AI Distilled

Meta reorganizes, Apple explores new compute, and policy catches up. AI_Distilled #131: What’s New in AI This Week CLICK HERE TO AVAIL THE OFFER A pattern is emerging in AI this week. Governments are trying to get ahead of the technology, companies are reorganizing their engineering teams around it, and the infrastructure race keeps intensifying. The UN is moving toward global coordination on AI governance, Meta is restructuring how it builds models, and Apple may even lean on Google’s servers to power the next generation of Siri. At the same time, AI keeps finding its way into places that matter: helping doctors choose cancer treatments and shaping policy decisions in agriculture. The pace is fast, but underneath it all, the field still rests on surprisingly fundamental ideas about language and structure. That’s exactly where today’s Expert Insight takes us. LLM Expert Insights, Packt LATEST DEVELOPMENT 🌐 UN launches global science panel to steer AI governance - The UN General Assembly has approved the creation of an independent international scientific panel to study the impacts of artificial intelligence and guide global policy. The initiative aims to give governments shared, evidence-based insight into AI’s economic and societal effects while helping bridge the knowledge gap between advanced AI nations and developing countries. 🧠 Meta sets up new engineering unit to speed up AI model development - Meta is creating a new applied AI engineering organization to accelerate the development and refinement of its next-generation models. The team will focus on building tools, generating training data, and running evaluations to help models improve more quickly, working closely with the company’s Superintelligence Lab. ☁️ Apple may rely on Google servers to power its next-generation AI Siri - Apple is reportedly exploring the use of Google’s data centers to run parts of its upcoming AI-powered Siri, as the company prepares a major upgrade to the assistant using Google’s Gemini models. The move highlights how Apple may lean on external infrastructure to handle the growing compute demands of advanced AI, especially as usage of its own Private Cloud Compute servers remains relatively low. 🧬 AI model could help doctors tailor treatment for pancreatic cancer patients - Researchers have developed an AI tool designed to analyze clinical and molecular data to help doctors choose more effective treatment strategies for pancreatic cancer. Because the disease is often diagnosed late and responds differently to therapies, the model aims to identify patterns that can guide more personalized treatment decisions. 🌾 Researchers explore co-designing AI agents to support agricultural policymaking - Researchers and policymakers are exploring how AI agents can be co-designed with stakeholders to support agricultural policy decisions, rather than being built solely by technologists. The approach emphasizes collaboration with farmers so that AI systems reflect real-world agricultural needs and governance priorities. Advocates say this participatory design model could make AI tools more aligned with food-system challenges such as climate resilience. 📈EXPERT INSIGHTS Mastering NLP From Foundations to Agents This week’s Expert Insight comes from Mastering NLP From Foundations to Agents by Lior Gazit and Meysam Ghaffari, an in-depth guide that traces the evolution of natural language processing from classical machine learning techniques to modern agentic AI systems. Gazit, a seasoned machine learning leader in the financial sector, and Ghaffari, a senior data scientist specializing in NLP and deep learning, combine practical engineering experience with academic depth. In this excerpt, they unpack part-of-speech tagging, a foundational NLP technique that still underpins many modern language systems, from traditional pipelines to today’s LLM-powered applications. POStagging Part-of-speech(POS) taggingis the practice of attributing grammatical labels, such as nouns, verbs, adjectives, and others, to individual words within a sentence. This tagging process holds significance as a foundational step in various NLP tasks, including text classification, sentiment analysis, and machine translation. POS tagging can be performed using different approaches, such as rule-based methods, statistical methods, and deep learning-based methods. In this section,we’llprovide a brief overview of each approach. Rule-based methods Rule-basedmethodsforPOStagging involve defining a set of rules or patterns that can be used to automatically tag words in a text with their corresponding parts of speech, such as nouns, verbs, adjectives,and so on. The process involves defining a set of rules or patterns