The New Stack Oct 21
How to review AI code without reading the code:
Stop reading AI code line by line. Reviewing architectural decisions instead of diffs fixes the PR bottleneck ...
thenewstack.io/review-decisions-not-code/
Story Details
| Last Updated | |
| Total Articles | 2 |
Main Topics
field that develops and studies software enabling machines to exhibit intelligent behavior
Similar to This
Previous
Computerworld Oct 27
OpenAI bets on AI economics with lower-cost GPT-6.1 Terra: Replacing the legacy GPT-5.6 Terra, this new reasoning model sits between OpenAI's lower-cost ...
computerworld.com/article/4241023/openai-bets-on-ai-economics-with-lower-cost-gpt-6-1-terra-2.html
The New Stack Oct 21
AI sped up coding. Sonar instills confidence with verification.: AI coding tools give teams a burst of speed, then a pile of technical debt ...
thenewstack.io/ai-coding-verification-loops/
The New Stack Oct 20
Scripted tests can’t keep up with AI-written code. Datadog is betting agents can.
thenewstack.io/datadog-propolis-agentic-testing/
AI coding agents: Code quality declines in long-term test: Das Forschungsprojekt SlopCodeBench will aufzeigen, wie KI-Coding-Agenten bei iterativen Aufgaben mit ...
pcgameshardware.de/Kuenstliche-Intelligenz-Hardware-279517/News/KI-Coding-Agenten-Langzeittest-Code-Qualitaet-ueber-70-Prozent-schlechter-1557263/
The New Stack Oct 09
AWS, Upstage and Ollama agree on a decision-model API. OpenAI hasn’t signed on.: Decision models are converging on a startup’s API. Developers gain cheaper ...
thenewstack.io/decision-models-system-one/
The New Stack Aug 09
Anthropic recommends a git worktree per agent. Your runtime infra makes that a problem.
thenewstack.io/agent-native-runtime-branching/
The New Stack Jul 29
Shipping code without human verification: Discover how automated verification allows engineering teams to safely ship AI-generated code without human review ...
thenewstack.io/ship-code-without-verification/
github.com Jul 27
GitHub - krishagarwal314/autodev-studio: Autonomous multi-agent SDLC harness: describe a feature in plain English and AI agents scope, code, test, review ...
github.com/krishagarwal314/autodev-studio
The New Stack Jul 16
AI hasn’t shifted the bottleneck from coding to code review: Think AI shifted your bottleneck to code review? Think again. The real issue is downstream ...
thenewstack.io/ai-code-bottleneck-myth/
Agentic coding finally clicked when I wired it to a kanban board: AI agents are just like us, when they get stuck
xda-developers.com/watching-ai-agents-code-was-a-revelation/
The New Stack Jun 09
How long before we stop reading the code?: AI is breaking code reviews. Stop reading code and move the human checkpoint upstream to review intent, specs ...
thenewstack.io/future-of-code-reviews/
The New Stack Apr 09
Open source maintainers are drowning in AI-generated pull requests. Enterprise teams are next.
thenewstack.io/ai-generated-code-crisis/
App Store Submissions Have Surged 84%. Now Apple Is Declaring War on Vibe Coding.
entrepreneur.com/business-news/app-store-submissions-are-the-highest-in-10-years
The New Stack Mar 11
The 2 failures with AI coding that are creating security bottlenecks: AI coding tools are creating massive security bottlenecks. Learn about the main failures ...
thenewstack.io/ai-coding-security-bottlenecks/
github.com Feb 26
GitHub - boraoztunc/agent-system: 7 specialized AI agents that plan, implement, verify, review, and ship code together.
github.com/boraoztunc/agent-system
Thomas Dohmke: Former GitHub CEO founds AI developer platform - | Golem.de: Entire aims to be a GitHub alternative for developers that meets the challenges of ...
golem.de/news/thomas-dohmke-frueherer-github-ceo-gruendet-ki-entwicklerplattform-2602-205267.html
Next