# The New Stack Technology is complex. We make it clear. Go beyond the headline on cloud native, DevOps, open source, and AI-native software development news. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Why human oversight is shifting from writing code to defining requirements DevFeed: [Why human oversight is shifting from writing code to defining requirements]() Original publisher: [Read original article]() Author: Naseeb Ahmed Mian Published: 2026-09-17T13:00:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [Requirements](), [AI Agent](), [Code](), [Availability]() Tags: [agent](), [agents](), [ai-agents](), [ai-engineering](), [andela](), [automated](), [availability](), [code](), [pipeline](), [post-contributed](), [requirements](), [review](), [software-development](), [sponsor-andela](), [sponsored-post-contributed](), [tests]() ### AI overview The article argues that human oversight of AI-assisted software development should focus on defining and reviewing requirements, not only checking whether generated code conforms to them. It illustrates the risk with a flawed availability-related requirement that passed specification review, generated six passing tests, traceability checks, and automated QA while violating the feature's intended outcome. ### Source excerpt This walks through the pipeline our agents operate inside--from a recorded scoping meeting through unit specs, spec review, generated code, The post Why human oversight is shifting from writing code to defining requirements appeared first on The New Stack. ## Perplexity's AI agents helped build a database. They weren't allowed to run it. DevFeed: [Perplexity's AI agents helped build a database. They weren't allowed to run it.]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-16T21:51:15Z Content type: article Language: en Sources: [The New Stack]() Topics: [Database](), [DynamoDB](), [Rust](), [Artificial Intelligence](), [rocksdb](), [Amazon S3]() Tags: [agents](), [ai](), [ai-agents](), [ai-infrastructure](), [api](), [coding](), [coding-agents](), [database](), [databases](), [dynamodb](), [open-source](), [performance](), [perplexity](), [rocksdb](), [rust](), [s3]() ### AI overview Perplexity built CobbleDB, a Rust key-value store, after finding DynamoDB too costly and insufficiently controllable for its search workload. Coding agents helped develop it, but were not allowed to run it in production. Perplexity measured lower read latency and expects lower costs, with plans to open-source the database. ### Source excerpt Perplexity decided it was paying too much for DynamoDB and wasn't getting the control it wanted over read performance. So The post Perplexity's AI agents helped build a database. They weren't allowed to run it. appeared first on The New Stack. ## Automattic CEO Matt Mullenweg returned after 33 hours of leave without a public explanation DevFeed: [Automattic CEO Matt Mullenweg returned after 33 hours of leave without a public explanation]() Original publisher: [Read original article]() Author: Adrian Bridgwater Published: 2026-09-16T20:39:42Z Content type: news Language: en Sources: [The New Stack]() Topics: [WordPress](), [App](), [Open Source](), [Tumblr]() Tags: [cloud-services](), [company](), [cto](), [developer-tools](), [governance](), [matt-mullenweg](), [open-source](), [wordpress]() ### AI overview Automattic CEO Matt Mullenweg was placed on leave and reinstated about 33 hours later. The company has not publicly explained what prompted the leave or return, while observers have raised--but not established--the possibility of an attempted change in control. ### Source excerpt There were unusual goings-on this month at Automattic, a company known for its free and open-source app for building WordPress The post Automattic says CEO Mullenweg was gone and back inside 33 hours. What happened between? appeared first on The New Stack. ## Zed launches Delta public beta for collaborative code review with developers and coding agents DevFeed: [Zed launches Delta public beta for collaborative code review with developers and coding agents]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-16T19:45:30Z Content type: article Language: en Sources: [The New Stack]() Topics: [GitHub](), [AI-assisted coding](), [pull-requests](), [Developer Platform](), [Tooling]() Tags: [ai](), [ai-agents](), [beta](), [coding-agents](), [collaboration](), [developer](), [developer-tools](), [github](), [pull-requests](), [review](), [software-development]() ### AI overview Zed has announced the public beta of Delta, a collaborative environment where developers and coding agents work, review, and revise code together in shared threads rather than pull requests. The article presents Delta