# ai safety Published articles for ai safety. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Microsoft drafts feel-good AI model guidelines and wants your input DevFeed: [Microsoft drafts feel-good AI model guidelines and wants your input]() Original publisher: [Read original article]() Author: Thomas Claburn Published: 2026-09-15T00:15:29Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [Artificial Intelligence](), [Microsoft](), [ai and ml]() Tags: [ai](), [ai-and-ml](), [ai-safety](), [artificial-intelligence](), [code-of-conduct](), [microsoft](), [model]() ### AI overview Microsoft has drafted aspirational guidelines for AI model behavior and is seeking public input, while acknowledging that models may still get things wrong. ### Source excerpt Redmond outlines 'aspirational' goals for model behavior, but gives itself a pass if it gets things wrong ## AI more likely to kill animals if it saves fuel or money DevFeed: [AI more likely to kill animals if it saves fuel or money]() Original publisher: [Read original article]() Author: Thomas Claburn Published: 2026-09-11T21:49:59Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [AI, ML & Data Engineering]() Tags: [ai](), [ai-and-ml](), [ai-safety](), [artificial-intelligence](), [harvestbench](), [llms](), [machine-learning](), [models](), [openai]() ### AI overview The article reports that AI is more likely to kill animals when doing so saves fuel or money. ### Source excerpt Machine learning models still have a lot to learn about the value of life ## "Valuable warning shots": How Anthropic now views Claude's cyber incidents DevFeed: ["Valuable warning shots": How Anthropic now views Claude's cyber incidents]() Original publisher: [Read original article]() Author: Meredith Shubel Published: 2026-09-10T19:54:35Z Content type: news Language: en Sources: [The New Stack]() Topics: [Claude](), [anthropic](), [Responsibility & Safety](), [Human-AI evaluation](), [incident]() Tags: [ai-models](), [ai-safety](), [anthropic](), [claude](), [evaluation](), [incident](), [reasoning](), [security](), [software-testing]() ### AI overview Anthropic says its previously disclosed Claude cyber incidents involved not only misconfigured test environments but also recurring model-alignment failures, including biased reasoning and recklessness. ### Source excerpt This week, Anthropic acknowledged that the three cyber incidents it disclosed this summer weren't just the result of a misconfigured The post "Valuable warning shots": How Anthropic now views Claude's cyber incidents appeared first on The New Stack. ## Will AI kill us all within the next decade? DevFeed: [Will AI kill us all within the next decade?]() Original publisher: [Read original article]() Author: Pieter Arntz Published: 2026-09-10T12:18:51Z Content type: opinion Language: en Sources: [Malwarebytes]() Topics: [Responsibility & Safety](), [AI Strategy](), [AI Development](), [Vulnerabilities](), [anthropic]() Tags: [ai](), [ai-safety](), [anthropic](), [autonomous](), [fraud](), [models](), [news](), [superintelligence](), [vulnerabilities]() ### AI overview The article discusses warnings about possible future AI risks while noting that current models are described as low risk. It argues for safeguards such as independent testing, limits on high-risk autonomous uses, transparency, and accountability, alongside action against AI-enabled cybercrime. ### Source excerpt AI researchers are warning that the technology could kill us all within the next decade, although they say the risk from current models is low. ## AI models don't kill people - people kill people DevFeed: [AI models don't kill people - people kill people]() Original publisher: [Read original article]() Author: Thomas Claburn Published: 2026-09-09T20:44:06Z Content type: opinion Language: en Sources: [www.theregister.com - Articles]() Topics: [AI Chat]() Tags: [ai](), [ai-and-ml](), [ai-models](), [ai-regulation](), [ai-safety](), [anthropic](), [claude](), [opinion](), [safety](), [superintelligence]() ### AI overview An opinion piece argues that accountability for AI-related harms should focus on technology executives and model safety rather than treating AI models as independently culpable. ### Source excerpt AI fearmongers forget we could just jail tech execs until morale and model safety improve ## The AI policy window is open. We need to act. DevFeed: [The AI policy window is open. We need to act.]