XIO

xWire

Posts from every feed QUEST has found across the web — blogs, news, podcasts, channels and more.

AI Agents Archives - The New Stack

“Be ready for change”: AAIF’s CTO on why the agent stack won’t settle

If you’ve spent any time over the past year trying to get AI agents to talk to each other without tearing your architecture apart, you know the struggle: vendor lock-in, fragmented protocols, and context that definitely vanishes the second you attempt to make a cross-framework handoff. It’s astounding how fast developers’ needs have changed just in 10 months since the Agentic AI Foundation (AAIF) was formed to help solve those problems. The Linux Foundation-backed AAIF gives shared agent…

IDrive wants to back up your coding agents, too

Coding agents need backups, too, or at least that’s what IDrive is arguing. Backup and storage service IDrive on Thursday announced AI Agents Backup, a feature in its desktop app that finds the data these agents store locally for Claude Code, Cursor, Codex, and Cline and copies it to the user’s IDrive account. By default, agents tend to keep a lot of their state on a developer’s machine, including session transcripts, instruction files, and MCP server configurations. The problem is that most of…

A “headless Slack”: Vercel’s new message board lets Claude Code and Codex agents work together

For AI agents to work together effectively, they need a way to communicate and divvy up tasks — much as humans already do through a swath of digital collaboration tools. Vercel is tackling this with Board, an experimental shared message board through which agents can claim tasks, exchange findings and track progress across different tools and environments, while allowing developers to follow and intervene in the work. In a blog post published on Wednesday, Vercel says it developed Board for its…

Agent security is product security, and your marketing site counts

A marketing site used to have two kinds of visitors: people and search crawlers. Now an agent can build a page, a second agent can scrape it, a third can summarize it for a potential customer, and a fourth can optimize it overnight after studying yesterday’s traffic. “The ones that you do not control make the marketing site a product with agent users, and products need product security.” You control some of these agents but not all the data they ingest and train on. The ones that you do not…

Groundcover Investigations lets engineers steer AI SRE agents

Groundcover, the eBPF-based observability startup, has introduced Investigations, giving agents and engineers one place to collaborate on incident response in real time. In the shared workspace, groundcover’s investigator and moderator agents work with on-call engineers and their preferred coding agents to investigate production incidents together, analyzing behavior across applications and infrastructure to create a shared record of evidence. Rather than handing full control to agents, the…

Why groundcover’s CEO says agents are the power users of observability

An AI coding agent can write a patch in minutes. Ask it whether that patch slows down the API endpoint your customers hit most, and suddenly it needs something that lives outside the repository. It needs to see how the software runs. That’s the premise behind groundcover, an observability platform that wants to put production telemetry in the hands of developers and their coding agents. Yes, you read that correctly. In a conversation with The New Stack’s Frederic Lardinois at KubeCon +…

Google’s Gemini 4 Neon tripled its coding score without changing the model

Google’s new Gemini 4 Neon resolved 12.8% of the SWE-sweep coding benchmark using the mini-SWE harness, but that score jumped to 39.0% when the same model ran inside Antigravity. The more-than-threefold improvement raises questions about how much coding-agent performance comes from the underlying model and how much depends on the harness… Both results were reported Wednesday as part of the Neon launch. The more-than-threefold improvement raises questions about how much coding-agent performance…

Microsoft says Bing serves 1B people. Its next search engine isn’t for them.

Microsoft says its Bing search engine now has one billion monthly users. The company says those are humans — not AI agents — looking up information on the web. What most people may not realize, though, is that Microsoft also uses the same Bing index to serve agents through Web IQ. Web IQ is Microsoft’s agentic search service, competing with upstarts like Exa, Firecrawl, and Tavily. DeepSeek opened its own search API to developers in October. At Microsoft’s Ignite conference this week in San…

“The best escape room players that you’ve ever met”: What Red Hat’s AI architect really thinks about agents.

Last week at KubeCon + CloudNativeCon North America, a major gathering of the open-source and cloud-native communities, many speakers — when they weren’t contemplating what the then-rapidly unfolding Nvidia fiasco would mean for them — worried about AI security. Hence, all the coverage of OpenShell and Agent Substrate. So it fit the mood when Jessica Forrester, Red Hat’s chief architect of AI Catalyst Engineering, opened her keynote at the Salt Palace Convention Center in Salt Lake City by…

OpenAI spent $1.2 million finding nearly 1,000 Linux security flaws. Sam Altman says this is just the beginning.

