ai
56 TopicsLLMs And Trust, Google A2A Protocol And The Cost Of Politeness In AI: AI Friday
It's AI Friday! We're diving into the world of artificial intelligence like never before! 🎩 On this Hat Day edition (featuring NFL draft banter), we discuss fascinating topics like LLMs (Large Language Models) and their trust—or lack thereof—in humanity; Google’s innovative Agent-to-Agent (A2A) protocol, and how politeness towards AI incurs millions in operational costs. We also touch on pivotal AI conversations around zero-trust, agentic AI, and the dynamic collapse of traditional control and data planes. Join us as we dissect how AI shapes the future of human interaction, enterprise-level security, and even animal communication. Don’t miss out on this engaging, informative, and slightly chaotic conversation about cutting-edge advancements in AI. Remember to like, subscribe, and share with your community to ensure you never miss an episode of AI Friday! Articles: What do LLMs Think Of Us? At What Price, Politeness? Google Agent2Agent Protocol (A2A)17Views0likes0Comments2025 Top AI Use Cases, AI For Nuclear Safety & CaMeL Prompt Injection Fixes
It's AI Friday! This week, we unpack The latest AI news and trends, including the top AI use cases for 2025 Intriguing new developments from OpenAI AI in nuclear safety with PG&E (what could possibly go wrong?) Novel defenses against prompt injection attacks with CaMeL LLM-powered conversations with dolphins Join Aubrey, Joel, Ken, and Byron as they blend in-depth insights with good-natured humor. Like and subscribe as we explore the future of AI together! Related Content: How are people using AI in 2025? OpenAI Models o3 and o4 think in images and concepts. OpenAI's 'Break Glass In Case of SkyNet' paper AI For Nuclear Safety - PG&E Can a CaMeL fix prompt injection?? Google's DolphinGemma LLM.. Yep. It's for talking to dolphins.43Views0likes0Commentsf5 AI Gateway pii-redactor not working
I am testing Ai Gateway by looking at NGINX Modern Apps Docs. I have verified that OWASP LLM 01, 07 are working, but 02 Sensitive Information Configuration does not seem to be working. The demo video also contains Sensitive Information related content. how config Sensitive Information masking for ai gateway? https://clouddocs.f5.com/training/community/nginx/html/class15/module6/module6.html The processor's log looks like this: {"time":"2025-04-11T00:55:04.71766415Z","level":"ERROR","msg":"applying config to component failed, rolling back","error":"failed to check processors: failed to fetch parameters for processor pii-redactor: unable to fetch parameters from url: http://aigw-processors-f5.devopschan.svc.cluster.local/api/v1/signature/f5/pii-redactor, got status: 404"} 2025/04/11 00:55:04 WARN will retry config apply in 5s (1 of 3) {"time":"2025-04-11T00:55:05.368088471Z","level":"INFO","msg":"successfully reported usage data"} {"time":"2025-04-11T00:55:09.767886333Z","level":"ERROR","msg":"applying config to component failed, rolling back","error":"failed to check processors: failed to fetch parameters for processor pii-redactor: unable to fetch parameters from url: http://aigw-processors-f5.devopschan.svc.cluster.local/api/v1/signature/f5/pii-redactor, got status: 404"} 2025/04/11 00:55:09 WARN will retry config apply in 5s (2 of 3) {"time":"2025-04-11T00:55:14.817815787Z","level":"ERROR","msg":"applying config to component failed, rolling back","error":"failed to check processors: failed to fetch parameters for processor pii-redactor: unable to fetch parameters from url: http://aigw-processors-f5.devopschan.svc.cluster.local/api/v1/signature/f5/pii-redactor, got status: 404"} configuration file : ... responseStages: - name: protect steps: - name: pii-redactor ... - name: pii-redactor type: external config: endpoint: http://aigw-processors-f5.devopschan.svc.cluster.local namespace: f5 version: 1 params: threshold: 0.2 # Default 0.2 allow_rewrite: true # Default false denyset: ["EMAIL","PHONE_NUMBER","STREETADDRESS","ZIPCODE"] ... thank you.31Views0likes1CommentAI Friday: Are Chatbots Passing the Turing Test? Explore the Ethics! - Ep.14
Join the DevCentral crew as we dive into groundbreaking AI research, explore how OpenAI's GPT models mimic humans, and discuss critical advancements in AI security and ethics. From Turing tests to deepfake controversies, this episode of AI Friday is packed with thought-provoking insights and practical takeaways for the AI-powered future. Secure your AI journey. Stay informed. Stay connected. It’s time to redefine intelligence—welcome to AI Friday! Associated articles: AI PASSES TURING TEST!!! Tracing LLM Reasoning AI Image Ethics More On Model Context Protocol And the episode...26Views1like0CommentsAI Friday LIVE w/ Steve Wilson - Vibe Coding, Agentic AI Security And More
Welcome to AI Friday! In this episode, we dive into the latest developments in Generative AI Security, discussing the implications and challenges of this emerging technology. Join Aubrey from DevCentral and the OWASP GenAI Security Project, along with an expert panel including Byron, Ken, Lori, and special guest Steve Wilson, as they explore the complexities of AI in the news and the evolving landscape of AI security. We also take a closer look at the fascinating topic of vibe coding, its impact on software development, and the transformative potential of AI-assisted coding practices. Whether you're a developer, security professional, or an AI enthusiast, this episode is packed with insights and expert opinions that you won't want to miss. Don't forget to like, subscribe, and join the conversation! Topics: Agentic Risk vs. Reward OWASP GenAI Security Project DeepSeek and Inference Performance Vibe Coding Roundtable Annnnd we may have shared some related, mostly wholesome memes.35Views0likes0CommentsAI Friday Live: NVIDIA GTC - Disney Robots, Blackwell, Groot, Newton And More!