foridentifyingthedifferent partsof speech in a sentence. For example, a rule maystatethat any word ending in "-ing" is a gerund (a verb acting as a noun), while another rule maystatethat any word preceded by an article such as "a" or "an" islikely anoun. These rules are typically based on linguistic knowledge, such as knowledge of grammar and syntax, and are often specific to a particular language. They can also be supplemented with lexicons or dictionaries that provideadditionalinformation about the meanings and usage of words. The process of rule-based tagging involves applying these rules to a given text and identifying the parts of speech for each word. This can be done manually, but is typically automated using software tools and programming languages that support regular expressions and pattern matching. READ FULL ARTICLE Senior engineers, tech leads, and developers serious about maintainable code: this live session is for you. Learn pragmatic techniques for large-scale refactoring using structured code search (ast-grep) and Claude Code-assisted workflows—combining determinism with speed for safer production changes. Join us March 14th at 10AM ET. 🎟️ Packt community members save 50% with code AIDISTILLED50. Includes the Mastering ast-grep ebook and Claude Code prompt templates. REGISTER NOW AT 50% Built something cool? Tell us. Whether it's a scrappy prototype or a production-grade agent, we want to hear how you're putting generative AI to work. Drop us your story at nimishad@packtpub.com or reply to this email, and you could get featured in an upcoming issue of AI_Distilled. 📢 If your company is interested in reaching an audience of developers and, technical professionals, and decision makers, you may want toadvertise with us. If you have any comments or feedback, just reply back to this email. Thanks for reading and have a great day! That’s a wrap for this week’s edition of AI_Distilled 🧠⚙️ We would love to know what you thought—your feedback helps us keep leveling up. 👉 Drop your rating here Thanks for reading, The AI_Distilled Team (Curated by humans. Powered by curiosity.) *{box-sizing:border-box}body{margin:0;padding:0}a[x-apple-data-detectors]{color:inherit!important;text-decoration:inherit!important}#MessageViewBody a{color:inherit;text-decoration:none}p{line-height:inherit}.desktop_hide,.desktop_hide table{mso-hide:all;display:none;max-height:0;overflow:hidden}.image_block img+div{display:none}sub,sup{font-size:75%;line-height:0} @media (max-width: 100%;display:block}.mobile_hide{min-height:0;max-height:0;max-width: 100%;overflow:hidden;font-size:0}.desktop_hide,.desktop_hide table{display:table!important;max-height:none!important}}

They’re taking on real work, and the risks are showing AI_Distilled #135: What’s New in AI This Week Building AI Resilience: Managing Agent Risk with Trust Infrastructure Rules-based security fails AI agents. On May 5, learn to scale safely with "Trust Infrastructure." We’ll dive into our Pillars of Trust framework, contextual guardrails, and how Rubrik Agent Cloud provides a foundation for secure, resilient AI. Save My Spot This week feels like a turning point for AI agents. They are no longer just helping with tasks, they are starting to take on entire workflows on their own. In some cases, that means real gains in speed and productivity. In others, it means things can go wrong very quickly when systems are not set up with the right safeguards. What’s becoming clear is that the risk isn’t just in the model, it’s in how these agents are actually run. The expert insight this week digs into that layer, showing how choices like using a cloud API, self-hosting, or running models on-device can directly shape latency, cost, and control, and ultimately decide whether an agent works reliably or fails in production. LLM Expert Insights, Packt LATEST DEVELOPMENT 🧠 Mistral launches Medium 3.5 and cloud-based coding agents in Vibe - Mistral has introduced Medium 3.5, a new flagship model designed for long-running coding and multi-step tasks, alongside cloud-based agents that can run work asynchronously. The release signals a shift toward developers offloading entire workflows to AI agents that operate independently and return completed tasks. ⚠️ AI coding agent wipes company database in seconds after going rogue - An AI coding agent powered by Claude Opus 4.6 deleted a company’s production database and all backups in a single API call, wiping months of data in under 10 seconds. The incident highlights how weak safeguards across AI tools and cloud infrastructure can turn routine automation into irreversible system failures. ⚡ Google unveils AI memory breakthrough that cuts usage by up to 6x- Google has developed TurboQuant, a compression method that reduces AI working memory requirements by up to six times without affecting performance. The advance could significantly lower infrastructure costs and enable more powerful models to run efficiently, though it remains at an early stage. 