OpenAI spent approximately $1.2 million in API costs to generate working exploits for 948 Linux kernel vulnerabilities. At The New York Times’ DealBook Summit on Wednesday, CEO Sam Altman pointed to those results as an example of what developers could accomplish by spending substantially more on compute to solve difficult engineering problems. “Apply that to optimizing your code, apply that to solving other hard problems. All that’s coming,” Altman says, appearing alongside OpenAI President…

How Orkes ParticleDB turns an impressive demo into a remarkable application

Building an AI agent that performs an impressive demonstration is one thing. Building one that can reliably process financial transactions, handle customer refunds, or make business decisions without compromising sensitive data is quite another. That distinction is becoming increasingly important as enterprises move from experimenting with generative AI to deploying agentic applications in production. Developers need more than powerful language models. They need dependable access to enterprise…

200 OK is dead as an AI agent health signal. Here’s what comes next.

A customer asks whether they can swap unworn boots for a size 10. The agent replies, in under a second, that it cannot help with that topic. The web service returns 200 OK. Latency is nominal, error counters are flat, and the Datadog dashboard stays solid green. A customer has just left, and nothing in the APM stack knows. That is the failure this article is about: the kind that looks like success. In lean manufacturing, this exact category of silent defect is solved using two twin principles:…

Why verification, not generation, is your secret to AI coding ROI

For two years, the question around AI coding was whether agents could write good code. Developers have largely answered it: AI now generates or significantly assists 65% of the code they commit, according to Sonar’s 2027 State of Code Developer Survey. A year ago that figure was 42%, and this year’s number matches what respondents then expected to see a year later. Clearly, adoption is outrunning expectations. “Clearly, adoption is outrunning expectations.” This is because AI tools are getting…

Your AI coding agent could cost 5x more depending on the harness, benchmark finds

The same AI model can cost up to five times more to run depending on the coding agent harness it’s paired with, according to a new benchmark that tested 22 configurations across five open-weight models. Runta and Baseten ran those combinations 27,280 times for FrontierHarness Eval v1.1, consuming roughly 83 billion tokens in the process. Nearly 65% of estimated inference spending went to runs that failed verification or timed out. The model itself accounted for 92.8% of the cost differences,…

OpenAI’s own tests show GPT-6.2 Astra is twice as likely to hide coding failures

OpenAI’s new GPT-6.2 Astra is nearly twice as likely as its predecessor to leave users unaware of problems that prevented it from finishing a coding task, according to the company’s own safety evaluations. Developers building autonomous agents could encounter the same problem, since OpenAI has added a mitigation to Codex that isn’t automatically applied to direct API requests. In its GPT-6.2 system card, published Tuesday alongside the release of GPT-6.2 Astra and GPT-6.2 Sol, OpenAI reported…

Replit’s agent swarms built an app monitoring platform in 2 days on a $3K budget. Now, it’s offering them to customers.

Agent swarms are all the rage, as companies set about finding ways to coordinate multiple AI agents to tackle complex tasks in parallel. In the past week alone, Google and Cursor unveiled competing approaches to multi-agent coding, building on existing efforts from companies including Anthropic, whose experimental Claude Code Agent Teams feature lets multiple agents collaborate on development tasks. OpenAI has also explored shared workspaces for agents. On Tuesday, Replit revealed that it’s…

AI agents were all over KubeCon. Production is another story

AI agents are testing systems that were originally built for people, and Jonathan Bryce thinks the cloud-native community has a lot of work to do to help those systems keep up in this new era. The New Stack sat down with Bryce, the executive director of the Cloud Native Computing Foundation (CNCF), at KubeCon + CloudNativeCon North America in Salt Lake City to talk about the projects joining the foundation and how AI is changing its work. Bryce tells The New Stack, “A lot of the existing…

Google found hackers using autonomous AI agents to turn security patches into exploits

Google’s Threat Intelligence Group says attackers are using autonomous AI agents to reverse-engineer security patches, generate exploits, and attempt to execute them without human approval. In a report published Monday, Google and Mandiant describe the first cases their researchers have identified of attackers using LLM frameworks to fully automate vulnerability discovery and exploitation. The framework uses an orchestrator to coordinate specialized agents, share context, and invoke tools…

DuckDB 2.0 goes client-server and adds an Agent Mode for coding agents

DuckDB has always been the database you don’t have to set up: Import it into your code and start querying. DuckDB 2.0 was released in October, and it can now run as a server that other machines can connect to. DuckLabs’ Gábor Szárnyas calls this the headline feature of the release. The team decided to make this latest upgrade a major release since that feature, along with a new storage format and a new SQL parser, marks a big shift in how DuckDB works. On The New Stack podcast, Szárnyas…

Dax Raad rebuilt his browser tool in Rust for $60. Then memory use fell 97%.

OpenCode developer Dax Raad says he rebuilt the project’s browser automation tool in Rust for $60, replacing the parts of Playwright and Patchright it actually used and dramatically reducing its memory footprint. A 4.3 MB binary The figures he posted to X on Saturday are striking. The new Rust binary is just 4.3 MB, compared with 53 to 64 MB for the previous Node version. Memory use for each OpenCode Browse connector also fell from roughly 190 MB to 5.6 MB after a few calls, a reduction of…

AWS Emulator proves agents need a verification loop. Realism is the hard part.

