Install
The New Stack is a media platform for the people who build and manage software the world relies on. We provide context and explanation of at-scale technologies to advance knowledge and create conversations through our coverage of modern architectures, components of the software development life cycle, and operations to
- 152articles · 30d
- 23+ hour agolatest article
- Aug 14, 2026earliest in window
- 96%with images
- 88avg words
- Science & Technology 139
- Software Dev. 101
- Computers & Electronics 95
- News 38
- Software 21
- Science & Nature 12
- Economy, Business & Finance 9
- Finance & Business 9
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
It passed CI. It passed your evals. The customer still got the wrong answer.
19+ min ago (771+ words) Your AI agent returned a 200, passed its faithfulness check, and still answered the wrong question. The evidence that explains why lives in the trace....
The AI-native SDLC won't be one process
1+ day, 19+ min ago (92+ words) Anthropic says code is no longer the bottleneck. It's right -- but the process that catches your agent's mistakes can't be one size for every change....
Stop AI code sprawl before it destroys your software design
3+ day, 1+ hour ago (450+ words) Prevent AI code sprawl and Comprehension Debt. Use Python tools like pytest-archon to enforce Executable Architecture in your CI/CD....
Harness rebuilt its Git repository for nonstop AI agent traffic
4+ day, 3+ hour ago (891+ words) As one of Harness’s field CTOs, Martin Reynolds spends much of his time asking engineering leaders one question with no easy answer. It’s how they’re keeping up with all the pull requests their coding agents now produce. One of them…...
AI broke code review. Two experts disagree on what replaces it.
4+ day, 22+ hour ago (330+ words) Ask two experienced engineers about how to handle the flood of AI-generated code in their review queues, and you’ll get two different answers. The debate remains very much unsettled. And on Tuesday, September 29, two industry leaders will join a live…...
“Twenty years of brand building simply froze in time”: How coding agents select their tools of choice
6+ day, 2+ hour ago (311+ words) A new study shows Claude Code, Cursor, and Codex pick wildly different tools for the same job - and vendors are racing to influence the choice....
It cost $33 to build a virtual Union Square. Here's what the agents got wrong.
1+ week, 2+ day ago (152+ words) AI coding agents built a 3D browser replica of San Francisco's Union Square in two hours, then used Playwright screenshots to catch visual errors no test could....
Vercel built a feedback loop that treats agent instructions like software
1+ week, 3+ day ago (391+ words) Vercel cut known design failures by 57% by treating agent guidance like software. Yet none of the six generated pages was ready to ship....
Runway wants to generate software as you use it. Solaris is its first step.
1+ week, 4+ day ago (371+ words) The first model of a new class of AI systems Runway calls Interface World Models turns the visual into the application itself....
Cut coding agent token use with better tool output
1+ week, 5+ day ago (695+ words) Before an AI coding agent writes a single line of code, it has already spent tokens. For example, on source files, ticket descriptions, build logs, quality findings, and dependency alerts. Most of what you pay for isn’t the pull request;…...