as a response to the volume of agent-generated code and limitations of the pull-request model. ### Source excerpt Something of a consensus has emerged from the developer fraternity in 2026 -- GitHub, a platform built substantively for human The post "Everyone's in a race to replace GitHub": Zed launches Delta because agents made pull requests obsolete appeared first on The New Stack. ## Anthropic merges Claude Chat and Cowork into one interface DevFeed: [Anthropic merges Claude Chat and Cowork into one interface]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-16T16:46:36Z Content type: news Language: en Sources: [The New Stack]() Topics: [anthropic](), [Claude]() Tags: [ai-agents](), [ai-infrastructure](), [anthropic](), [chat](), [claude](), [connectors](), [context](), [developer-tools](), [tools](), [workflow]() ### AI overview Anthropic is merging Claude Chat and Cowork into a single interface, allowing conversations to handle simple questions, multi-step projects, connected tools, and background execution. Claude Docs and Claude Slides are launching in beta on paid plans, while Claude Design is moving into conversations. ### Source excerpt Using Claude for anything beyond a quick question has always started with a routing decision to use Chat or Cowork? The post Anthropic bet users were choosing wrong. So it removed the choice. appeared first on The New Stack. ## AI leaders propose embedded third-party evaluators for frontier AI safety DevFeed: [AI leaders propose embedded third-party evaluators for frontier AI safety]() Original publisher: [Read original article]() Author: Adrian Bridgwater Published: 2026-09-16T15:58:41Z Content type: news Language: en Sources: [The New Stack]() Topics: [Job](), [Artificial Intelligence](), [Frontier AI](), [anthropic](), [AI Models]() Tags: [ai](), [ai-infrastructure](), [ai-strategy](), [alignment](), [anthropic](), [developers](), [frontier-ai](), [google](), [job](), [meta](), [openai](), [safety](), [tech-careers]() ### AI overview The article examines Anthropic CEO Dario Amodei's proposal for frontier AI companies to provide embedded third-party evaluators with employee-like access. These evaluators would verify safety practices, report incidents, and assess AI models, training pipelines, and processes. ### Source excerpt The pace of frontier AI model development spurred Anthropic CEO Dario Amodei to publish an essay last weekend, calling for The post AI evaluator: The most important AI job in history? How developers might fill the proposed new job appeared first on The New Stack. ## OpenAI's Greg Brockman discusses computer use as an alternative to purpose-built AI agent integrations DevFeed: [OpenAI's Greg Brockman discusses computer use as an alternative to purpose-built AI agent integrations]() Original publisher: [Read original article]() Author: Meredith Shubel Published: 2026-09-15T23:41:22Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [computer-use](), [OpenAI](), [Model Context Protocol](), [Reinforcement learning]() Tags: [ai-agents](), [computer-use](), [developer-tools](), [developers](), [mcp](), [model-context-protocol](), [openai](), [reinforcement-learning]() ### AI overview OpenAI president and co-founder Greg Brockman discusses whether AI agents could use computers through screens, keyboards, and mice instead of relying on purpose-built MCP servers, CLIs, APIs, and other integrations. ### Source excerpt This week on the a16z show, Greg Brockman, president and co-founder of OpenAI, made the point that developers have been The post OpenAI president: "The computer should be there to empower you." So stop retooling software for AI agents appeared first on The New Stack. ## Meta lets Claude and Codex configure WhatsApp Business via MCP DevFeed: [Meta lets Claude and Codex configure WhatsApp Business via MCP]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-15T22:08:56Z Content type: news Language: en Sources: [The New Stack]() Topics: [Meta](), [Model Context Protocol](), [AI-assisted coding](), [Claude](), [codex](), [API]() Tags: [ai](), [ai-agents](), [ai-coding-agents](), [api](), [claude](), [codex](), [developer-tools](), [mcp](), [mcp-server](), [meta](), [model-context-protocol](), [product](), [updates]() ### AI overview Meta announced a WhatsApp Business Tools MCP server that lets developers connect Claude or Codex to selected businesses they administer. The agents can help configure WhatsApp Business accounts, verify phone numbers, manage templates, and perform related API tasks, with access scoped to the businesses the developer selects. ### Source excerpt Any business worth its salt in 2026 needs to be embracing the right tools to reach its customers, and few The post Meta