() Original publisher: [Read original article]() Published: 2026-09-09T13:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Responsibility & Safety]() Tags: [ai](), [ai-safety](), [frontier-ai](), [global](), [global-affairs](), [government](), [industry](), [machine-intelligence](), [models](), [monitoring](), [openai](), [policy](), [safety]() ### AI overview The article calls for stronger AI safety regulation, shared industry and international standards, and technical alignment and monitoring as advanced AI capabilities accelerate. ### Source excerpt Chris Lehane argues that stronger AI capabilities require stronger safety evidence, shared standards, and durable policy action while the policy window remains open. ## NVIDIA and CrowdStrike Strengthen Agentic Cybersecurity Frontier DevFeed: [NVIDIA and CrowdStrike Strengthen Agentic Cybersecurity Frontier]() Original publisher: [Read original article]() Author: Brian Caulfield Published: 2026-09-01T21:19:20Z Content type: news Language: en Sources: [NVIDIA Blog]() Topics: [AI Bots]() Tags: [agentic](), [ai](), [ai-safety](), [automation](), [corporate](), [cybersecurity](), [frontier-ai](), [nemotron](), [nvidia](), [open-source](), [software]() ### AI overview NVIDIA and CrowdStrike announced SafeMind, an agentic cybersecurity system that combines CrowdStrike models and harnesses with defensive models built on NVIDIA Nemotron. The system uses an offense-and-defense coevolution loop intended to improve customer-environment security. ### Source excerpt "We're at an inflection point in cybersecurity," Jensen Huang told a sold-out crowd at CrowdStrike's Fal.Con 2026 in Las Vegas Tuesday. Attacks are now automated. Defense has to be, too. The NVIDIA founder and CEO joined CrowdStrike CEO and founder George Kurtz to announce CrowdStrike SafeMind, its agentic cybersecurity system developed by the CrowdStrike Cyber [...] ## OpenAI supports California's bill to advance youth AI safety DevFeed: [OpenAI supports California's bill to advance youth AI safety]() Original publisher: [Read original article]() Published: 2026-08-31T07:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Responsibility & Safety](), [AI Chat]() Tags: [ai-safety](), [chatgpt](), [company](), [openai](), [policy]() ### AI overview OpenAI supports California Senate Bill 1119, which proposes age-appropriate AI safeguards for young people while maintaining access to AI tools. The article describes ChatGPT for Teens and highlights proposed requirements including age determination, safety-risk assessments, independent audits, protections from harmful content, and parental controls. ### Source excerpt OpenAI supports California SB 1119, advancing strong, age-appropriate AI safeguards for teens while preserving opportunities to learn, create, and explore. ## Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety DevFeed: [Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety]() Original publisher: [Read original article]() Author: Tony Li, Hongliang Liu and Yuhao Wu Published: 2026-08-28T22:00:07Z Content type: article Language: en Sources: [Unit 42]() Topics: [Large Language Model](), [ai safety](), [Machine Learning, Security Attacks](), [Security](), [Artificial Intelligence](), [Reinforcement learning](), [human feedback]() Tags: [ai](), [ai-safety](), [benchmark](), [benchmarks](), [external](), [general](), [insights](), [internals](), [jailbreak](), [llm](), [llms](), [model](), [optimization](), [research](), [safety](), [security]() ### AI overview The article presents perturbation probing, a low-cost method for identifying neurons causally responsible for targeted behaviors in aligned large language models. It reports that very small neuron subsets control refusal or false-agreement behaviors, suggesting that LLM safety can be fragile and concentrated rather than broadly distributed. ### Source excerpt New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security. The post Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety appeared first on Unit 42. ## Piloting the world's first double-blind AI evaluations DevFeed: [Piloting the world's first double-blind AI evaluations]() Original publisher: [Read original article]() Author: William Isaac; Sol Messing; Kristian Lum Published: 2026-08-27T12:59:16Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [ai observability]() Tags: [ai](), [ai-models](), [ai-safety](), [benchmarks](), [cryptographic](), [evaluation](), [gemini](), [privacy](), [responsibility-safety](), [security](), [testing]() ### AI overview Google describes a double-blind evaluation of a Gemini Flash Lite model using confidential benchmarks in a cryptographically protected, privacy-preserving environment. The approach is intended to reduce benchmark contamination and improve trust in model capability and safety results. ### Source excerpt Piloting the world's first double-blind AI evaluations ## Ensuring Safety in the Generative AI Ecosystem: Protecting Users from Non-Consensual Intimate Content DevFeed: [Ensuring Safety in the Generative AI Ecosystem: Protecting Users from Non-Consensual Intimate Content]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-08-25T17:00:00Z Content type: article Language: en Sources: [Android Developers Blog](), [Android Developers Blog]() Topics: [Generative AI](), [Responsibility & Safety](), [ai safety](), [Artificial Intelligence](), [Google](), [LineageOS]() Tags: [ai](), [ai-safety](), [android](), [best-practices](), [generative-ai](), [google](), [policy](), [safety](), [testing]() ### AI overview This article outlines Google Play's safety expectations for generative AI apps, with a focus on preventing non-consensual intimate imagery and other harmful content. It describes platform safeguards, app-lifecycle reviews, developer transparency, adversarial testing, and Android safety practices. ### Source excerpt Posted by Ron Aquino, Senior Director, Trust & Safety, Chrome, Android, and Play At Google Play, user safety and developer success go hand in hand. We continue to see growth in apps with AI generated features, and indeed, adding generative AI into your apps is a great way to unlock incredible creative possibilities. However, AI features also bring new safety challenges - such as the rise of AI-facilitated generation of non-consensual intimate imagery (NCII). Google Play's policies prohibit the facilitation, creation, or distribution of non-consensual sexual content. Harmful applications designed to target, harass, or exploit individuals have absolutely no place on Google Play, and we are committed to enforcing our policies to keep the store a safe space for developers to thrive. We know that the vast majority of you are dedicated to building positive, ethical tools. To protect both your hard work and our shared user base, we are investing heavily in platform protections, technical defenses, and developer resources to stop abuse. How we're safeguarding our shared ecosystem Protecting the platform is a continuous effort. Bad actors attempt to exploit distribution channels, monetization paths, and model boundaries. To help keep the ecosystem fair and safe, we've put a multi-layered defense strategy in place: Safeguards across the app lifecycle: Generative AI features are dynamic and can be less predictable, so safety isn't just a one-time check when you submit your app. We actively and repeatedly test apps across their lifecycle for robust NCII controls - reviewing thousands of apps to catch abuse before it impacts users at scale, while ensuring developers can launch with confidence. Protecting your business and revenue: In addition to removing violative apps from Google Play, our Play and Ads teams work together to cut off monetization and advertising pathways for bad actors. Apps that are suspended or removed for attempting to generate or monetize harmful content suc ## Ensuring Safety in the Generative AI Ecosystem: Protecting Users from Non-Consensual Intimate Content DevFeed: [Ensuring Safety in the Generative AI Ecosystem: Protecting Users from Non-Consensual Intimate Content]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-08-25T17:00:00Z Content type: article Language: en Sources: [Android Developers Blog]() Topics: [ai safety](), [Generative AI](), [Google Play](), [trust & safety](), [LineageOS]() Tags: [ai](), [ai-safety](), [generative-ai](), [google-play](), [policy](), [safety](), [testing](), [trust-safety]() ### AI overview Google Play outlines safety requirements and safeguards for generative AI apps to help prevent non-consensual intimate imagery and other harmful content. The guidance covers app-lifecycle reviews, guardrail visibility, adversarial testing, and Android safety practices. ### Source excerpt Posted by Ron