T
A gap has long existed between the shipping velocity of the best engineering teams and the rest of the bell curve. For most of the industry’s history, it was a multiple measured in deploys per week. Agents are turning that multiple into an exponent, and the dividing line is no longer tooling or talent. It is whether a team has rebuilt its delivery system into what the industry now calls a “software factory,” a largely autonomous system where intent goes in, agents plan, write, test, and ship…
T
Ask an SRE a deceptively simple question: What is the right size for checkout-api, and how many replicas should it run right now? Their Helm values specify replicas: 3, cpu: 1000m, and memory: 2Gi. But the live cluster tells a different story: HPA has scaled the app to 11 replicas on CPU load; VPA insists it is over-provisioned, recommending cpu: 350m and memory: 3.1Gi; KEDA demands 24 replicas due to an upstream Kafka lag spike; and Karpenter has provisioned two new nodes, sizing physical…
T
For teams running AI workloads on Kubernetes, a fully allocated GPU pool and a growing batch-job queue might make expanding the pool seem like the obvious next step. But a growing queue could point to timing, serving capacity, or the choice of model and hardware. Before expanding a GPU pool, teams should define what success looks like, when it must finish, and what it costs to deliver. “An allocated GPU, a busy GPU, and a workload producing valuable results are not the same thing.” That starts…
T
Vercel wants to eliminate long-lived API keys from its ecosystem. It is giving Marketplace vendors until January 2027 to offer more secure authentication or risk being delisted. The push comes as credential-stealing supply chain attacks — including a recent npm worm that scraped tokens straight out of CI pipelines — keep proving how much damage a single leaked secret can do. In an October 22 announcement, Vercel CTO Malte Ubl said the company surveyed more than 1,000 SaaS vendors and found that…
T
Welcome to another edition of Road to KubeCon! We’re tracking movements in the Kubernetes and cloud-native ecosystem as we count down to KubeCon + CloudNativeCon North America 2026 November 9–12 in Salt Lake City. Half of our column this week focuses on untangling Kubernetes as we add the demands of agentic AI: automating pod-restart troubleshooting, syncing communication between the scheduler and autoscaler, and maturing how we distribute inference across a cloud-native stack. The other half…
T
Linux is already part of the AI developer’s desktop toolkit. Nvidia’s DGX Spark, which became available to order on October 15, 2025, runs the Ubuntu-based DGX OS. OpenAI’s Codex CLI already supports Linux, another example of AI tools meeting developers where they work. There’s just one problem. Developers can fall in love with Linux at home. Getting enterprise IT to let them use it at work is another matter. Angelo Huang, founder and CEO of Swif.ai, a platform that manages and secures employee…
T
Government websites and public services across Europe went offline this week as organizations responded to two newly disclosed PHP vulnerabilities. Germany took several federal websites offline, France temporarily shut down prefecture sites, Belgium’s foreign ministry disabled its websites, and organizations in the Netherlands pulled public-facing services as a precaution. It wasn’t confined to Europe, with countless other entities and businesses worldwide responding similarly. They were all…
T
“I think you said, ‘representative.’” It’s the fastest way to bypass automated speech recognition chatbots that fail to route human callers to the service they need. Achieving a human handoff to a living, breathing representative still feels like a badge of honor. Microsoft wants to change that dynamic. Naomi Moneypenny, senior director of product development at Microsoft Foundry Models division, blogged on October 1 to introduce three new Microsoft AI (MAI) models in Microsoft Foundry,…
T
AI agents are getting better at remembering past conversations and earlier tasks but remembering something doesn’t guarantee an agent can use it to do better work next time. Letta’s new FrontierMemory benchmark, released Wednesday, tests that gap by measuring whether agents can learn from experience rather than by just retrieving stored information. Early results show a widespread in performance across agent harnesses, the the infrastructure that manages how an agent operates. Letta Dream came…
T
Ramp spent months testing managed agent APIs, open-source frameworks, and third-party platforms before concluding it would be better off building its own. The result is Laminar, an internal agent harness that took six weeks to reach a first version and now powers every agentic product at the fintech company. “We studied the other offerings on the market and decided that we could do better, move faster, and have stronger alignment to where we want to go by building in house.” “We studied the…
