Knowledge catalogue
Data connectivity and integration firm CData Software Inc. today introduced Connect AI Gateway, a platform designed to control how artificial intelligence agents choose models, use tools and access co
arXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows la
arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model tha
arXiv:2609.30325v1 Announce Type: new Abstract: Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a
arXiv:2609.30614v1 Announce Type: cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM
Automated lint: 17 errors, 59669 warnings, 3 info
The article introduces the Unity Gateway Command Line Interface (CLI) as a tool for deploying and managing coding agents at large scale. It outlines how users can automate agent deployment, monitor pe
Enterprises are increasingly standardizing on Google Kubernetes Engine (GKE) to run their most critical and AI-driven workloads. From Cloud Storage FUSE for high-throughput data access to custom compu
arXiv:2609.28197v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has
Cybersecurity company Barracuda Networks Inc. today launched Barracuda AI Data Security, a product that monitors and controls what company data employees feed into artificial intelligence tools. The r
I shipped something I've been building for the last few weeks : phantom-kv , a refusal-removal system for large language models that doesn't touch a single weight. Instead of editing the model, it loa
Automated lint: 14 errors, 54840 warnings, 3 info
These are precisely the scenarios that I spend a significant time actually being concerned with. The adoption of unreliable, brittle, and inaccurate LLMs within safety-critical fields (e.g., defense a
arXiv:2609.17686v1 Announce Type: cross Abstract: Three recent results describe what look like unrelated LLM reliability problems. Yin et al. (2026) show reasoning RL collapses tool-reliability repres
Welcome to the first Cloud CISO Perspectives for September 2026. Today, Sandra Joyce shares the latest details on Google’s visibility into how attackers are using AI, and how we’re using AI to stop th
arXiv:2609.16647v1 Announce Type: new Abstract: Gender bias in large vision-language models (LVLMs) undermines their fairness and reliability, compromising output trustworthiness. Current mitigation m
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide
arXiv:2609.14211v1 Announce Type: cross Abstract: Scientific applications increasingly rely on high-performance computing (HPC), yet translating a scientist's high-level goal into a correct target-sca
arXiv:2609.15045v1 Announce Type: cross Abstract: Prompt echoing is a recognized failure mode of instruct language models, in which a model instead of generating a response, mirrors the provided promp
arXiv:2609.14115v1 Announce Type: cross Abstract: Safety-critical control of autonomous systems requires formal safety certificates, such as controlled invariant sets, that must be computed online as
Salesforce Inc. is stretching its data and artificial intelligence tentacles further into the public cloud, announcing expanded strategic integrations with both Amazon Web Services Inc. and Google Clo
Matthew Yglesias / Slow Boring: OpenAI employees need to oppose its support for Leading the Future, which seeks to chill federal regulation, and Congress should hold hearings on AI risks — When I saw
Automated lint: 12 errors, 54839 warnings, 3 info
Excited to be part of the Dreamforce keynote next week with @bcherny! Who will be there? 👋 Master the next era of enterprise tech Unlock strategies on AI governance, scalable machine learning, digital
“right now, AI companies are underinvesting in safety” might prove to be the understatement of the century. I left Anthropic's safety team two weeks ago. Now feels like a good moment to explain why. A
arXiv:2602.05354v3 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed in moderation and policy enforcement, where correct decisions often depend on evidence that is not i
arXiv:2609.07194v1 Announce Type: new Abstract: We present EmoMed - a multimodal medical consultation agent that adapts its responses based on users' emotional states while maintaining clinical accura
Agent skills fit well alongside documentation and remote MCP servers as ways of enabling the success of your AI workflows. They reduce context window usage for certain use cases, and they're straightf
arXiv:2609.08789v1 Announce Type: cross Abstract: Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California
arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-
arXiv:2609.06851v1 Announce Type: cross Abstract: Broad misalignment has been produced by finetuning on narrow data, harmful or benign, and in context only by demonstrations of the undesirable behavio
Automated lint: 12 errors, 53990 warnings, 3 info
arXiv:2508.00935v3 Announce Type: replace-cross Abstract: Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if m
arXiv:2609.02168v1 Announce Type: new Abstract: Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through th
arXiv:2609.02754v1 Announce Type: cross Abstract: Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and mis
By redesigning planning, validation, and risk review around AI agents, Coinbase Wallet dramatically shortened the path from product idea to working software. The post How Coinbase Wallet built an agen
arXiv:2609.00015v1 Announce Type: new Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, controll
arXiv:2608.29378v1 Announce Type: cross Abstract: Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade
During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as 'reverse engineering' We were in contact with the Anthropic team the
arXiv:2608.29228v1 Announce Type: new Abstract: Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution
arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in a
arXiv:2608.27102v1 Announce Type: new Abstract: Large Language Models (LLMs) operate in hospitals, courtrooms, banks, and public service desks, where fluent, confident outputs are treated as authorita
Need a low-cost, high-performance way to run long-lived, stateful workloads such as AI agents? Today, we introduced Cloud Run instances, which let you do just that. Consider AI agents such as OpenClaw
Sharing my harness for running local LLMs that I built using Qwen 3.x 27B (> 90% locally built) under my supervision - not vibe-coded. Its free, no telemetry, and open-source (AGPL). Works on Windows,
Despite rapid advances in artificial intelligence, the enterprise world is still dealing with a data pipeline problem. More than 80% of enterprise data is unstructured, and 99% of this data is dark to
arXiv:2608.24087v1 Announce Type: cross Abstract: Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and
arXiv:2608.23941v1 Announce Type: new Abstract: Pre-execution oversight is core to trusted monitoring in AI control: a fallible LLM monitor vets planned actions before irreversible execution. Over-blo
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyon
arXiv:2608.20378v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation
arXiv:2608.19216v1 Announce Type: new Abstract: AI control research asks how to deploy models safely even when they may be misaligned, but many control protocols assume that the deployer can instrumen
arXiv:2608.19902v1 Announce Type: new Abstract: AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limite
arXiv:2512.14012v2 Announce Type: replace-cross Abstract: The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate m
Agents changed what failure looks like, and the evaluation layer has to change with them. Why agent-as-a-judge is moving from research paper to production eval stack. The post Where agent evals are go
arXiv:2608.14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing me
arXiv:2608.12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt t
arXiv:2608.10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server
arXiv:2608.10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do
arXiv:2608.11146v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. How
arXiv:2608.10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream dec
arXiv:2608.09900v1 Announce Type: new Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably wa