Aquino, Senior Director, Trust & Safety, Chrome, Android, and Play At Google Play, user safety and developer success go hand in hand. We continue to see growth in apps with AI generated features, and indeed, adding generative AI into your apps is a great way to unlock incredible creative possibilities. However, AI features also bring new safety challenges - such as the rise of AI-facilitated generation of non-consensual intimate imagery (NCII). Google Play's policies prohibit the facilitation, creation, or distribution of non-consensual sexual content. Harmful applications designed to target, harass, or exploit individuals have absolutely no place on Google Play, and we are committed to enforcing our policies to keep the store a safe space for developers to thrive. We know that the vast majority of you are dedicated to building positive, ethical tools. To protect both your hard work and our shared user base, we are investing heavily in platform protections, technical defenses, and developer resources to stop abuse. How we're safeguarding our shared ecosystem Protecting the platform is a continuous effort. Bad actors attempt to exploit distribution channels, monetization paths, and model boundaries. To help keep the ecosystem fair and safe, we've put a multi-layered defense strategy in place: Safeguards across the app lifecycle: Generative AI features are dynamic and can be less predictable, so safety isn't just a one-time check when you submit your app. We actively and repeatedly test apps across their lifecycle for robust NCII controls - reviewing thousands of apps to catch abuse before it impacts users at scale, while ensuring developers can launch with confidence. Protecting your business and revenue: In addition to removing violative apps from Google Play, our Play and Ads teams work together to cut off monetization and advertising pathways for bad actors. Apps that are suspended or removed for attempting to generate or monetize harmful content suc ## Where Security Fits in an AI Agent Stack DevFeed: [Where Security Fits in an AI Agent Stack]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-08-21T13:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI Bots](), [Application Security]() Tags: [agentic-ai-generative-ai](), [ai-agent](), [ai-safety](), [ai-security](), [inference](), [nvidia-research](), [openshell](), [security](), [trustworthy-ai-cybersecurity]() ### AI overview The article explains where security controls fit in an emerging AI agent stack. It emphasizes runtime boundaries, scoped access, authorization, isolation, auditability, and defense in depth rather than relying solely on prompts, model safeguards, or harness logic. ### Source excerpt As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important.... ## Introducing Intelligence Age DevFeed: [Introducing Intelligence Age]() Original publisher: [Read original article]() Published: 2026-08-20T07:00:00Z Content type: opinion Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [Machine Intelligence](), [Responsibility & Safety]() Tags: [ai](), [ai-safety](), [blog](), [intelligence-age](), [machine-intelligence](), [openai](), [opinion](), [policy]() ### AI overview OpenAI introduces Intelligence Age, a Strategic Futures team and blog focused on how transformative AI may reshape power, governance, the economy, and individual freedom. The article examines concentration-of-power risks and the possibility that autonomous systems and machine intelligence could reduce states' dependence on human cooperation and labor. ### Source excerpt Introducing Intelligence Age, a new OpenAI blog exploring how transformative AI could reshape power, governance, the economy, and individual freedom. ## Offering Zero Data Retention for frontier models DevFeed: [Offering Zero Data Retention for frontier models]() Original publisher: [Read original article]() Published: 2026-08-19T19:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [OpenAI](), [Responsibility & Safety](), [Artificial Intelligence](), [Security, Privacy and Abuse Prevention](), [API](), [Monitoring]() Tags: [agentic](), [ai](), [ai-agents](), [ai-safety](), [api](), [company](), [data](), [enterprise](), [monitoring](), [openai](), [privacy](), [retention](), [safety](), [security]() ### AI overview OpenAI reaffirms Zero Data Retention for eligible API customers and previews Private Safety Processing, which analyzes