T
OpenAI on Thursday announced that it is donating the Open Responses API specification to the open source Agentic AI Foundation (AAIF). In addition to Open Responses, OpenSandbox, Anthropic’s Agent Skills, and HuggingFace’s OpenEv framework for agent environments are also joining the AAIF. The join other AAIF projects like the MCP and A2A protocols, AGENTS.md (also from OpenAI), the open source AI agent goose, agentgateway, and Agent Router. The foundation, which is part of the Linux Foundation,…
T
This week, OpenAI put COBOL in the spotlight. It announced benchmark results suggesting its latest models are getting much better at migrating COBOL programs and building software in languages with less code and documentation for models to learn from. On OpenAI’s own COBOL migration test, GPT-6.1 Sol reached 86.6% accuracy at low reasoning effort, up from GPT-5.6 Sol’s 5.4%, while costing 39% less. At higher reasoning effort, the newer model reached 97.9%. But the evidence behind the two…
T
At PyTorch Conference North America 2026 this week, Google open-sourced TorchTPU, a native PyTorch stack for Google TPUs, now available on GitHub. AWS also launched TorchNeuron in public beta, its open-source native PyTorch backend for AWS Trainium, also available on GitHub. Both releases seem aimed at making it easier for developers to move beyond Nvidia GPUs, whose CUDA software ecosystem has long dominated AI development. But while Google and AWS’s new offerings do ease some of the…
T
Did one of your favorite websites go dark on Wednesday? Some did, as operators took services offline while they waited for fixes to two critical flaws in PHP, the language behind much of the web. The precaution didn’t mean those sites were hacked. The holes themselves were bad news with a capital B. But the bigger long-term concern might be how the embargo on the patches was handled. PHP powers roughly 70% of websites, but that figure describes PHP’s reach, not the number of vulnerable or…
T
At 2:07 a.m., an AI agent starts failing. The application is still running, but requests are timing out because a downstream API is returning errors. The agent has already retried twice, using more tokens than usual, and its response time has roughly doubled. The first question should not be: “Which model should we use?” It should be: “Who owns this system right now?” That question is easy to overlook when building AI agents. Teams often pour effort into prompts, retrieval, tools, and model…
T
One of the biggest security scares to hit the web is causing widespread disruption, prompting businesses, hospitals, schools, and government agencies to temporarily shut down websites and online services as they scramble to protect themselves against two critical vulnerabilities in PHP, the programming language underpinning much of the internet. The vulnerabilities, collectively dubbed PHP2Shell, could allow unauthenticated attackers to execute malicious code on affected servers. Major…
T
DeepSeek released V4.1-Flash-1017 on October 17 as an update to its Flash model. Its change log says the update cuts task runtime and output length. It lists 11 benchmark scores, including 42.3 on Terminal-Bench 4.0. Developers can use it through DeepSeek’s API or a service like OpenRouter. Because it’s an open-weight model, they can also download it from Hugging Face and run it on their own servers. I tested it through OpenRouter on DeepSeek’s own servers, at DeepSeek’s prices. DeepSeek’s…
T
Enterprise security has traditionally operated on a relatively straightforward premise: establish identity, authenticate the requester, determine what that identity can access, and enforce those permissions. AI agents introduce a fundamental complication. They don’t simply access systems. They interpret objectives, select tools, create sub-agents, make decisions, and execute actions, often using credentials and permissions inherited from humans. The problem isn’t necessarily that an agent lacks…
T
Google will soon make the infrastructure that powers its Gemini agents available to Google Cloud users in preview. Announced on Thursday at the Linux Foundation’s AGNTCon+MCPCon in San Jose, Agent Compute Engine will become available in preview to Google Cloud users later this year. It will provide every AI agent with a hardware-isolated microVM that combines the speed of containers with the security of a sandbox. Who else offers agent sandboxes? The idea of agent sandboxes is anything but new,…
T
PHP powers roughly 70% of the world’s websites, according to Wiz Research, so a flaw in its core engine affects much more than any single application. On Wednesday, researchers disclosed two critical vulnerabilities discovered with help from frontier AI models. OpenAI also proposed a new framework for handling the growing number of security flaws AI is helping uncover. The flaws, tracked as CVE-2026-109618 and CVE-2026-109619 and collectively called PHP2Shell, score 9.2 on the CVSS v4.0…
T
