Results for “Agent”

Help Net Security Mirko Zorz Security

Your AI red team may be finding the same prompt injection thousands of times

AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working attacks produced the weaker defense. Prompt injection purple-teaming workflow (Source: Research paper) Someone hides instructions in an email, a web page or a tool’s output, and the AI agent that ……

Read at Help Net Security

Digital Trends Anvinraj Valiyathara

Meta is putting Muse in a Chrome sidebar, and the official announcement just arrived

Meta has officially announced a Muse Chrome extension that puts the agent in a sidebar. It quietly appeared last week, and 200,000 people are already using it.

Read at Digital Trends

Digital Trends Rachit Agarwal

Google built a fake internet so Chrome’s AI doesn’t break your real one

Google built an entire fake internet, complete with banks and social feeds, to train Chrome’s AI agents. Here’s why the real web was too hostile to practice on.

Read at Digital Trends

Help Net Security Anamarija Pogorelec Security

AI agent API security hasn’t caught up with agents already running in production

Postman asked nearly 9,000 developers, architects and executives how they’re handling AI agents, and the answers tell a familiar story. Companies put the new thing to work first and left the question of who holds the keys for later. A quarter of the organizations that answered already have agents calling their APIs in production. Source: Postman The keys are where it gets uncomfortable. About four in ten respondents haven’t worked out how credentials and identity … More →

Read at Help Net Security

Digital Trends Anvinraj Valiyathara

Apple wants its own AI assistant for the Mac, and a late 2027 launch is already in view

Apple is working on its own AI assistant that can use a Mac the way a capable person would, according to a Bloomberg report. The report is based on a job listing Apple posted this week for a senior engineering manager to lead a proactive AI assistant. The posting asks you to imagine an agent

Read at Digital Trends

The New Stack Chris J. Preimesberger

Does your AI agent need an LLM to decide what to do next?

Say “good morning” to an AI agent, and it might search its long-term memory before saying hello back. Somewhere in

Read at The New Stack

Tech in Asia Naomi Li Gan Startups

MAS warns of financial risks from AI agents

MAS plans a “know your agent” protocol to identify agents and verify their identity, authority, and mandate.

Read at Tech in Asia

TechCrunch AI Lucas Ropek SI

Apple may be developing its own AI agent that runs your Mac

The iPhone maker appears to be building agents that can compete with the likes of Meta Muse, Instinct, Claude, and OpenAI Dots.

Read at TechCrunch AI

Tech in Asia Grace Priscilla Teo Startups

GitLab 19.6 adds AI agent scheduling and security triage

The company said updates to its GitLab Duo Agent Platform will let most customers get up to 2x the work from the same GitLab Credits.

Read at Tech in Asia

AWS Machine Learning Blog Alex Thewsey SI

Use Kimi Code CLI with models on Amazon Bedrock

Kimi Code CLI v2.7.0 adds a native Amazon Bedrock provider, so you can connect the open source coding agent to models like Kimi K3.1 Pro using your standard AWS credential chain (named profiles or SSO) instead of a separate API key. This post shows how to configure the provider and send your first request.

Read at AWS Machine Learning Blog

SiliconANGLE AI Duncan Riley SI

Resolve AI’s SRE-1 model finds root causes of production alerts as AI agents go on call

Incident remediation company Resolve AI Inc. has announced the launch of SRE-1, a new model that has been trained to find the root cause of production alerts, and Primary On-call, a new service that puts its artificial intelligence agents on call ahead of human engineers. The new model, announced Wednesday, reflects the company’s argument that

Read at SiliconANGLE AI

AWS Machine Learning Blog Madhu Samhitha Vangara SI

Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore payments

Amazon Bedrock AgentCore payments now supports AWS Marketplace, so agents can discover and buy x402-enabled products, APIs, data, and content and pay in USD on the developer's AWS bill, with no stablecoin wallets or API keys. This post walks through a research agent that finds a tool, pays per request through AWS Billing, and answers with sources.

Read at AWS Machine Learning Blog

MacRumors Juli Clover Gadgets

Apple is Building an AI Agent That Can Use Apps and Code

Apple is working on a proactive AI agent like Meta's Muse or OpenAI's Dots, according to job listings spotted by Bloomberg. The listing describes an AI agent that can code, use apps, and browse the web. Imagine an AI agent that can use a computer the way a capable person does. It browses the web, works across apps, runs commands, writes and debugs code, and calls services, and it chooses the right tool for each step. It does all this privately and with the polish people…

Read at MacRumors

Dark Reading Robert Lemos Security

Qwen Incidents Show Self-Hosted AI Models Need Stronger Steering

Companies deploying AI agents have the illusion of control, but several incidents demonstrate that businesses need to be ready to enforce directions.

Read at Dark Reading

The Verge Emma Roth SI

Apple is hiring engineers to build its own AI agent

Apple is working on its own AI agent that can perform a range of tasks for you, including browsing the web, working across apps, writing code, and calling services. That's according to a job listing spotted by Bloomberg, which says Apple is looking for an engineer to lead the creation of an agentic AI assistant.

Read at The Verge

9to5Mac Marcus Mendes SI

Report: Apple job listings detail plans for autonomous AI agents

Bloomberg reports that Apple is hiring engineers to develop an autonomous AI agent capable of browsing the web, writing code, and controlling apps on behalf of users. Here are the details.