This week, Amazon Web Services released AWS Emulator, a local copy of AWS that coding agents can test against. It covers more than 200 AWS services and was written entirely by agents. The most useful part of the launch is a story Swami Sivasubramanian tells in the announcement. About 20 years ago, Sivasubramanian helped build the replication engine inside Alf, a Paxos-based lock service that still powers AWS systems such as S3 and DynamoDB. The first build took about four months. When he later…

Web search for agents is here: Why ranking still decides the answer

AI agents have had a URL problem for a while. When an agent needs current information but has no search tool, it often makes up the web address it thinks the answer lives at. It might guess something like docs.example.com/v4.2/auth, try to load it, and get a “page not found” error because the page doesn’t exist. Then it either keeps guessing or falls back on outdated information from its training. “Live web search gives AI agents fresh pages. Deciding which ones to trust over your own data is…

Claude Fable 5.2 vs. GPT-6 Astra: A lower list price didn’t mean a lower bill

Anthropic is positioning its new model, Claude Fable 5.2, for demanding coding and technical work. Anthropic launched Fable 5.2 on Nov. 9 and reported higher scores than OpenAI’s GPT-6 Astra on two coding benchmarks. Fable 5.2 also has lower standard API rates. Anthropic’s launch benchmarks put Fable 5.2 ahead of Astra, 49.1% to 42.8% on FrontierCode 2.0 and 69.9% to 65.5% on FrontierSWE v2. Fable’s 49.1% came at X high effort. At High, its default on the Claude API, it scored 45.3%. Benchmark…

Anthropic now lets you self-host Claude Managed Agents. The catch? 8 hours to act if it flags a safety risk in the software

Anthropic has unveiled a self-hosted version of its platform for building and running AI agents. Self-hosted Claude Managed Agents, as it’s aptly called, is available now in private beta. Customers host both the server that coordinates the agents and the sandboxes where the agents run their tools, either in their own cloud account or in an on-premises data center. Credentials and session histories stay on their infrastructure, while requests to Claude go to the inference provider they…

DeepSeek’s coding agent is too tidy for its own good — and benchmarks are punishing it

DeepSeek’s open-source coding agent is losing points on a major benchmark for a habit developers usually treat as good practice: cleaning up after itself. The problem surfaced when Hugging Face harness optimization researcher Joël Niklaus added DeepSeek Harness to his coding-agent leaderboard, which compares ten harnesses running the same underlying models. DeepSeek Harness is statistically tied for first across the board’s five scored evaluations, yet on Terminal-Bench alone it drops to sixth,…

Here’s how to teach AI agents to search like human experts

Agentic retrieval is a hot topic for a reason: Every company wants to automate work, but they often just are not ready. It’s also extremely easy — and tempting — to spin up an agent, point it at a mountain of data, and spend heavily on tokens for a lackluster result. To unleash agents that can accomplish work, you’ll need a different approach. You can’t throw a more intelligent AI model at a failing agentic workflow without first sorting out how to provide it with better data. It won’t do much…

Google’s Gemini 4 coding agent now switches models mid-task — and finishes 19% faster

Google launched Gemini 4 Hydrogen on Thursday alongside a new system that changes how coding agents use AI models. Rather than keeping its most capable model running across an entire session, Google is pairing Hydrogen with the more powerful Gemini 4 Carbon and switching between the two as the work progresses. The company says the combination gets nearly the same results as running Carbon on its own while using 24% less quota and finishing tasks 19% faster. How Orchestrator handles the work The…

Google’s coding agents now /swarm for one developer. Cursor’s go multiplayer so teammates’ agents can talk.

Coding agents are pretty good at working in parallel: one writes a new API endpoint, another updates the tests, while a third fixes a bug elsewhere in the codebase. However, they’re not quite so adept at knowing what their coding counterparts are doing — put several on one project and they duplicate work, trip over each other’s changes, and leave the developer firefighting the fiasco that follows. That’s why the major AI labs and coding-tool makers have all been looking for ways to bring order…

See what AI looks like in production at Microsoft Ignite

If you’re deciding which AI pilots to move into production, Microsoft’s Satya Nadella and Judson Althoff’s opening keynote at Microsoft Ignite will show you where the company is taking the tools you’ll use to build and run those agents. They take the stage at 10 a.m. Pacific on Tuesday, November 17. After the opening keynote, you can experience how customers put AI into production at scale, see where Microsoft is taking the tools those customers use, and compare notes with industry colleagues…

Anthropic built a model that beats Opus. It recommends Opus anyway.

Anthropic just released a coding model that beats Opus 5.5 on two major benchmarks and can complete certain difficult tasks for half the cost. Yet in its Fable 5.2 announcement on Monday, the company recommended that most developers stick with Opus, calling it the “strongest daily driver” for coding and knowledge work. “Based on capabilities and pricing, Claude Opus 5.5 is still our recommended model for most everyday work, from coding to knowledge work,” Anthropic tells The New Stack. “Based…