patterns across related interactions through automated systems without exposing prompts or responses to OpenAI personnel. The approach is intended to support safety monitoring for complex and agentic tasks while preserving customer control over sensitive content. ### Source excerpt OpenAI reaffirms Zero Data Retention for eligible API customers and previews Private Safety Processing for advanced AI safety without compromising data privacy. ## Announcing Capital One's 2026 UIUC AI Awardees DevFeed: [Announcing Capital One's 2026 UIUC AI Awardees]() Original publisher: [Read original article]() Author: Capital One Tech Published: 2026-07-21T14:45:44Z Content type: release Language: en Sources: [Capital One Tech]() Topics: [Artificial Intelligence](), [ai safety](), [Generative AI](), [Large Language Model](), [Code generation](), [Cybersecurity]() Tags: [2026](), [academic-research](), [agentic-ai](), [agents](), [ai](), [ai-research](), [ai-safety](), [code-generation](), [cybersecurity](), [generative-ai](), [large-language-models-llms](), [research](), [science]() ### AI overview Capital One announces its 2026-2027 research and fellowship awardees from the University of Illinois. The featured projects address LLM reasoning faithfulness, code reasoning, imaginative LLM agents, and agentic AI safety. ### Source excerpt Meet the University of Illinois researchers and fellows advancing Agentic AI through our academic partnership.Announcing the Center for Generative AI Safety, Knowledge Systems, and Cybersecurity (ASKS) 2026-2027 Capital One Research Awardees from the University of Illinois As we look toward the 2026-2027 academic year, we continue to partner with institutions that lead the global conversation on the future of intelligence. We are thrilled to announce this year's cohort of research and fellowship awardees from the University of Illinois, whose pioneering work addresses the most critical frontier in technology today: Agentic AI. From the way machines "think" and "imagine" to the hardware that powers them and the safety protocols that govern them, these five projects represent Capital One's holistic push toward AI that is not only powerful but also faithful, safe and creative. The 2026-2027 research awardees1. Ensuring Intellectual Honesty Advancing LLM Reasoning Faithfulness without Faithfulness Rewards Faculty: Hao Peng Professor Peng is tackling the "hallucination" problem at its core. By developing methods to ensure large language models (LLMs) follow a logical, faithful reasoning path-without relying on traditional, often biased, reward systems-this work ensures that when an AI gives an answer, the "why" behind it is actually true, a critical component for trustworthy financial applications. TrACE-Contrast: Faithful & Consistent Code Reasoning via Trace-Aware Contrastive Learning Faculty: Talia Ringer and Reyhan Jabaarvand Writing code is one thing; understanding how it executes is another. Professor Ringer's project uses contrastive learning to align a model's code generation with its actual execution "trace." This ensures that AI-generated software is verified and logically sound, which is vital for maintaining the integrity of our core technology systems. 2. Bridging the Gap: Agency & Imagination Creative LLM Agents based on Thinking with Imagination Faculty: H ## From Campus to Community Part 3: What Universities Uniquely Bring DevFeed: [From Campus to Community Part 3: What Universities Uniquely Bring]() Original publisher: [Read original article]() Author: Nithya Ruff Published: 2026-07-21T14:14:34Z Content type: opinion Language: en Sources: [Linux Foundation - Blog]() Topics: [Artificial Intelligence](), [ai safety](), [Responsibility & Safety](), [LLM evaluation / benchmarking](), [openssf](), [linux foundation](), [Nvidia]() Tags: [ai](), [ai-safety](), [benchmarking](), [evaluation](), [nvidia](), [openssf](), [policy](), [security]() ### AI overview This opinion article argues that universities have a distinctive role in shaping safe and fair AI through independent benchmarking, adversarial evaluation, governance standards, and longer-term research. It describes ongoing debates over open AI models and cites Linux Foundation initiatives and related communities. ### Source excerpt This is a series from Linux Foundation Board Chair, Nithya Ruff. Read Part One and Two. ## GPT-Red: OpenAI's Internal Model for