Blog Category

Analyze

Know what's actually happening.

38 posts
Roundup: Claude alternatives: which Claude are you replacing?

Claude alternatives: which Claude are you replacing?

Anthropic sells the chat assistant plus five named products called Claude, and page one answers four different questions. Work out which you mean first.

Guide: ChatGPT agent is gone: what replaced it, and what Plus gets now

ChatGPT agent is gone: what replaced it, and what Plus gets now

ChatGPT agent mode no longer exists. Here is what ChatGPT Work and its cloud browser do instead, which plans get them, and what the old 40-a-month limit became.

Review: Claude AI review: brilliant at words, strange about limits

Claude AI review: brilliant at words, strange about limits

A Claude AI review from a paying Max account. My $100 Max plan invoiced at $111.11, three usage meters run at once, and overflow is billed at API rates.

Guide: Claude Artifacts tested: a working app in 2 minutes, private at first

Claude Artifacts tested: a working app in 2 minutes, private at first

I built a tip calculator, a five-slide deck and an AI reply tool as Claude artifacts. What saved, what exported, what asked permission, and what Free gets.

Guide: Claude Max plan: 5x now covers your week, and 20x is gone

Claude Max plan: 5x now covers your week, and 20x is gone

Claude Max is $100 a month for 5x Pro usage every five hours and every week. The $200 tier is now Ultra: no five-hour cap, 10x Pro weekly. Which one to buy.

Review: ChatGPT review: the free tier is the story, not the $20 one

ChatGPT review: the free tier is the story, not the $20 one

A ChatGPT review from a year on the free tier plus one month of Plus. Six rungs from $0 to $500, and ads now run on both the Free and $8 Go tiers.

Guide: Claude Projects tested: what it finds, and what it can't read

Claude Projects tested: what it finds, and what it can't read

I built a Claude project with three files and ran six chats. It found one line in a 1.46 MB file, but could not count across it. Setup, limits and plans.

Guide: Gemini Deep Research tested: fast, thorough, and trusts the vendor

Gemini Deep Research tested: fast, thorough, and trusts the vendor

I ran two Gemini Deep Research reports on the free plan and scored them against our own tests. Strong on the docs, weak where the real products differ.

Guide: NotebookLM video overview: I asked for 5 minutes, got 9

NotebookLM video overview: I asked for 5 minutes, got 9

I made a NotebookLM video overview in both formats on a free account. The 72-second Short got the science right. The Explainer ran 8:57 and ignored my limit.

Roundup: Best AI assistant: the free tiers decide it, not the $20 ones

Best AI assistant: the free tiers decide it, not the $20 ones

The best AI assistant depends on whether you pay. Five tested on real accounts: at $20 they are close, on the free tier the gap runs opposite to the ranks.

Comparison: ChatGPT vs Grok: 4 prompts, both free tiers, a clear tie

ChatGPT vs Grok: 4 prompts, both free tiers, a clear tie

I ran four prompts through ChatGPT free and Grok free. They tied on all four. The real gaps: Plus $20 vs Grok Premium $30, and five free models against none.

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.