Copilot tops GitHub’s own AI code review benchmark. An independent one tells a different story.
If there’s one thing the AI software engineering world doesn’t lack, it’s benchmarks. Want to know whether an agent can The post C…
Testing & QA
⚑ Report a ProblemLatest Testing & QA news from Tech News
All topics
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
Agents have made CI the bottleneck. Faster pipelines are the wrong fix.
Three posts landed in September that I think engineering leaders should read together. Anthropic’s engineering team wrote that their continuou…
Claude Opus 5.5 vs. Fable 5.1: One overthinks, the other cuts corners
Anthropic released Claude Opus 5.5 on September 22, saying it performs at the level of Claude Fable 5.1 on most The post Claude Opus 5.5 vs. Fable 5…
One engineer shipped 2,000 PRs a month to production. Verification is the key.
Lauren Tan, an engineer on the Grok team at SpaceXAI, who previously worked at Cursor and Meta, recently published a The post One engineer shipped 2…
Your agent is only as good as your infrastructure
You built a great agent, but something happened when it moved into production. In testing, your agent reviewed pull requests The post Your agent is…
“Twenty years of brand building simply froze in time”: How coding agents select their tools of choice
The impact of AI has led to a shift in interest from Search Engine Optimisation (SEO) to Answer Engine Optimisation The post “Twenty years of brand…
AI agent evaluations are part of the product
A team builds an agent, gives it a few representative questions in a test chat, and watches it produce useful The post AI agent evaluations are part…
It cost $33 to build a virtual Union Square. Here’s what the agents got wrong.
PhiloLabs wanted to see how far a group of AI coding agents could get building something where working code wasn’t The post It cost $33 to bui…
Vercel built a feedback loop that treats agent instructions like software
Vercel ran more than 200 agent runs to build design.md, a new public prompt file designed to help agents create The post Vercel built a feedback loo…
Commits on GitHub have doubled in four months. Verification capacity has not.
I have been waiting for agent-generated code to show up in public infrastructure data rather than in vendor benchmarks. In The post Commits on GitHu…
Most coding agent benchmarks skip large-scale refactoring. Not this one.
AI coding agents still struggle with large-scale refactoring, with the best model achieving only a 41.2% resolve rate on a The post Most coding agen…
Coding agents can be evaluated. We just have to evaluate the work.
I recently argued with a software factory provider, whose position was that coding agents cannot be evaluated. Their reasoning was The post Coding a…
“The beast needs a cage”: Why PortSwigger’s agentic pentesting is kept safe behind bars
As agentic services diversify across the entire enterprise technology stack, the rise of agentic coding tools is being challenged by The post “…
Shipping code without human verification
Agents are writing code faster than humans can review it. The answer is not “review faster”; that would be like The post Shipping code without human…
Как агент сам откроет дверь хакеру? Разбираю три реальных пробоя AI-агентов и почему обычный ред-тиминг их не найдёт
В 2026 году основной поверхностью атак становятся уже не сами LLM, а AI-агенты с инструментами, памятью и доступом к внешним сервисам. Я добавил в с…
Greptile, Cursor, and Devin agree that agents should run their code. What they run it against matters.
The industry has recognized that shipping agent code at scale requires runtime verification, and it is moving that way fast. The post Greptile, Curs…
How to delegate 40% of tickets to AI
AI beats us at coding. But it’s also better and faster at nearly everything else: planning, QA, working with all The post How to delegate 40% of tic…