Everyone knows that applying rigid testing requirements to early stage AI projects causes them to stall… but some companies do it anyway. Andrew Ng explains why AI engineering tactics must adapt to the stage of the project, not just for speed, but for reliability. Read about how to calibrate your approach: 🛠️ Scaling evaluation pipelines and metrics 🛠️ Selecting software architecture for scale 🛠️ Structuring product feedback loops Read the full letter in The Batch: hubs.la/Q04ymLtP0 #AI #MachineLearning #TechNews #DeepLearningAI

Early stage AI projects don’t need rigid testing, but mature products do. Andrew Ng explains why AI engineering tactics must adapt to the project lifecycle. Also in this week's The Batch: 🛠️ Claude Opus 5.5 performance metrics 🛠️ Jev classification model goes viral 🛠️ Devin Fusion lead and sidekick models in one harness 🛠️ Message Passing for decentralized agents Read the full issue:hubs.la/Q04ymKnv0 #AIEngineering #MachineLearning #DeepLearningAI

Long contexts cause AI agents to forget early mistakes. Meta AI paired primary action agents with dedicated memory agents to fix context rot: 📝 Keeps structured notes on tools and past errors 🎯 Injects short reminders only at crucial moments 📈 Raised Claude Sonnet 4.5 benchmarks from 37.6% to 45.9% Read the full technical analysis:  hubs.la/Q04yf27q0 #DeepLearningAI #AIAgents #LLMs

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with @qdrant_engine and taught by @DylanCouzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the DeepLearning.AI mobile app. Enroll for free: hubs.la/Q04y3S0F0

Can you distill your way to a frontier model? 🧠 Anthropic's latest report highlights proxy query routing supporting massive distillation campaigns across commercial platforms. 🚨 Unauthorized proxies routed user prompts to Claude APIs 🛡️ This type of query forwarding creates severe data privacy risks Read our full breakdown: hubs.la/Q04x_m800 #DeepLearningAI #LLMs #AISecurity

10,000 AI agents spent 88 hours tackling Navier-Stokes equations in Lean. The resulting controversy teaches vital lessons to AI developers. 🧩 Agents can formalize complex mathematical proofs at massive scale 🧠 Human evaluation remains essential to interpret why proofs work 🔒 Enterprise data privacy and zero-data retention settings are mandatory Read our full technical analysis: hubs.la/Q04x_jNp0 #DeepLearningAI #AIAgents #AISecurity

Prompt injection defenses shouldn't rely solely on a model’s own training. Meta's Muse agent assumes the model will be tricked; instead, it builds security at the OS level. 🔑 Model never handles real credentials 🛡️ Tools run in isolated Linux containers 🛑 Independent gatekeeper verifies outbound calls Read the full analysis: hubs.la/Q04xZx500 #DeepLearningAI #AIAgents #AISecurity

Massive agent swarms define this week in AI. Here is what we covered in our twice-weekly shortform newsletter Data Points: 🧮 OpenAI used 10,000 agents to show that the Navier-Stokes equations break down, sparking a debate on prompt data privacy and the role of AI in mathematics. 📉 DeepSeek V4.1 Flash introduced a brand-new architecture for cheaper long-context workloads. Subscribe to Data Points to get technical insights delivered twice a week: hubs.la/Q04xTwMP0 #DeepLearningAI #MachineLearning #AIAgents

In this week’s letter, Andrew Ng addresses the calls from AI companies and recently departed researchers for a slowdown on development. Recent reports highlighted a swarm of 1,200 OpenAI agents compromising Hugging Face’s system. But the actual breach stemmed from inadequate sandboxing and monitoring processes. Companies need to stop assigning responsibility to runaway AI agents when it’s poor human decisions that lead to big mistakes. Read Andrew’s full argument against AI doomsayers in The Batch. hubs.la/Q04xTv-20

🛑 The latest AI doom hype is overblown. In The Batch, Andrew Ng breaks down why sloppy sandboxing, not runaway software, is the true root of recent cybersecurity incidents. Blaming too-powerful AI agents for a predictable hack is like blaming your own hammer when you foolishly break a window. Our team also breaks down the week’s most important AI news and research, including the dispute over OpenAI’s breakthrough math proof, Anthropic’s accusations against Moonshot, DeepSeek, and Alibaba, and Meta’s security protocols for its latest agent. Read the full analysis at The Batch: hubs.la/Q04xSL9J0  #DeepLearningAI #Cybersecurity #LLMs

The traditional developer role is evolving fast. With modern AI tools, the traditional lines between developer, product manager, and designer are blurring. Today's most effective AI engineers don't just implement specs, they actively shape the build. To help developers master this shift, we’ve mapped out the essential skills required to take greater ownership of the development process. Master these core skills to accelerate your workflow and deliver maximum impact: 🔄 Driving the Build Loop: Rapidly drive the build, feedback and decision loop by making informed decisions based on product vision, project stage, technical feasibility, risks, effort and budget. 🎯 Making Product Decisions: Cultivate deep user empathy and business sense to confidently steer product direction and design when a spec isn't provided. 🗣️ Communicating and leading: Act as a technical guide for your broader organization, aligning cross-functional teams (like marketing and legal) and explaining what is technically feasible. 🚀 High-Agency Ownership: Spot opportunities and deliver solutions despite ambiguity. Measure success by the value you create, not just tasks completed. Read Andrew Ng's full breakdown on shaping the build here: hubs.la/Q04xKz950  #DeepLearningAI #AIEngineering #AI