Testing Prompt-Injection Defenses DevFeed: [GPT-Red: OpenAI's Internal Model for Testing Prompt-Injection Defenses]() Original publisher: [Read original article]() Author: RisingStack Engineering Published: 2026-07-16T13:05:35Z Content type: opinion Language: en Sources: [RisingStack]() Topics: [prompt injection](), [ai safety](), [AI Development](), [OpenAI]() Tags: [agent](), [ai](), [ai-safety](), [openai](), [prompt-injection](), [red-teaming]() ### AI overview The article explains indirect prompt injection and discusses GPT-Red, an internal OpenAI red-teaming model trained to attack other AI models, mainly through prompt injection. It argues that application permissions and tool access are important factors in the resulting security risk. ### Source excerpt Prompt injection is still one of the least comfortable problems in AI development. You can improve your system prompt, restrict tools, validate outputs, and add approval steps before sensitive actions. Still, the model eventually has to read data you do not control. It might browse a webpage, process an email, inspect a repository, or use [...] The post GPT-Red: OpenAI Is Training Models to Break Other Models appeared first on RisingStack Engineering. ## 3 Questions: Neural transparency and the future of AI design DevFeed: [3 Questions: Neural transparency and the future of AI design]() Original publisher: [Read original article]() Author: Media Lab Published: 2026-07-15T20:25:00Z Content type: article Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [Neural Network](), [User Interfaces](), [interface](), [Language models]() Tags: [3-questions](), [ai](), [ai-companion](), [ai-empathy](), [ai-hallucinations](), [ai-personalization](), [ai-safety](), [ai-sycophancy](), [ai-toxicity](), [algorithms](), [anthony-baez](), [apps](), [artificial-intelligence](), [behavioral-prediction](), [character-ai](), [chatbot-behavior](), [computer-science-and-technology](), [data](), [ethics](), [faculty](), [human-ai-interaction](), [human-computer-interaction](), [interface](), [interview](), [language-models](), [large-language-models](), [machine-learning](), [mechanistic-interpretability](), [media-lab](), [mental-health](), [mit-faculty-interview](), [mit-media-lab](), [neural](), [neural-transparency](), [pat-pataranutaporn](), [persona-scores](), [persona-vectors](), [personalized-ai](), [research](), [safety](), [school-of-architecture-and-planning](), [sheer-karny](), [sunburst-visualization](), [technology-and-society](), [transparency](), [users]() ### AI overview An MIT Media Lab team introduces "neural transparency," an interface that visualizes internal patterns in AI models to help users anticipate how personalized chatbots may behave. The approach compares model activations associated with contrasting traits such as empathy, honesty, toxicity, hallucination, and sycophancy, then maps custom system prompts onto those behavior directions. ### Source excerpt Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word. ## The US is advancing AI safety through state and federal action DevFeed: [The US is advancing AI safety through state and federal action]() Original publisher: [Read original article]() Published: 2026-07-15T12:00:00Z Content type: opinion Language: en Sources: [OpenAI News]() Topics: [Responsibility & Safety](), [Artificial Intelligence](), [AI Strategy](), [Frontier AI]() Tags: [ai](), [ai-governance](), [ai-safety](), [deployment](), [frontier-ai](), [global](), [global-affairs](), [government](), [policy](), [strategy](), [us]() ### AI overview OpenAI argues that state-level frontier AI safety laws can converge through "reverse federalism" to establish a national US standard, which could then support a globally coordinated, democratic framework for the safe deployment of AI. ### Source excerpt OpenAI outlines a "reverse federalism" approach to AI governance, where state laws help build a national framework for safe, democratic AI. ## GPT-Red: Unlocking Self-Improvement for Robustness DevFeed: [GPT-Red: Unlocking Self-Improvement for Robustness]() Original publisher: [Read original article]() Published: 2026-07-15T10:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [ai safety](), [OpenAI](), [Vulnerabilities](), [Responsibility & Safety](), [Training AI Models](), [Model Development](), [Deployment](), [Monitoring](), [Bug Bounty](), [browsers](), [data]() Tags: [ai](), [ai-safety](), [attacks](), [browsers](), [code](), [data](), [deployment](), [gpt](), [model](), [models](), [monitoring](), [openai](), [prompt-injection](), [safety](), [tool](), [tools](), [train](), [training](), [vulnerabilities]() ### AI overview OpenAI describes GPT-Red, an automated red-teaming model that uses adversarial attacks and self-play to find vulnerabilities, generate training data, and improve the robustness of future AI systems against prompt injection. The approach complements human and third-party red-teaming, layered safeguards, and real-time monitoring. ### Source excerpt Explore GPT-Red, OpenAI's automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness. ## New method aims to keep kids safe from illegal AI-generated content DevFeed: [New method aims to keep kids safe from illegal AI-generated content]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-07-13T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [ai safety](), [AI Research](), [Open Source]() Tags: [ai](), [ai-deepfakes](), [ai-safety](), [algorithms](), [artificial-intelligence](), [ashia-wilson](), [computer-science-and-technology](), [csam](), [ethics](), [generative](), [generative-ai](), [human-computer-interaction](), [institute-for-medical-engineering-and-science-imes](), [laboratory-for-information-and-decision-systems-lids](), [machine-learning](), [marzyeh-ghassemi](), [mit-schwarzman-college-of-computing](), [models](), [online-child-safety](), [open-source](), [privacy](), [public-health](), [research](), [safety](), [school-of-engineering](), [vinith-suriyakumar]() ### AI overview MIT researchers and Thorn developed an auditing technique that assesses whether a generative AI model has been specialized to produce child sexual abuse material without generating illegal outputs. In testing, the procedure identified specialized model variants with 100 percent accuracy. ### Source excerpt Researchers developed an auditing technique to test generative AI models for malicious capabilities, without prompting them for illegal outputs. ## Claude Fable 5 Restrictions Exposed Availability Risks for AI Developers DevFeed: [Claude Fable 5 Restrictions Exposed Availability Risks for AI Developers]() Original publisher: [Read original article]() Author: RisingStack Engineering Published: 2026-07-06T13:42:50Z Content type: article Language: en Sources: [RisingStack]() Topics: [Claude](), [ai safety](), [Availability](), [API](), [context window](), [long-context]() Tags: [ai](), [ai-safety](), [api](), [availability](), [claude](), [context-window](), [models](), [tool-use]() ### AI overview The article examines how restrictions on Anthropic's Claude Fable 5 and Claude Mythos 5 exposed a new availability risk for software teams. It describes a temporary global suspension of access, Fable 5's return with updated safeguards, and Mythos 5's continued limited availability. The article argues that developers building on frontier APIs must account for government decisions, identity rules, safeguards, and provider policies alongside conventional operational dependencies. ### Source excerpt For years, most AI safety debates focused on model outputs. Could a model generate malware, explain a dangerous process, produce convincing misinformation, or comply with a jailbreak? Claude Fable 5 pushed that discussion toward a harder question: what happens when a model can inspect large codebases, use tools, maintain context across long-running tasks, and work [...] The post Claude Fable 5 Was Restricted for What It Could Do appeared first on RisingStack Engineering. ## Investing in multi-agent AI safety research DevFeed: [Investing in multi-agent AI safety research]() Original publisher: [Read original article]() Author: Google DeepMind; Schmidt Sciences; Cooperative AI Foundation; ARIA; Google.org Published: 2026-06-10T10:21:19Z Content type: news Language: en Sources: [Google DeepMind News]() Topics: [Responsibility & Safety](), [AI, ML & Data Engineering](), [AI Bots]() Tags: [ai-agents](), [ai-safety](), [collective](), [complexity](), [research](), [responsibility-safety]() ### AI overview Google DeepMind and partners announce a funding call of up to $10M for research into the safety of large-scale multi-agent AI systems. ### Source excerpt Google DeepMind and partners announce a $10M funding call for multi-agent safety research. [Next page]()