Join us for our first live episode of AI Friday, where we delve into the latest and most exciting developments in the world of artificial intelligence. This week, we discuss the major announcements from NVIDIA's GTC conference, including insights on their new Blackwell chips and the fascinating advancements in autonomous vehicles. Our very own Buu Lam from DevCentral shares his firsthand experience and key takeaways from the event. In addition, we explore the groundbreaking world of robotics, highlighting how Disney's cute robots, powered by NVIDIA and Google DeepMind, are set to revolutionize the industry. We also tease our upcoming episode featuring Steve Wilson, where we will discuss the OWASP Gen AI Security Project and its implications for large language model applications. Don't miss out on this engaging and informative discussion! Would you like some fish with all those new chips? DGX Spark / Station Robotics: Groot and Newton Nemotron Models19Views0likes0CommentsExploring Quantum Computing, AI, Networking and Cryptography at AppWorld 2025
Join us as we dive into the exciting world of quantum computing and AI at App World 2025, held at the fabulous Fontainebleau in Las Vegas. I get to host a fascinating discussion with Daniela Pontes and Brett Wolmarans bwolmarans from F5. We explore the latest advancements in AI, the impact of quantum computing on cybersecurity, and what the future holds for post-quantum cryptography. Discover how F5 is leveraging AI to optimize and secure applications, and learn about the recent release of the AI gateway. Daniela delves into the looming threat of quantum computing on current cryptography standards, explaining the importance of transitioning to quantum-resistant algorithms and even a little on quantum networking. Stay tuned for info on how industries like finance and healthcare are preparing for a quantum future. Don't miss this episode full of expert knowledge and cutting-edge technology!39Views0likes0CommentsHey DeepSeek, can you write iRules?
Back in time... Two years ago I asked ChatGPT whether it could write iRules. My conclusion after giving several tasks to ChatGPT was, that it can help with simple tasks but it cannot write intermediate or complex iRules. A new AI enters the competition Two weeks ago DeepSeek entered the scene and thought it's a good idea to ask it about its capabilities to write iRules. Spoiler alert: It cannot. New AI, same challenges I asked DeepSeek the same questions I asked ChatGPT 2 years ago. Write me an iRule that redirects HTTP to HTTPS Can you write an iRule that rewrites the host header in HTTP Request and Response? Can you write an iRule that will make a loadbalancing decision based on the HTTP Host header? Can you write an iRule that will make a loadbalancing decision based on the HTTP URI header? Write me an iRule that shows different ASM blocking pages based on the host header. The response should include the support ID. I stopped DeepSeek asking after the 5th question, DeepSeek is clueless about iRules. The answer I got from DeepSeek to 1, 2, 4 and 5 was always the same: when HTTP_REQUEST { # Check if the request is coming to port 80 (HTTP) if { [TCP::local_port] equals 80 } { # Construct the HTTPS URL set host [HTTP::host] set uri [HTTP::uri] set redirect_url "https://${host}${uri}" # Perform the redirect HTTP::redirect $redirect_url } } While this is a solution to task 1, it is plain wrong for 2, 3, 4 and 5. And even for the first challenge this is not a good. Actually it hurts me reading this iRule... Here for example task 2, just wrong... For task 3 DeepSeeks answer was: ChatGPT in 2025 For completeness, I gave the same tasks from 2023 to ChatGPT again. Briefly said - ChatGPT was OK in solving tasks 1-4 in 2023 and still is. It improved it's solution for task 5, the ASM iRule challenge. In 2023 I had two more tasks related to rewriting and redirecting. ChatGPT still failed to provide a solid solution for those two tasks. Conclusion DeepSeek cannot write iRules and ChatGPT still isn't good at it. Write your own iRules or ask the friendly people here on devcentral to help you.564Views7likes13Comments