Read at 9to5Mac

AWS Machine Learning Blog Dr. Jens Kohl SI

How the BMW Group governs hundreds of agents across thousands of developers

When hundreds of agents serve thousands of developers, governance cannot be an afterthought. The BMW Group shares the practices and patterns its R&D teams use to build, govern, and operate AI agents at enterprise scale without sacrificing speed, quality, or compliance.

Read at AWS Machine Learning Blog

The Hill Ryan Mancini Geopolitics

Becerra suggests prosecutions for AI attacks

California Gov.-elect Xavier Becerra (D) on Thursday suggested that humans behind AI cyberattacks should face prosecution. "If some of these incursions that we’ve seen by these AI agents have been done by human beings, we’d have filed criminal charges against those individuals," Becerra said in an interview at Politico Pub at the National Governors Association’s...

Read at The Hill

Hacker News StackBuilders SI

AI Agent Authorization That Limits the Damage of Prompt Injection

Article URL: https://www.stackbuilders.com/insights/ai-agent-authorization-that-limits-the-damage-of-prompt-injection/ Comments URL: https://news.ycombinator.com/item?id=50566999 Points: 2 # Comments: 0

Read at Hacker News

TechCrunch AI Dominic-Madori Davis SI

These tech outages are giving Y2K, AI agent style

Are the recent outages in the airline booking systems, banking platforms, and productivity platforms really a coincidence? There's actually likely something deeper going on, cybersecurity experts say.

Read at TechCrunch AI

The Decoder Matthias Bastian SI

An OpenAI agent assigned a simple writing task decided on its own to build a secret email surveillance tool

An internal OpenAI model was supposed to create a fitness document but instead began planning scripts to secretly forward emails to an "attacker." The agent recognized the conflict with its assigned task but dismissed it as an environment error. OpenAI identified security training against prompt injection as a possible trigger but cannot establish it as the sole cause. The article An OpenAI agent assigned a simple writing task decided on its own to build a secret email…

Read at The Decoder

SiliconANGLE AI Paul Nashawaty SI

Enterprise AI is pushing cloud infrastructure beyond the GPU

Enterprise adoption of artificial intelligence is creating new requirements for enterprise AI infrastructure. While much of the early AI investment centered on access to powerful GPUs, organizations moving AI applications and agents into production are discovering that accelerators are only one part of the equation. Agentic AI systems need environments where they can execute code,

Read at SiliconANGLE AI

The Verge Jay Peters SI

Meta’s Muse Charm might cost $300

Meta is planning to price the Muse Charm, a little gadget with a screen that lets you chat with your Muse AI agent, at $300, according to The Information. CEO Mark Zuckerberg revealed the gadget earlier this year and said the company expected to ship the Charm "in time for the holidays in December," but

Read at The Verge

AWS Machine Learning Blog Evandro Franco SI

Amazon Bedrock AgentCore harness adds Strands harness defaults, built-in tools, and lifecycle hooks

Amazon Bedrock AgentCore harness now runs on the open-source Strands harness, bringing a recommended model, task-oriented defaults, automatic prompt caching, proactive context management, and new built-in tools. It also adds lifecycle hooks so you can run deterministic allow or deny checks at defined points in the agent loop.

Read at AWS Machine Learning Blog

arXiv (research papers) Weihao Cheng SI

PlayCraft: Designing Engaging Games from Agent Play Experience

Recent AI agents can generate playable games, but these games are not necessarily engaging. Mastery is a key source of engagement, yet designing for it requires extensive human play and tuning. We propose PlayCraft, an automated framework that uses a vision-based agent to play games and draws on its detailed play experience to revise them for mastery. Starting from an initial game, PlayCraft alternates between playing and crafting. In the playing stage, a player agent…

Read at arXiv (research papers)

arXiv (research papers) Yiyang Du

AgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot Control

Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce…

Read at arXiv (research papers)

arXiv (research papers) Amine Lbath SI

SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research

LLM-based agents are becoming increasingly capable at discovering, validating and patching vulnerabilities in real software, and vendors and researchers report that this is already changing how vulnerabilities are found and fixed. These claims, however, are scattered across papers, vendor reports and disclosures and are rarely comparable. We introduce a framework that rates these capabilities on an autonomy scale modeled on the levels of driving automation, and qualifies…

Read at arXiv (research papers)

AWS Machine Learning Blog Rakesh Vangari SI

From learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI League

Cisco and AWS used Cisco Transformation Fest and AWS AI League to turn hands-on AI learning into a culture of building. A Cisco engineer won the 2025 AWS AI League global title and 1,200 engineers competed in 2026. This post shares Cisco's journey, lessons from the 2026 winning agent built on Amazon Bedrock AgentCore, and how to host your own league.

Read at AWS Machine Learning Blog

The New Stack Chris J. Preimesberger

“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

Read at The New Stack

arXiv (research papers) Mengxiao Wang SI

Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)

Agents based on large language models (LLMs) can now delete files and send payments on behalf of their users. News media reports routinely describe failures of these agents (e.g., Replit's coding agent deleting a production database), but a report often only says what went wrong and rarely (in)validates the incident or finds its root cause. Incident catalogs collect these reports, and benchmarks record whether agents fail, but neither replicates an incident nor tests the…

Read at arXiv (research papers)

Older stories