The New Stack
92 件昨日 · 11月3日（火）
A developer opened Postman. Then two AI coding agents changed without their permission.
A developer says Postman’s desktop app installed plugins into Claude Code and OpenAI Codex without their permission. The app also tried to a…
Can agent standards keep up with the companies building them?
Mazin Gilbert, executive director of the Linux Foundation’s Agentic AI Foundation, left Google earlier this year to lead the new AAIF, and h…
Goldman Sachs restricted Claude Code for bankers — but made one surprising exception
Replit CEO Amjad Masad is warning that AI coding agents running on employee devices are becoming a security risk for enterprises and governm…
Anthropic speeds up Claude Code with message threads. But your token bill stays the same.
Anthropic has announced a new feature that aims to speed up long-running Claude Code sessions by reducing the amount of conversation data re…
OpenAI built itself a new Git backend, too
OpenAI on Monday detailed how it built a new Git backend for its monorepo to power the ever-increasing number of commits its developers and…
11月2日（月）
Developers are downgrading their AI on purpose — and it’s working
Anthropic has confirmed that it added new restrictions to Claude Code to prevent users from recreating existing video games. But developers…
Your AI coding agent now runs on a budget — and it can cut you off mid-task
The days of pointing an AI agent at a backlog and letting it burn through compute without much oversight may be coming to an end. Cognition…
Canva’s new design model doesn’t generate images. It writes code to edit them.
Australian graphic design software company Canva took the wraps off Canva Brush last week, its new vision-language model for designers. Brus…
OpenAI’s new shared usage limit pits ChatGPT against Codex
OpenAI has revealed plans to combine usage allowances across ChatGPT and Codex, as part of a broader effort to integrate its conversational…
11月1日（日）
Open-source security in the AI exploit era: Patch without changing a thing
Here’s how a vulnerability in a popular open-source library plays out in 2026: A maintainer merges a fix and publishes an advisory. Within h…
A step-by-step guide for how to kill the line-by-line code review
Agents verify; people decide. Most teams running AI code review today have it the other way around. They point a model at the diff, ask it w…
10月31日（土）
The context problem: How Docusign built agents that understand the business behind contracts
Ask a general-purpose language model to summarize a contract, and it will probably do a reasonable job. Ask it to calculate what a company o…
Five years after the fork, OpenSearch is slowly stepping out of AWS’s shadow
OpenSearch has come a long way since Amazon Web Services first announced the project back in January 2021, in response to Elastic’s decision…
Amazon CEO predicts 6 to 8 AI models will be ‘good enough’ for almost everything
Amazon CEO Andy Jassy expects the frontier AI model race to produce several competitive models rather than a single winner, telling analysts…
GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at max effort
OpenAI launched GPT-6.1 Terra on October 26, and included two direct comparisons with Opus 5.5 in its marketing materials. It claimed Terra…
Shielding the patch gap: The exploit doesn’t wait for Patch Tuesday
Four years after Log4Shell became one of the most consequential vulnerabilities in software history, vulnerable instances of the library are…
10月30日（金）
Anthropic just removed one of Claude’s biggest usage limits — but not for everyone
Claude Code users on Anthropic’s $200 plan will no longer face a rolling five-hour usage cap, provided their accounts are verified and they…
Busy GPUs can hide slow AI inference on Kubernetes
A Kubernetes cluster can be healthy while the AI service running on it disappoints users. A model might return its first token quickly but t…
What worries Entire co-founder Thomas Dohmke about the future of tech?
Former GitHub CEO Thomas Dohmke is taking on his old company. His startup, Entire, launched a GitHub alternative this week, replacing tradit…
Kubernetes just formed a workload conformance group. Here’s why it matters for AI teams.
Welcome to the final edition of Road to KubeCon, where we track the Kubernetes and cloud-native ecosystem each week on The New Stack as we h…
GPT-6.1 Terra vs. GPT-6 Astra: One sacrifices accuracy for lower cost and higher speed at high effort
OpenAI released GPT-6.1 Terra on October 26, marketing it as a cheap, fast model for high-volume everyday work, priced at a tenth of its GPT…
What five P99 CONF talks reveal about database trade-offs
P99 CONF is a virtual conference on high-performance, low-latency applications. Its 2026 event ran October 21–22. Here, we cover five of its…
10月29日（木）
Sam Altman almost scrapped token pricing. Here’s why he backed off.
OpenAI considered dropping token-based pricing for its next model, letting developers submit a prompt and receive a price for the work, befo…
AWS’s Hydro team wants the compiler to catch coding agents’ mistakes
Earlier this month, the team behind Hydro developed a new way to check that a distributed system still works correctly when it resends messa…