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
- 1,954articles · 365d
- 23+ hour agolatest article
- Sep 14, 2025earliest in window
- 93%with images
- 277avg words
- ai 1,614
- software 1,431
- artificial intelligence 1,355
- coding 1,313
- development 1,283
- engineering 1,242
- inclusive 1,206
- community 1,198
- technology 976
- programming 691
- webdev 540
- devops 456
- security 433
- generative ai 425
- agentic ai 382
- ai agents 329
- productivity 328
- business 321
- tech 275
- anthropic 274
- Science & Technology 1,834
- Software Dev. 1,495
- Computers & Electronics 1,379
- News 310
- Software 201
- Business & Industrial 173
- Science & Nature 131
- Economy, Business & Finance 85
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.
1+ day, 41+ 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
2+ day, 41+ 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....
Harness rebuilt its Git repository for nonstop AI agent traffic
5+ 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.
5+ day, 23+ 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…...
Shai-Hulud: Whoever controls your package registry controls your pipeline
1+ week, 6+ day ago (20+ words) Learn how the Shai-Hulud worm targets package registries and how to protect your software pipeline from automated supply chain attacks....
Your agent context needs a development lifecycle
2+ week, 1+ hour ago (700+ words) Manage your AI agent context like software. Discover how the Context Development Lifecycle improves skill quality, testing, and scaling....
Commits on GitHub have doubled in four months. Verification capacity has not.
2+ week, 2+ day ago (508+ words) AI code generation doubled commit volume, but verification capacity remains flat. Learn how to match testing speed to machine-paced code....
The 3 roles AI agents play in your developer platform
2+ week, 2+ day ago (197+ words) Discover how AI agents function as consumers, internal components, and managed resources within modern developer platforms....
Observability has a data problem. AI is about to make it worse.
2+ week, 4+ day ago (746+ words) OpenTelemetry solved telemetry collection, but exposed a costly storage gap. Bronto says AI will force observability to rebuild around the data layer....
Securing sandboxes: What happens when AI agents escape containment?
3+ week, 1+ day ago (86+ words) AI agents escaped test sandboxes using basic exploits. Learn why instruction-based containment fails and how to build hard boundaries....