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
- 151articles · 30d
- 15+ hour agolatest article
- Aug 15, 2026earliest in window
- 96%with images
- 86avg words
- Science & Technology 139
- Software Dev. 100
- Computers & Electronics 95
- News 37
- Software 21
- Science & Nature 13
- 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
Claude did best on a new benchmark for agents that build agents. It still passed fewer than a quarter of the tests.
4+ day, 10+ hour ago (492+ words) Sierra has open-sourced Hyper-𝜏-bench, a follow-up to its 2024 τ-bench that tests how well AI agents can build other agents....
GLM-5.3-Flash vs. GLM-5.3: Time and money, not the spec sheet
1+ week, 5+ day ago (801+ words) I always wonder about the end goal when companies launch products so close together and undercut each other by claiming the new one is “so much better.” GLM-5.3 and GLM-5.3-Flash are a great example of this. Z.AI launched…...
Cut coding agent token use with better tool output
1+ week, 6+ 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;…...
DeepSeek's first vision model vs. Gemini 3.7 Flash: It comes down to spend vs. speed
1+ week, 6+ day ago (334+ words) DeepSeek matched Gemini on nine vision questions for a third of the price. The tradeoff: slower, less consistent responses that matter at scale....
Your AI agent is only as good as the harness around it
2+ week, 15+ hour ago (959+ words) Build production-ready AI agents with effective guardrails, tool contracts, permissions, and tracing systems beyond simple demos....
"Save frontier models for frontier problems": Why Korea's Solar Pro 4 is a workhorse agent reliability play
3+ week, 3+ day ago (369+ words) Upstage AI's Solar Pro 4 targets reliable AI agents for enterprise workflows, promising 90% lower costs than frontier models for document tasks....
An industrial-scale distillation of models, or subtle benchmaxxing: What developers really think of GLM-5.3
3+ week, 4+ day ago (536+ words) Z.ai's GLM-5.3 claims big coding gains, but AI professionals say the real story may be distillation from Anthropic's Claude models, or a case of subtle bencmaxxing, not novel training....