lets Claude and Codex configure WhatsApp Business via MCP appeared first on The New Stack. ## Google and OpenAI take different approaches to reducing voice-agent latency DevFeed: [Google and OpenAI take different approaches to reducing voice-agent latency]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-15T21:50:15Z Content type: comparison Language: en Sources: [The New Stack]() Topics: [Latency](), [Google AI](), [OpenAI](), [API](), [Orchestration](), [real-time](), [Artificial Intelligence]() Tags: [ai](), [ai-agents](), [ai-engineering](), [api](), [comparison](), [google-ai](), [large-language-models](), [latency](), [openai](), [orchestration](), [real-time]() ### AI overview The article compares Google's Gemini 3.8 Live Extended Thinking with OpenAI's GPT-Live-1 for reducing latency in voice agents. Google keeps speech, reasoning, and asynchronous tool execution in one stateful session, while OpenAI uses a real-time conversation model alongside a backend reasoning model, shifting more orchestration to the application. ### Source excerpt Voice agents have a latency problem that shows up as soon as they have to do real work. Within five The post OpenAI's voice model doesn't think. That's the point. appeared first on The New Stack. ## AWS agents will suggest your new flights. Code decides what gets booked. DevFeed: [AWS agents will suggest your new flights. Code decides what gets booked.]() Original publisher: [Read original article]() Author: Meredith Shubel Published: 2026-09-15T21:27:21Z Content type: news Language: en Sources: [The New Stack]() Topics: [AWS Step Functions](), [Amazon Bedrock AgentCore](), [Orchestration](), [Generative AI](), [Amazon Web Services]() Tags: [ai-agents](), [ai-engineering](), [airline](), [amazon-bedrock-agentcore](), [aws](), [aws-step-functions](), [cloud-services](), [generative-ai](), [orchestration]() ### AI overview AWS published a Step Functions pattern for airline rebooking in which Amazon Bedrock AgentCore agents propose itineraries and compensation messages, while deterministic workflow steps validate proposals before reservations change or payments are issued. ### Source excerpt AWS published a new Step Functions pattern this week that gives AI agents a role in airline rebooking while keeping The post AWS agents will suggest your new flights. Code decides what gets booked. appeared first on The New Stack. ## Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions DevFeed: [Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-15T18:47:23Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI-assisted coding](), [Training AI Models](), [Open Source Models & Datasets](), [Agent Harness]() Tags: [agent](), [agent-harness](), [ai](), [ai-development](), [ai-engineering](), [ai-models](), [coding-agents](), [data](), [developer-tools](), [developers](), [training]() ### AI overview Bolt.new is testing Forge, a research preview for individual Pro subscribers that offers up to 50 times more usage of open-weight coding models in exchange for opting in to share anonymized coding sessions. The sessions may include prompts, source code, fix traces, and conversations with the coding agent, and will support an Arcee AI project to train a trillion-parameter-class open-weight model. ### Source excerpt Bolt.new, StackBlitz's browser-based AI development platform, is testing a new trade with developers: more coding-model usage in exchange for training The post Bolt is giving developers 50x more compute. But there's a catch. appeared first on The New Stack. ## Agents operate, humans govern: Scale your operations and reduce toil with Azure SRE Agent DevFeed: [Agents operate, humans govern: Scale your operations and reduce toil with Azure SRE Agent]() Original publisher: [Read original article]() Author: TNS Staff Published: 2026-09-15T16:21:45Z Content type: article Language: en Sources: [The New Stack]() Topics: [SRE](), [incident](), [Azure](), [observability](), [DevOps](), [Redis]() Tags: [agent](), [ai-agents](), [ai-operations](), [azure](), [code-review](), [deployment](), [devops](), [incident](), [microsoft-azure](), [monitoring](), [observability](), [post](), [redis](), [sponsor-microsoft-azure](), [sponsored](), [sponsored-post](), [sre](), [telemetry]() ### AI overview The article describes Azure SRE Agent as a system that analyzes telemetry, correlates deployment and monitoring data, investigates incidents, identifies root causes, recommends or prepares fixes, and supports mitigation and other operational tasks under human approval. It cites examples involving Microsoft service teams and InEight, including a recommendation to scale Redis. ### Source excerpt What if engineers could spend their time building and