleted the rule that made it wrong

OpenAI Codex renamed 33 references across 7 files and 3 languages in a single run. Then it edited my rules file, ungated, deleting the line that made it wrong.

Roundup: Replit alternatives: 8 picks, and what a real build cost

Replit alternatives: 8 picks, and what a real build cost

Eight Replit alternatives ranked by job. I ran one identical prompt on three: Bolt built it for $0.25, Lovable $0.30, Replit would not say what it cost.

Guide: ChatGPT Plus vs Pro: three Pro prices and no published multiplier

ChatGPT Plus vs Pro: three Pro prices and no published multiplier

ChatGPT Plus costs $20; Pro is now $100, $200 or $500 a month. OpenAI dropped the 5x and 20x figures, so here is what each tier still says it buys.

Comparison: ChatGPT vs Claude: one writes, one does everything else

ChatGPT vs Claude: one writes, one does everything else

ChatGPT vs Claude, from a paid Claude account and a year on ChatGPT free. Both $20, but the free tiers differ far more — and only one generates images.

Comparison: ChatGPT vs Gemini: the free tier decides this one

ChatGPT vs Gemini: the free tier decides this one

ChatGPT vs Gemini, both tested on free accounts. One hands a non-paying user its advanced reasoning model; the other will not let you pick a model at all.

Guide: Grammarly AI detector: I tested it, and the #1 claim is stale

Grammarly AI detector: I tested it, and the #1 claim is stale

Grammarly's free AI detector, tested on human and AI text: what it caught, what it missed, the two-scan daily cap, and why its RAID #1 claim is out of date.