Search: “safety”

arXiv:2607.21988v1 Announce Type: new Abstract: Self-harm content is particularly challenging to detect using NLP techniques, and is also a high-stakes task which requires the highest accuracy to enab

arXiv:2607.22165v1 Announce Type: cross Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation a

New York Times: Microsoft introduces MAI-Cyber-1-Flash, an AI model trained for cybersecurity, and launches Perception, an agentic security system to patch vulnerabilities — As some executives fret ov

The National Oceanic and Atmospheric Administration (NOAA) is embarking on a transformative journey to redefine how we understand and predict patterns in the Earth’s atmosphere that affect the weather

arXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor

arXiv:2512.15423v2 Announce Type: replace Abstract: Monocular depth foundation models achieve remarkable generalization by learning large-scale semantic priors, but this creates a critical vulnerabili

arXiv:2607.21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often eva

This is our biggest comparison yet. We've taken 23 Gemma 4 E4B models from huggingface and ran them through the abliterlitics gauntlet. We also have a new abliterlitics discord, feel free to jump on a

A group of tech firms has released an open letter that calls on policymakers not to ban open-source artificial intelligence models. The development follows a report that some Trump administration offi

Very happy to support this on behalf of Google. We have long benefited from open source, are big contributors to open source and in fact have consistently made open weights models with Gemma available

arXiv:2607.20488v1 Announce Type: new Abstract: Multi-agent LLM frameworks typically fix their team topology at boot time. When an individual agent becomes overloaded at runtime, for example by mixing

arXiv:2505.18672v2 Announce Type: replace Abstract: Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to e

arXiv:2607.20547v1 Announce Type: new Abstract: Safe Advanced Air Mobility operations require aircraft to maintain separation when surveillance information is noisy, delayed, incomplete, or temporaril

arXiv:2607.20581v1 Announce Type: cross Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat

arXiv:2607.20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavi

arXiv:2604.01925v2 Announce Type: replace-cross Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit bias

arXiv:2607.20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with au

Open models matter. Ollama works hard with the model creators, hardware partners, and most importantly developers building software leveraging various open models for their own use cases. For my first

Open weights = freedom. You can run them on your own hardware. No vendor can pull the plug. No API can deprecate you. No company logs your private data. That's sovereignty. Closed models hand one comp

arXiv:2607.20791v1 Announce Type: new Abstract: High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs. Recent advances in truncation-based sampling techniques hav

arXiv:2607.21518v1 Announce Type: new Abstract: Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction.

arXiv:2607.15557v4 Announce Type: replace Abstract: Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Pub

arXiv:2607.20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poor

arXiv:2607.09328v2 Announce Type: replace-cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across dis

arXiv:2607.19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel thr

arXiv:2607.19484v1 Announce Type: new Abstract: Real-world collision avoidance is a core motivation for studying the dynamics and control of high sideslip drifting in vehicles, yet the practical benef

arXiv:2607.19409v1 Announce Type: new Abstract: Recent advances in large language models have accelerated deployment of agentic systems in operational finance. Existing benchmarks emphasize measuring

arXiv:2607.19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unre

Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to

arXiv:2607.20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be reg

arXiv:2607.19971v1 Announce Type: new Abstract: Accurate motion prediction of surrounding agents and safe motion planning are two closely coupled key tasks for social robot navigation in crowded envir

One thing I noticed in American politics, whenever the government wants to push unpopular actions or laws, they often introduce fear to convince the public to support them. This is actually how i view

OpenAI’s zero-day exploit hack of HuggingFace *should* be a wake up call. Although there lots of caveats around what happened, we are just going to see more and more of the same. We have no guarantees

Hey everyone, I’m a Full-Stack Developer with 6+ years of experience. I’m relatively new to AI-assisted development workflows and want to build a production-ready, enterprise-level Next.js web applica

Let me try to explain this clearly, simply, and neatly. Originally, I just wanted to build a small WebUI adapter with an admin panel, but things escalated over the last few months. At first, I faced t

Last Week in AI #250 is the podcast’s 250th episode, summarizing recent frontier‑AI policy developments. It reports that the U.S. government has granted Anthropic permission to release Mythos‑5 to a l

LWiAI Podcast #248 (June 12, 2026) reviews major AI developments, noting Anthropic’s release of Claude Fable 5, a safeguarded variant of Mythos 5, which shows benchmark improvements but raises concern

LWiAI Podcast #252 (July 11, 2026) reviewed major AI releases: OpenAI unveiled GPT‑5.6 and relaunched its agentic coding product as ChatGPT Work, amid disputes over U.S. governmental oversight and jai

Automated lint: 20 errors, 8743 warnings, 3 info

arXiv:2607.13940v1 Announce Type: new Abstract: Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an ope

arXiv:2607.13716v1 Announce Type: new Abstract: Agentic AI systems increasingly act through heterogeneous runtimes: local coding hooks, SDK tools, browser automation, managed-agent traces, API gateway

arXiv:2607.13330v1 Announce Type: cross Abstract: Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their pract

arXiv:2607.13056v1 Announce Type: cross Abstract: Current vision-language-action (VLA) benchmarks primarily evaluate isolated manipulation skills while leaving human-robot interaction structure largel

arXiv:2607.09142v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clini

arXiv:2601.02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctua

arXiv:2607.13704v1 Announce Type: new Abstract: The dominance of traditional rule-based methods in autonomous driving has gradually been replaced by learning-based approaches. While learning-based pla