# Trustworthy AI An artificial intelligence discipline focused on incorporating trustworthiness considerations throughout AI system design, development, deployment, use, and evaluation. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Using deterministic systems and provenance to make AI-generated financial analysis verifiable DevFeed: [Using deterministic systems and provenance to make AI-generated financial analysis verifiable]() Original publisher: [Read original article]() Published: 2026-08-25T00:00:00Z Content type: article Language: en Sources: [Chainguard: Unchained]() Topics: [Trustworthy AI](), [Artificial Intelligence](), [AI Platform](), [Large Language Model](), [Code](), [Finance]() Tags: [ai](), [ai-platform](), [financial](), [models](), [provenance](), [trustworthy-ai](), [verification]() ### AI overview Kepler describes a model-agnostic approach to trustworthy AI that combines language models with deterministic tools for retrieval, computation, provenance, and traceability. The article focuses on making financial analysis outputs verifiable by linking numbers to their sources, formulas, or computations. ### Source excerpt Trustworthy AI takes more than a powerful model. See how Kepler uses deterministic systems and provenance to make financial analysis verifiable. ## Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS DevFeed: [Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS]() Original publisher: [Read original article]() Author: Nuno Loureiro; Luis Grangeia Published: 2026-08-10T00:00:00Z Content type: article Language: en Sources: [Blog RSS Feed | Snyk]() Topics: [Security](), [Vulnerabilities](), [Authorization](), [Software as a service](), [Microservice](), [Microservices](), [Front end](), [API](), [App](), [Artificial Intelligence](), [Trustworthy AI]() Tags: [agent](), [ai](), [api](), [application-security](), [applications](), [attacks](), [autonomous](), [awareness](), [blog](), [customer](), [customer-featured](), [cybersecurity](), [devops](), [enterprise](), [frontend](), [interest](), [microservices](), [saas](), [security](), [vulnerabilities](), [vulnerability-insights](), [web]() ### AI overview Evo Continuous Offensive Security (COS) is presented as an autonomous offensive-security system combining AI pentesting, agent red teaming, and dynamic testing. The article reports a real assessment of a multi-tenant enterprise SaaS application that uncovered 33 confirmed vulnerabilities, including tenant-wide compromise and critical authorization flaws. ### Source excerpt A real Evo Continuous Offensive Security assessment uncovered 33 confirmed vulnerabilities in a multi-tenant enterprise SaaS, including tenant-wide compromise and critical authorization flaws. ## LLM reasoning and agentic safety at ICML 2026 DevFeed: [LLM reasoning and agentic safety at ICML 2026]() Original publisher: [Read original article]() Author: Capital One Tech Published: 2026-07-02T14:14:40Z Content type: article Language: en Sources: [Capital One Tech]() Topics: [Large Language Model](), [Fine-tuning](), [Trustworthy AI](), [Artificial Intelligence]() Tags: [2026](), [ai](), [ai-research](), [fine-tuning](), [icml](), [icml-2026](), [llm](), [llm-reasoning](), [reasoning](), [research](), [safety](), [science](), [trustworthy-ai]() ### AI overview Capital One presents research for ICML 2026 on critique-guided distillation for robust LLM reasoning and on safety risks in multi-turn tool-using agents. The article says its Critique-Guided Distillation framework trains models to refine flawed responses using teacher critiques, and reports higher mathematical-reasoning benchmark performance than critique fine-tuning and standard distillation, including a 7% average improvement and gains of up to 15.0% on AMC23 and 12.2% on MATH-500. ### Source excerpt Explore our latest research in critique-guided distillation and multi-turn agent uncertainty in Seoul.Explore our latest research in critique-guided distillation and multi-turn agent uncertainty in Seoul. Capital One technologists are excited to participate in the 43rd International Conference on Machine Learning (ICML) taking place at the COEX Convention & Exhibition Center in Seoul, South Korea, July 6-11, 2026. As a premier global venue for machine learning research, ICML provides an essential forum for exploring foundational advancements, algorithmic innovations and cutting-edge deep learning systems. Capital One is