optimizing systems rather than maintaining them? It's 3 a.m., and the The post Agents operate, humans govern: Scale your operations and reduce toil with Azure SRE Agent appeared first on The New Stack. ## How to attach an owner to every cloud resource you find DevFeed: [How to attach an owner to every cloud resource you find]() Original publisher: [Read original article]() Author: Zeen Rachidi Published: 2026-09-15T14:00:00Z Content type: tutorial Language: en Sources: [The New Stack]() Topics: [Cloud](), [Provisioning](), [Open Policy Agent](), [audit trail]() Tags: [audit-trail](), [cloud](), [cloud-services](), [devops](), [env-zero](), [how-to](), [logs](), [open-policy-agent](), [platform-engineering](), [policy](), [post-contributed](), [provisioning](), [sponsor-env-zero](), [sponsored-post-contributed]() ### AI overview This tutorial explains how to identify cloud resources without assigned owners and prevent new ownerless resources. It presents continuously synced inventory queries, Open Policy Agent policies requiring owner tags, and logs or audit trails for resource governance. ### Source excerpt The engineer who knew why that cloud instance existed has left the company. The instance is still running, the bill The post How to attach an owner to every cloud resource you find appeared first on The New Stack. ## Kubernetes 1.36 restores a lost guarantee for database backups DevFeed: [Kubernetes 1.36 restores a lost guarantee for database backups]() Original publisher: [Read original article]() Author: Shubham Pampattiwar Published: 2026-09-15T13:00:00Z Content type: news Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack](), [The New Stack]() Topics: [Kubernetes](), [PostgreSQL](), [Databases]() Tags: [backups](), [cncf](), [consistency](), [database](), [databases](), [kubernetes](), [post-contributed](), [postgresql](), [snapshots](), [sponsor-cncf](), [sponsored-post-contributed](), [stateful](), [storage]() ### AI overview The article explains how Kubernetes 1.36 restores coordinated snapshots for applications whose state spans multiple volumes, addressing inconsistent database backups caused by taking individual PersistentVolumeClaim snapshots at different times. ### Source excerpt It's 2 a.m., and you're restoring a PostgreSQL cluster from last night's backup. Its data directory lives on one PersistentVolumeClaim The post Kubernetes 1.36 restores a lost guarantee for database backups appeared first on The New Stack. ## AI's best coding agent fails 60% of the time -- and the data backs it up DevFeed: [AI's best coding agent fails 60% of the time -- and the data backs it up]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-14T22:22:27Z Content type: news Language: en Sources: [The New Stack]() Topics: [Benchmark](), [AI-assisted coding](), [Fable](), [Claude Code](), [codex](), [Command-line interface](), [anthropic]() Tags: [ai](), [ai-engineering](), [ai-models](), [benchmark](), [benchmarks](), [claude-code](), [cli](), [codex](), [coding](), [fable](), [performance](), [software-testing]() ### AI overview Real-SWE evaluates coding agents on private company codebases and reports substantially lower success rates than public-repository benchmarks. Claude Fable 5.1, running through Claude Code, led the comparison with a 38.8% score, while the tested systems often failed most attempts. ### Source excerpt Claude Fable 5.1 just won a new coding benchmark despite failing more than six out of 10 times. Its 38.8% The post AI's best coding agent fails 60% of the time -- and the data backs it up appeared first on The New Stack. ## Perplexity's new agent runs entirely on your GPU -- with one expensive catch DevFeed: [Perplexity's new agent runs entirely on your GPU -- with one expensive catch]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-14T18:21:44Z Content type: news Language: en Sources: [The New Stack]() Topics: [GPU](), [Nvidia](), [Windows](), [Orchestration](), [qwen](), [Cloud](), [browser](), [Ollama]() Tags: [ai-agents](), [ai-infrastructure](), [gpu](), [hardware](), [infrastructure](), [news](), [nvidia](), [ollama](), [orchestration](), [qwen](), [windows]() ### AI overview The article reports that Perplexity's Portable Computer, a local version of its Computer agent, is available in the Perplexity app for Windows on compatible Nvidia GeForce RTX and RTX PRO GPUs. It requires at least 24GB of VRAM and combines local models, orchestration, a browser, tool calling, and a proprietary SPACE sandbox. The article also discusses platform-specific engineering, external service connectors, and the boundary between local and cloud computing. ### Source excerpt Running an LLM on your PC is easy enough, but putting an agent to work there is a different story. The post Perplexity's new agent runs entirely on your GPU -- with one expensive catch appeared first on The New Stack. ## Your AI coding spend bought 25% more output. Duplication rose 81%. DevFeed: [Your AI coding spend bought 25% more output. Duplication rose 81%.]