Anthropic first released Mythos-class models in February 2026, but CEO Dario Amodei said it delayed broader access until June to build stronger cybersecurity safeguards. Amodei laid out that reasoning Tuesday in a lengthy post on X, written in response to criticism from Nathan Calvin and defending the company’s approach to AI safety. He conceded the decision may have cost Anthropic a competitive edge. Releasing the models sooner, he argues, would have given organizations less time to prepare…
T
Tech leaders face a dilemma as they prepare to put AI agents into production. They want the higher productivity and lower costs that AI agents can provide. But they fear unknown risks from AI capabilities that differ from the rest of their software stack. When an agent makes decisions and takes actions on its own, it might be doing its best work. It might also be doing its worst. As AI agents become more capable, organizations want assurance that their oversight can keep up. How do they strike…
T
AI coding tools can produce a striking burst of productivity — but the initial surge may not last. A Carnegie Mellon study of public repositories adopting Cursor found a three- to five-fold increase in lines added during the first month, with the gains dissipating after roughly two months. The study, which used SonarQube (Sonar’s core platform) to measure code quality, also found that static analysis warnings rose by 30% and code complexity by 41%. The short-term velocity boost therefore comes…
T
Nvidia wants new AI capacity to show up at the data center fully built. At its GTC Berlin conference on Wednesday, the company introduced DSX POD, a reference design for shipping containers that partners fill with Vera Rubin racks, networking, and liquid cooling before they leave the factory. Installing and wiring up racks in a conventional data center can take months, Nvidia says. But a DSX POD can be ready to deliver tokens in as few as 14 days, as long as the site already has the necessary…
T
Every enterprise company is currently trying to figure out how to have its AI tools work with its data. Meanwhile, every major enterprise vendor that works with those enterprises (think SAP, Microsoft, Salesforce, Workday, etc.) is making a claim on becoming the central hub for managing and securing that data. But what about the companies that want to do it themselves? Nvidia, on Wednesday, announced how it wants to provide enterprise AI agents with the data they need to make sense of company…
T
Respan released an open-source AI gateway written in Rust on Tuesday, after spending two years building more than 100,000 lines of wrapper code around LiteLLM. The new gateway replaces that system with a small core and plugins that handle model providers, routing, MCP tools, realtime voice, and security controls. A LiteLLM upgrade breaks The breaking point came in January 2026, when a routine LiteLLM upgrade caused intermittent connection failures. Respan rolled back the update but never…
T
Cloudflare is going all-out to ensure that AI coding agents can check their work without exhausting available computing resources, leading a new effort to bring Microsoft’s TypeScript compiler to Rust. But whatever you do, don’t call it a fork. Taking to X, Cloudflare’s director of engineering Christoph Nakazawa confirmed that the company is taking ownership of tsrs, a Rust port of TypeScript that it claims is up to eight times faster, and uses 70% less memory than TypeScript 7.0. Microsoft’s…
T
Impressive benchmark results should make it easy for engineers to select the right open model for the outcome they are tasked with developing. However, that is not the case. Benchmarks indicate an open model’s optimal performance, but in production, a model must work repeatedly. The challenge is that in production, other factors matter, such as the information provided to the model and its accuracy. So benchmarks can’t tell an engineer whether the AI they are developing will complete the task…
T
ElevenLabs launched Eleven Realtime on Tuesday, introducing two managed voice-agent models, Mini and Max, that integrate speech recognition, reasoning, turn-taking, and voice generation. Both use a cascaded architecture, but developers can’t select or independently configure the underlying models. With this launch, the company is effectively taking over the voice-agent harness, including turn detection, interruption handling, and orchestration. With this launch, the company is effectively…
T
Nearly a year into the agentic coding explosion, many teams now use AI to write software as their de facto approach. As a result, Anthropic’s engineers are shipping eight times as much code as before, and some engineers are shipping thousands of PRs per month. Management teams expecting their engineering capacity to explode will find that AI-written code doesn’t necessarily compress the software development lifecycle (SDLC) on its own. The critical bottleneck in software creation has shifted…