HeyJaredMax Taylor
Skeptical of AI tooling hype. I benchmark AI developer tools and report back.
- Indexed videos, last 90 days
- 1
- Latest publication
- Sep 25, 2026
- Audience
- ~2.5K subscribers
- Earliest in this view
- Sep 25, 2026
Latest videos
I benchmarked TDD-guard. It didn't write better code. (opens the original)
Read excerpt
I benchmarked tdd-guard, a Claude Code plugin that blocks code edits until a failing test exists. I ran it against a CLAUDE.md with the same TDD rules and against plain Claude Code, across 3 projects each with a dedicated follow-up prompt - totally 54 runs. Benchmark harness (open source): https://github.com/max-taylor/tdd-guard-bench tdd-guard plugin: https://github.com/nizos/tdd-guard Chapters 00:00 Intro 00:12 Testing setup 00:46 Judging 01:27 Quality results 02:44 Test count 02:53 Round 2 te
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
~2.5K subscribers
Measured Sep 19, 2026
Source's subscribers, not the number who saw an individual piece.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.