() Original publisher: [Read original article]() Author: Steve Fenton Published: 2026-09-14T14:39:14Z Content type: article Language: en Sources: [The New Stack]() Topics: [ai-coding](), [Claude Code](), [cursor](), [datasets]() Tags: [agentic](), [ai](), [ai-coding](), [ai-impact](), [ai-operations](), [ai-strategy](), [ai-tools](), [claude-code](), [coding](), [contributed](), [contributed-octopus-deploy](), [cursor](), [dataset](), [software-development]() ### AI overview The article examines the return on investment from AI coding tools. It reports that heavy users gained 25% over their previous velocity, while code duplication rose 81%, and argues that output measures such as lines of code, pull requests, and feature counts do not reliably represent business value. ### Source excerpt Since they arrived on the scene, a great swathe of the software industry has pinned its hopes on AI tools, The post Your AI coding spend bought 25% more output. Duplication rose 81%. appeared first on The New Stack. ## Chinese AI models dominate OpenRouter's US token consumption. It can now guarantee that traffic stays entirely in the US. DevFeed: [Chinese AI models dominate OpenRouter's US token consumption. It can now guarantee that traffic stays entirely in the US.]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-14T13:59:33Z Content type: news Language: en Sources: [The New Stack]() Topics: [AI Models](), [Routing (disambiguation)](), [Security](), [data](), [Availability](), [hugging face](), [Nvidia](), [Nemotron](), [OpenAI]() Tags: [ai](), [ai-infrastructure](), [ai-models](), [availability](), [data](), [hugging-face](), [large-language-models](), [models](), [nemotron](), [nvidia](), [openai](), [routing](), [security]() ### AI overview OpenRouter has launched US in-region routing for business and enterprise customers. Requests sent through its US endpoint are decrypted, processed, and served entirely inside the United States, or rejected if that cannot be guaranteed. The feature addresses concerns about data location when businesses use open-weight models, including models developed in China. ### Source excerpt Everyone knows the open-weight model pitch by now: companies can download the weights, customize them, run them on infrastructure of The post Chinese AI models dominate OpenRouter's US token consumption. It can now guarantee that traffic stays entirely in the US. appeared first on The New Stack. ## Using Exact-Match Response Caching to Reduce LLM Costs DevFeed: [Using Exact-Match Response Caching to Reduce LLM Costs]() Original publisher: [Read original article]() Author: Abhilash Rao Mesala Published: 2026-09-14T11:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Caching](), [Large Language Model]() Tags: [ai-engineering](), [ai-infrastructure](), [caching](), [contributed](), [cost](), [finops](), [generation](), [hash](), [llm](), [token]() ### AI overview The article explains how to reduce LLM costs by fingerprinting requests, context, model settings, and underlying data to create exact-match cache keys. Valid cached responses can be reused without calling the model. It distinguishes response caching from provider prompt caching, where only eligible prompt computation is reused. ### Source excerpt An LLM can answer the same question a thousand times and charge you each time. Before paying for another answer, The post Why an old caching trick is your secret to lower LLM costs appeared first on The New Stack. ## Chip Huyen explains how to cut inference costs without new hardware DevFeed: [Chip Huyen explains how to cut inference costs without new hardware]() Original publisher: [Read original article]() Author: Tim Koopmans Published: 2026-09-13T15:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Inference Performance](), [Low-Latency Inference](), [model-deployment](), [Optimization](), [Frontier Model](), [AI Engineering](), [Latency](), [math]() Tags: [ai](), [ai-agents](), [ai-engineering](), [ai-infrastructure](), [frontier-model](), [inference](), [low-latency](), [metrics](), [optimization](), [performance](), [post-contributed](), [reasoning](), [scylladb](), [sponsor-scylladb](), [sponsored](), [sponsored-post-contributed](), [tokens]() ### AI overview Chip Huyen explains why inference costs can outweigh one-time frontier-model training costs and outlines ways to optimize inference without new hardware. The article emphasizes latency metrics such as time to