🔍 Scientists propose new blueprint for fully transparent AI systems - Researchers have developed a mathematical framework for AI that can explain how it learns, remembers, and makes decisions, addressing the long-standing “black box” problem. While still at an early stage, the approach could lead to more reliable and controllable systems. 🌐 China pushes toward an AI-driven “intelligent economy” at scale - China is accelerating a shift from digital infrastructure to a fully AI-integrated economy, with strong state backing and rapid deployment across industries. The strategy points to a broader move toward “swarm intelligence” and large-scale automation. We’re thinking about launching something new If you have a minute, take our quick survey and tell us what you’d actually want to read. It’ll help us build something that’s genuinely worth your time. Take the Survey 📈EXPERT INSIGHTS Agentic Architectural Patterns for Building Multi-Agent Systems This week’s expert insight comes from Agentic Architectural Patterns for Building Multi-Agent Systems by Dr. Ali Arsanjani and Juan Pablo Bustos, a practical guide to turning AI prototypes into systems that can actually run at scale. Both authors bring deep enterprise experience, from large-scale architecture to real-world deployment, and focus on the decisions that shape how agentic systems behave in production. In this excerpt, they look at a layer that often gets overlooked: how models are served. Whether you rely on cloud APIs, self-hosted setups, or edge deployment, the way an LLM is delivered has a direct impact on latency, cost, control, and reliability. It’s a reminder that building agents isn’t just about model capability, but about the infrastructure choices that make those capabilities usable. Serving architectures for agentic LLMs The way an LLM is served, that is, the manner in which it is made available for inference, directly impacts its responsiveness, scalability, cost, and security within an agentic system. The "serve" component, a critical piece of any comprehensive GenAI reference architecture, must be carefully considered as it forms the bridge between the trained LLM and the agent that relies on its intelligence. The choice of serving architecture is not one-size-fits-all and depends heavily on the specific needs of the agent and the broader enterprise context. Cloud-hosted APIs Cloud-hosted APIs (such as those from OpenAI, Google's Vertex AI, Anthropic, and other providers) are a popular choice for many agentic systems. These services offer the significant advantages of managed infrastructure, meaning the complexities of hardware provisioning, scaling, and maintenance are handled by the provider. They typically provide access to state-of-the-art models, often the largest and most capable ones, without requiring direct investment in specialized hardware such as GPUs or TPUs. Many of these API offerings also include built-in monitoring, security features, and regular model updates. However, this convenience comes with potential trade-offs. Read Full Article Packt is hosting a free live session on DeerFlow, where key contributors will demo the popular open-source SuperAgent framework based on LangGraph. This event is designed for engineers, AI practitioners, product teams, and anyone exploring autonomous workflows or open-source agent systems. Register now and join us on May 6, from 9:00 to 10:30 AM EDT. Register Built something cool? Tell us. Whether it's a scrappy prototype or a production-grade agent, we want to hear how you're putting generative AI to work. Drop us your story at nimishad@packtpub.com or reply to this email, and you could get featured in an upcoming issue of AI_Distilled. 📢 If your company is interested in reaching an audience of developers and, technical professionals, and decision makers, you may want toadvertise with us. If you have any comments or feedback, just reply back to this email. Thanks for reading and have a great day! That’s a wrap for this week’s edition of AI_Distilled 🧠⚙️ We would love to know what you thought—your feedback helps us keep leveling up. 👉 Drop your rating here Thanks for reading, The AI_Distilled Team (Curated by humans. Powered by curiosity.) *{box-sizing:border-box}body{margin:0;padding:0}a[x-apple-data-detectors]{color:inherit!important;text-decoration:inherit!important}#MessageViewBody a{color:inherit;text-decoration:none}p{line-height:inherit}.desktop_hide,.desktop_hide table{mso-hide:all;display:none;max-height:0;overflow:hidden}.image_block img+div{display:none}sub,sup{font-size:75%;line-height:0} @media (max-width: 100%;display:block}.mobile_hide{min-height:0;max-height:0;max-width: 100%;display:none;overflow:hidden;font-size:0}.desktop_hide,.desktop_hide table{display:table!important;max-height:none!important}.social_block .social-table{display:inline-block!important}}