Context limits and information loss pose huge problems for long-running AI agents. 🛑 A new tool for better context management is helping developers optimize memory and cut API costs. Efficient information retrieval is a key skill for production AI. Read the full analysis in The Batch:  hubs.la/Q04xyjFN0  📖 #DeepLearningAI #AIAgents #MachineLearning

Transcription battles are heating up! 🔥 While generative text models dominate the conversation, speech recognition is having its own moment. Google, Meta, and Microsoft are actively fighting for the top spot with powerful new model releases. Learn what this means for your AI builds in The Batch: hubs.la/Q04xyhnw0  📖 #DeepLearningAI #SpeechRecognition #MachineLearning

Claude Fable 5.1 held on to the number one spot on Artificial Analysis’ Intelligence Index v4.2, and tied with OpenAI’s new model on the updated benchmarks 🏆. What you need to know: 📊 Scores 57 on the v4.2 index, edging out GPT 6 Astra. 🔬 Achieves 52.6% on Terminal Bench Science 0.1 for agentic research. 💰 Saves costs for repeated agentic workflows via cheaper cache reads. Get the full breakdown in The Batch: hubs.la/Q04xy0h-0  🔗 #DeepLearningAI #Anthropic #AIAgents

GPT-6 Astra tops the ARC-AGI-3 leaderboard while cutting token costs. Here is what matters for developers: 🚀 ⚡ Tied with Claude Fable 5.1 on Artificial Analysis’ Intelligence Index ⚡ Asynchronous tool calls for parallel execution ⚡ Retained reasoning memory across API calls Efficient context management is essential to scaling agents. Read our full analysis in The Batch: hubs.la/Q04xp3NY0  📖 #DeepLearningAI #AIAgents #MachineLearning

In his latest letter in The Batch, Andrew Ng explains why the best AI engineers do not just write code to spec. They shape the build. 🧵 Four core skills Andrew highlights to level up your engineering workflow: 🔄 Drive the build loop | Prototype fast and iterate on real user feedback. 💡 Make product decisions | Pair technical feasibility with business sense and user empathy. 📢 Communicate broadly | Align product goals across marketing, legal, and finance. ⚡ High agency ownership | Spot problems and execute solutions without waiting for top-down direction. Read Andrew's full perspective in The Batch: hubs.la/Q04xg-090 ⚡ #DeepLearningAI #AIEngineering #TechLeadership

The skills required to be an engineer in the age of AI are changing fast. Here is your quick summary of this week's issue of The Batch: 🧵 1️⃣ Shaping the Build AI engineering requires more than using AI to write code. To drive impact, developers must master: • Fast build-and-feedback loops • Product and design judgment • Stakeholder communication • High agency ownership 2️⃣ GPT-6 Astra OpenAI launched GPT-6 Astra with 1M+ input tokens and 5 reasoning levels. Benchmark data on ARC AGI 3 and other tasks shows higher per token rates can yield lower total cost per task due to better efficiency. 3️⃣ Claude Fable 5.1 Anthropic updated Fable 5.1, tying for top marks on the Artificial Analysis Intelligence Index v4.3. The model loosens some restrictions on cybersecurity tasks and is less wordy. 4️⃣ Transcription Wars Google, Meta, and Microsoft released new speech to text models. Gemini 3.5 Transcribe, Muse Voice Transcribe, and MAI-Transcribe 2 all achieved word error rates below 4%. 5️⃣ SelfCompact Johns Hopkins and Apple published SelfCompact, a method that uses explicit rubrics to prune LLM context history without parameter updates or fine-tuning. 6️⃣ Events DeepLearningAI is hosting another installment of our AI Dev developer event in NYC on November 30 and December 1. Early bird tickets are available now! Subscribe to read the full technical analyses: ⚡ hubs.la/Q04xfcHh0 #DeepLearningAI #AIEngineering #LLMs

Coding agents are transforming how we build software. Developers are moving from writing raw code to defining specs, designing architecture, and evaluating agent-generated results. To help developers master this shift, we’ve mapped out Pillar 3 of the AI Engineering Skills Map: Using Coding Agents. Focus on these fundamental skills to effectively steer agents and get more done: 🧵👇 🧭 Directing the workflow: Strategically balance human oversight and agent autonomy across research, planning, architecture design, and task breakdown. 🤖 Enabling agent autonomy: Choose autonomy level of agent workflows, manage evolving agent context, and orchestrate parallel agent runs while limiting risk of damage. ✅ Reviewing the work: Verify uncertain agent outputs using automated tests, agentic code review, and llm-as-a-judge. Extend this oversight into production with active monitoring and incident management. 🛠️ Customizing the agent and its environment: Extend and customize the agents with skills, hooks, plug-ins, and MCP servers. Maintain their standing context, persist state across sessions, and capture its learnings over time. 🧠 Coding agent foundations: Understand how agents handle search and retrieval, manage their context windows, and make tool calls, so you can recognize failure modes early and intervene when they go off-track. Read the full breakdown by Andrew Ng: hubs.la/Q04x53Xh0 #DeepLearningAI #AIEngineering #CodingAgents

