How to Humanize AI Text Without Losing the Content: A Diff-Based Review Workflow
Any rewrite tool, whether it's a humanizer, a paraphraser or "ChatGPT, make this sound natural," has the same failure mode: it improves the voice an…
Testing & QA
⚑ Сообщить о проблемеПоследние новости Testing & QA от Tech News
Все темы
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Cardinal vs Ordinal Numbers: Writing Them Correctly in Words
As developers, we write numbers in words more often than we realize. Release notes say "second major release," error messages say "the first argumen…
How to Write Better Prompts: The CO-STAR Framework (Tested)
Most prompt advice boils down to "be specific," which is true and useless. After months of running the same controlled test — five people, same task…
Learning to Fit the Room: A Skill I Built to Practice Concision
How working on my own communication led me to build Concision, a portable skill for AI agents. I’ve received the same kind of feedback more than onc…
Why AI Script Writers Lose Track of Characters
An AI writer can produce a convincing confrontation and still lose the character one scene later. A cautious investigator suddenly confesses without…
380 Articles, 5 Sites, $0 Hosting: What an AI Agent Learned Building a Content Network
380 Articles, 5 Sites, $0 Hosting: What an AI Agent Learned Building a Content Network Five Russian-language niche sites are live as subfolders of a…
Designing for people reading in their second language
Most people using the products I work on are preparing for a US licensing exam in a language that isn't their first. Many are studying after a full…
My Name Is Inigo Montoya
There may be no better bedtime story in cinema history than The Princess Bride , and it's worth understanding exactly why. Not the story-within-the-…
How long do you keep a published claim provisional?
I retracted a benchmark this week. Two weeks ago I published a timing figure, described it as a fixed cost, and built an argument on it. Today the s…
My writing linter can be defeated by writing more. I measured how much more.
I ran my writing checker over one of my own published posts twice: once on the whole file, once on just the body with the front matter removed. Same…
I read 1,064 "hire me" cards. 497 opened with the wrong sentence.
Most work that fails isn't badly made. It fails because one claim underneath it was never proven. Last month I read every listing on a directory of…
I wrote a linter for AI-writing tells. It gave one of my own READMEs a C.
A pull request description came back from my coding agent and I read it the way the reviewer would. An em dash in the first sentence. A bold label o…
The idea survives the walk and dies in the editor
I build the whole argument walking the dog. Beginning, middle, the objection someone will raise, my answer to it. It is all there. I get home, open…
This blog is written by an agent — here's the publisher, and the three times it shipped something else
The essays on this blog argue, at some length, that a tool's success message is not evidence. The tool that publishes them printed the same success…
The Sloppiest Thing About AI
Originally published on oxblog . There is a fashionable new way to avoid thinking. Notice an em dash, a tidy list or a sentence with suspiciously po…
Two prompts moved seven AI detectors by fifty points
The prompt was "Simplify word choices as if written by a non-native speaker." The essays were written by US eighth graders. Seven detectors had been…
Programming for Cybersecurity: What You Actually Need to Know
When I first got interested in cybersecurity, I thought it was all about tools. Nmap, Metasploit, Wireshark, Burp Suite. I downloaded them all, watc…
This blog is written by an agent — here's the publisher, and the three times it shipped something else
The essays on this blog argue, at some length, that a tool's success message is not evidence. The tool that publishes them printed the same success…
A Little Briny - A Multi-Agent Writing Experiment
All of the text below the dividing line here was generated by a group of AI agents, using the "Discussion" tool I described here . This particular s…
Writing Documentation With AI Assistance
The rule for documentation is one line: pull the API surface out of the source mechanically, put the extraction in the context, and reject any draft…
How I Turned a Technical Writing Team Upside Down...Or, Downside Up?
Every time I think about what happened to me that one beautiful day, I still get goosebumps because that was my whole career shift. I’m sure a lot o…
Six articles, 200 views. So I read the feed's source code.
Six articles in two months. About 200 views. Total. Here is the full table, because a postmortem without numbers is just a mood: # Article Views Rea…
From Silent Reader to 25 Articles: What 3 Months on DEV Taught Me + AMA
📌 TL;DR Three months ago, I decided to start writing consistently on DEV. Twenty-five articles later, I've learned far more than how to write better…
Knowing What’s Under the Hood Helps
I’m not a car guy. I can drive them, but I don’t know the first thing about fixing them, and not much about maintaining them. My son, on the other h…
Ebook Reviewer Wanted: Help Me Find What's Gone Stale
Technical books have a shelf life that nobody prints on the cover. A cookbook from 2018 still works. A history book from 2018 still works. A Laravel…
Cross-Vendor Audit: What It Caught in My Own Model's Writing, and What It Got Wrong
Originally published on hexisteme notes . I write these engineering notes with one main model, and until recently I also reviewed them with that sam…
The GitBook migration trap
Most teams that decide to leave GitBook — or Confluence, or a folder of Markdown, or any docs tool — reach for the same first step: export everythin…
My First Post
Big Howdy, I’m starting a blog. That sentence feels weirdly dramatic for what this is to me. The plan is to write about engineering, personal projec…
AI Fabricates Maxims: Caught Twice by Human Review in One Day
At the end of my previous article on Pieter Levels , I wrote that pre-publication review had actually caught a handful of AI-specific rough spots: "…
Stop Fixing Your AI Writing Prompt. Make These 5 Decisions First
I used to fix weak AI drafts by asking for better prose. "Make it clearer." "Make it more persuasive." "Make it sound less generic." The output impr…