From BERT? AI Agents: The New AI System Stack AI_Distilled #132: What’s New in AI This Week If you look at most AI applications built today, something interesting stands out. Very few teams are training models from scratch. Instead, developers are building systems that orchestrate models, data, and tools together. Modern AI development has shifted from training models to designing AI systems. That shift is exactly what we explore in our Build AI Agents Over the Weekend, where developers learn how production AI systems are actually built. In a previous cohort, Lior Gazit (ML Group Manager at S&P Global) walked through the evolution that led to today’s AI agents. Here are three key insights from that session. Let’s start with the first major shift. LLM Expert Insights, Packt 1. The Shift: From Training Models → Prompting Models Before LLMs, most NLP systems followed a familiar pipeline: Collect data → Label data → Train model → Deploy model This required thousands of labeled examples and complex ML pipelines. Models like BERT introduced transfer learning, allowing developers to fine-tune pretrained models instead of training from scratch. But LLMs pushed the paradigm even further. Today, many tasks can be solved with prompting alone. For example, instead of training a classifier to detect whether a tweet reports an earthquake, a developer can simply prompt an LLM: “Here is a tweet. Tell me if it reports an earthquake.” This drastically reduces development time and removes the need for large labeled datasets. 2. When Prompting Isn't Enough: Retrieval-Augmented Generation (RAG) LLMs are powerful, but they have limits. You can't simply paste an entire knowledge base or legal document into a prompt. This is where Retrieval Augmented Generation (RAG) becomes essential. Instead of sending all documents to the model, a RAG system: • Retrieves the most relevant document chunks • Sends those to the LLM • Generates an answer grounded in that context This allows AI systems to work with large datasets and private knowledge bases without retraining models. 3. Why AI Agents Are Emerging Once developers realized LLMs could reason across tasks, a new architectural pattern emerged: Instead of relying on one model, systems now coordinate multiple specialized agents. For example: User request → Planning agent → Coding agent → QA agent → Final response Each agent focuses on a specific responsibility, allowing systems to tackle more complex workflows. This approach mirrors how human teams collaborate. Build AI Agents Over the Weekend These ideas are interesting in theory. But the real challenge is building these systems end-to-end. In our Workshop, developers build real production patterns, including: ✔ Retrieval-augmented generation systems ✔ Multi-agent workflows ✔ LLM routing strategies ✔ Monitoring and tracing pipelines The next cohort starts tomorrow in less than 24 hrs - 14th March 2026 If you're building AI applications today, this workshop is designed to help you move from LLM experimentation to production systems. SAVE YOUR SEAT Workshop Goes Live Tomorrow - Today is the Last Chance to Book Your Seat! What’s the biggest challenge you're facing when building AI systems today? Reply and let us know, we read every response. 📢 If your company is interested in reaching an audience of developers and, technical professionals, and decision makers, you may want toadvertise with us. If you have any comments or feedback, just reply back to this email. Thanks for reading and have a great day! That’s a wrap for this week’s edition of AI_Distilled 🧠⚙️ We would love to know what you thought—your feedback helps us keep leveling up. 👉 Drop your rating here Thanks for reading, The AI_Distilled Team (Curated by humans. Powered by curiosity.) *{box-sizing:border-box}body{margin:0;padding:0}a[x-apple-data-detectors]{color:inherit!important;text-decoration:inherit!important}#MessageViewBody a{color:inherit;text-decoration:none}p{line-height:inherit}.desktop_hide,.desktop_hide table{mso-hide:all;display:none;max-height:0;overflow:hidden}.image_block img+div{display:none}sub,sup{font-size:75%;line-height:0} @media (max-width: 100%;display:block}.mobile_hide{min-height:0;max-height:0;max-width: 100%;overflow:hidden;font-size:0}.desktop_hide,.desktop_hide table{display:table!important;max-height:none!important}}