excited to share advancements in large language model (LLM) scaling efficiencies, multi-turn tool-using agent safety and the development of robust, trustworthy AI frameworks. This work delivers the underlying engineering and algorithmic improvements crucial for deploying the next generation of safe financial technologies. Main conference research: Robust reasoning and agentic risk The following research, accepted to the ICML Main Conference, pushes the boundaries of how models self-correct, how trajectory-level risks can be proactively flagged, and how multi-turn agent interactions maintain reliable execution. This section features work led by Capital One researchers alongside deep collaborations with academic partners. Critique-Guided Distillation for Robust Reasoning via Refinement Capital One Authors: Berkcan Kapusuzoglu, Supriyo Chakraborty, Michael Lee, Sambit Sahu Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While critique-based approaches show promise, training models to generate critiques directly, such as Critique Fine-Tuning (CFT), can lead to output-format drift and degradation of general capabilities. We propose Critique-Guided Distillation (CGD), a training framework that decouples critique consumption from crit ## Supporting Europe's work in ensuring a trustworthy AI ecosystem DevFeed: [Supporting Europe's work in ensuring a trustworthy AI ecosystem]() Original publisher: [Read original article]() Published: 2026-06-11T00:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [Trustworthy AI](), [ai-governance](), [Code]() Tags: [ai](), [ai-content](), [ai-governance](), [ecosystem](), [eu](), [global-affairs](), [openai](), [trustworthy-ai]() ### AI overview OpenAI announces support for the EU Code of Practice on Transparency of AI-Generated Content, building on provenance standards, C2PA metadata, marking and detection methods, research, and a public verification tool. The article frames provenance as a way to provide context about content and strengthen a trustworthy AI ecosystem. ### Source excerpt OpenAI supports the EU Code of Practice on AI content transparency, advancing provenance standards and tools to help people understand AI-generated content. ## Teaching AI to see the world more like we do DevFeed: [Teaching AI to see the world more like we do]() Original publisher: [Read original article]() Author: Andrew Lampinen; Klaus Greff Published: 2025-11-11T11:49:13Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [Human-AI evaluation](), [Trustworthy AI](), [AI Models](), [AI Research]() Tags: [ai](), [ai-models](), [model](), [research](), [science](), [trustworthy-ai](), [vision]() ### AI overview A new Nature paper examines how AI vision models organize visual representations differently from humans. The researchers show that reorganizing these representations to better align with human knowledge can improve models' robustness, reliability, and ability to generalize. ### Source excerpt Our new paper analyzes the important ways AI systems organize the visual world differently from humans. ## From Ideas to Impact: How the Bay Area Is Shaping the Future of Secure AI DevFeed: [From Ideas to Impact: How the Bay Area Is Shaping the Future of Secure AI]() Original publisher: [Read original article]() Author: Manoj Nair Published: 2025-08-06T04:00:00Z Content type: article Language: en Sources: [Blog RSS Feed | Snyk]() Topics: [Artificial Intelligence](), [Trustworthy AI](), [ai security](), [Securing AI](), [Generative AI](), [MCP Server](), [Responsibility & Safety](), [cursor](), [CI/CD](), [sdlc](), [Development](), [AWS Transform]() Tags: [agentic-ai](), [agents](), [ai](), [ai-security](), [application-security](), [awareness](), [blog](), [ci-cd](), [compliance](), [cursor](), [development](), [devsecops](), [executive](), [mcp-server](), [sdlc](), [secure-by-design](), [security](), [snyk-platform](), [trust](), [updates]() ### AI overview This article reports insights from Snyk's Silicon Valley Lighthouse event on building secure, trustworthy AI systems. It examines agentic applications, evolving development workflows, real-time security feedback, and a culture of shared responsibility across development, platform, and security teams. ### Source excerpt Insights from Snyk's Silicon Valley Lighthouse event on building secure, trustworthy AI. Learn how to secure agentic apps, embrace a "secure by everyone" culture, and use guardrails for AI innovation.