first token, time per output token, end-to-end latency, and goodput, especially for reasoning models. ### Source excerpt Last October, the P99 conference -- the online gathering for developers focused on high-performance, low-latency applications -- featured a cracking The post Chip Huyen explains how to cut inference costs without new hardware appeared first on The New Stack. ## "Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason DevFeed: ["Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason]() Original publisher: [Read original article]() Author: Adrian Bridgwater Published: 2026-09-13T14:21:46Z Content type: news Language: en Sources: [The New Stack]() Topics: [Mixture of Experts (MoE)](), [cohere](), [Artificial Intelligence](), [Benchmark](), [Inference](), [qwen](), [gemma4](), [Google]() Tags: [ai](), [ai-infrastructure](), [ai-models](), [aya](), [benchmark](), [cohere](), [gemma](), [google](), [inference](), [large-language-models](), [mixture-of-experts-moe](), [model](), [open](), [qwen]() ### AI overview Cohere's North Small Translate is an open-weight mixture-of-experts machine translation model covering 50 languages. The article discusses its non-reasoning design, sovereign AI positioning, deployment options, efficiency claims, and reported WMT26 benchmark comparisons. ### Source excerpt Enterprise AI company Cohere announced North Small Translate last week, a mixture-of-experts (MOE) open-weight machine translation model that works across The post "Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason appeared first on The New Stack. ## It passed CI. It passed your evals. The customer still got the wrong answer. DevFeed: [It passed CI. It passed your evals. The customer still got the wrong answer.]() Original publisher: [Read original article]() Author: Sean O'Dell Published: 2026-09-13T14:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI Agent](), [agent observability](), [observability](), [tracing](), [dynatrace](), [ci](), [coding]() Tags: [ai](), [ai-agent](), [ai-agents](), [ai-engineering](), [ci](), [coding](), [dynatrace](), [observability](), [post-contributed](), [sponsor-dynatrace](), [sponsored](), [sponsored-post-contributed](), [traces]() ### AI overview The article explains how AI-agent failures can pass CI and evaluations while still producing slow or incorrect customer-facing results. It presents distributed traces and agent trajectories--model calls, tool calls, arguments, and results--as evidence for debugging retrieval behavior, release context, and feature-flag state. ### Source excerpt A diff is not evidence. It's a statement of intent. The tests passed. The review's done. The change is live. The post It passed CI. It passed your evals. The customer still got the wrong answer. appeared first on The New Stack. ## Why MCP security is about permissions overhaul DevFeed: [Why MCP security is about permissions overhaul]() Original publisher: [Read original article]() Author: Mohit Bansal Published: 2026-09-12T15:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Model Context Protocol](), [Authorization](), [GitHub](), [anthropic]() Tags: [ai-agent](), [ai-agents](), [github](), [mcp](), [model-context-protocol-mcp](), [post-contributed](), [security](), [sponsor-webflow](), [sponsored-post-contributed](), [webflow]() ### AI overview The article argues that MCP security problems are fundamentally permission problems, not merely infrastructure flaws. It calls for compartmentalized, task-scoped access to reduce risks such as prompt injection, tool poisoning, and excessive inherited trust. ### Source excerpt Anthropic's Model Context Protocol (MCP) went into production in late 2024. It spread rapidly after that. Since then, thousands of The post Why MCP security is about permissions overhaul appeared first on The New Stack. ## "Same mission, bigger stage": OpenAI hires Git AI founders to help Codex prove its ROI DevFeed: ["Same mission, bigger stage": OpenAI hires Git AI founders to help Codex prove its ROI]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-12T14:46:53Z Content type: news Language: en Sources: [The New Stack]() Topics: [ai observability](), [cursor]() Tags: [ai](), [ai-agents](), [ai-coding](), [codex](), [cost](), [cursor](), [developer-tools](), [git](), [open-source](), [openai]() ### AI overview OpenAI hired Git AI's founders to help measure the performance, cost, and return on investment of Codex and other AI coding tools. ### Source excerpt OpenAI has hired the founders of Git AI, an open-source tool that tracks how much code is written by AI The post "Same mission, bigger stage": OpenAI hires Git AI founders to help Codex prove its ROI appeared first on The New Stack. [Next page]()