The New Stack・開発・ネットワーク
52 件今日 · 11月3日（火）
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…
昨日 · 11月2日（月）
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…
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…
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…
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…
Why MCP servers should tell agents what to do next
Many MCP servers do one thing. An agent asks for data, and the server hands it back. AWS’s James Ward thinks that leaves a lot on the table.…
Mistral’s Large 4 open weights arrive with a 1-point coding lead over GLM-5.3: “There’s nothing you can’t do with this model that you can do with competitors.”
On Thursday, Mistral released the weights for its frontier open model, Mistral Large 4 (ML4), on Hugging Face.
AWS Elastic Beanstalk for regulated workloads: Built for the next decade, not just the first deploy
For more than a decade, the managed application platform industry has optimized around a compelling promise: get code running as quickly as…
“I don’t think the world needs a new GitHub”: What GitHub’s leaders really think about their new rivals
At its annual Universe ’26 conference in San Francisco this week, GitHub took to the question of the platform’s stability head-on.
Why Kubernetes platforms keep rebuilding a layer they could share
Ask a platform team what they built last year, and the list likely includes a Kubernetes controller that creates a few objects in order and…
The 5 essential layers of AI agent sandboxing on Kubernetes
An AI agent given autonomy to run code will inevitably run code no human has reviewed. It may install model-selected packages, run scripts g…
“Urgency is an inherently subjective call”: Anthropic tells TNS how it grades Claude Duet
Anthropic built Claude Duet, an AI assistant that monitors your connected apps and works on tasks in the background, to decide what needs yo…
10月28日（水）
GitHub debuts Copilot Fusion, a new model selection & orchestration system that beats Claude Code for half the API cost
GitHub has debuted GitHub Copilot Fusion, a new system that handles model selection and orchestration for coding tasks so developers don’t h…
GitHub saw 7.4B commits in September, adding 4M CPU cores and 160 PB of storage to keep up
GitHub is seeing unprecedented demand and is updating its core infrastructure to keep pace.
What happens when the agent is long gone, but its access key lives on?
Imagine: There’s a line on the credential report that no one on the platform team can explain. An IAM user called research-agent-2 has an ac…