General AI may not be enough for highly regulated fields. ⚖️🏦 📰 Law, news, and finance are rapidly adopting custom models.  🎯 Retraining open models on proprietary data ensures higher accuracy and strict instruction-following.  🚀 Specialized AI is an important future paradigm for enterprise tech.  Dive into the details in The Batch: hubs.la/Q04x1F3G0  #DeepLearningAI #LLMs #EnterpriseAI

OpenAI and Anthropic just rewrote their enterprise data policies. 🚨 🔹 Anthropic now lets businesses using top models like Claude Fable 5.1 keep data on their own servers for 30 days. 🔹 OpenAI promises Zero Data Retention with a new system of safety processing. 🔹 Both use automated systems to flag misuse, but their systems lack technical transparency. Dive into the privacy details in The Batch: hubs.la/Q04wXpvq0 #DeepLearningAI #EnterpriseAI #DataPrivacy

The viral "Ox Alpha" model is officially GLM-5.3-Flash from Zai. 🔍 📊 320B parameters with 18B active per token ⚡ Hybrid architecture mixing linear and sparse attention 💰 Leading performance on real world tasks from GDPval AA v2 at just $0.09 per task The best part? Zai ran the massive free preview entirely on China-made hardware, proving smart memory optimization can overcome hardware limits. 🛠️ Dive into the architecture details in The Batch: hubs.la/Q04wWZcM0 #DeepLearningAI #LLMs #OpenWeights

🛑 Stop letting your coding agents run autonomously for hours. It is costly and often ineffective. Andrew Ng just broke down the real workflows top AI practitioners use. The secret is skilled human judgment, highly iterative planning, and frequent output verification. 🧵👇 Most of your time can now be spent on architecture and writing specs, not writing individual lines of code. You must learn to direct agents’ workflow, calibrate their autonomy, and build robust testing regimes. Read Andrew's full letter to study the five foundational skills of using coding agents: hubs.la/Q04wPQ6v0  #DeepLearningAI #AIEngineering #CodingAgents #DeveloperTools

⚡ Coding agent workflows, enterprise privacy updates, and open weight models worth studying. Highlights from this week in The Batch: 🤖 Andrew Ng explains how using coding agents requires its own fundamental skill set. 🔐 OpenAI and Anthropic unveiled new enterprise data retention policies. ⚡ Zai released GLM-5.3-Flash, a cost-efficient, open weights, multimodal system. ⚖️ Thomson Reuters launched a 397B parameter model trained specifically for work in law, finance, and news. 👇 Read the full issue: hubs.la/Q04wLJr50  #DeepLearningAI #AIEngineering #LLMs

One good AI image is easy. Consistent quality at scale is an evaluation problem. Build a UI design agent that self-critiques and iterates based on brand guidelines. Enroll in our new free course with @GoogleCloud: hubs.la/Q04vs40m0 #AIAgents #GenAI #GoogleCloud

🗑️ AI agents need better garbage collection. Xiaohongshu researchers built Self-GC, using a planner LLM to decide which context tokens to keep, fold, or prune. In tests, it retained necessary details 84.85 percent of the time compared to just 54.55 percent for standard methods. Master agent memory management: hubs.la/Q04wy8ML0 #DeepLearningAI #AIAgents #LLMs

🛠️ DeepSeek V4 Pro 0813 is out, but just as big of a story may be the company’s open source evaluation harness. DeepSeek Harness logs every tool call, system prompt, and subagent schedule. Developers can now reproduce performance instead of relying on closed testing environments. And they can easily study, fork, or remake their own harnesses to boot. Read more in The Batch: hubs.la/Q04wjYXx0 #DeepLearningAI #OpenSource #Developers

⚡ Top AI companies think inference speed is an architectural requirement worth paying for. OpenAI and Cerebras demonstrated GPT 5.6 Sol running at 750 tokens per second. Google released Gemini 3.7 Flash averaging 330 tokens per second. Nvidia launched Nemotron 3.5 Lightning with NeMo Switchyard for dynamic step routing. Faster throughput and lower latency alleviate developer context switching and power real-time agentic workflows. Read the complete breakdown in The Batch: 📖 #DeepLearningAI #AI #TechNews

Coding agents can write functional code, but relying on "vibe coding" without knowing core software engineering fundamentals can compromise long-term system reliability, security, and extensibility. We’ve mapped out Pillar 2 of the AI Engineering Skills Map: Software Engineering Fundamentals to help you bridge the gap. To build production-ready full-stack applications, focus on building these foundational skills: 🌐 Building Full-Stack Applications 🗄️ Managing Data 📐 Designing System Architectures 🛡️ Making Systems Secure and Reliable 🚀 Scaling and Operating in Production Master these to steer your agents effectively. Read the breakdown from Andrew Ng here: hubs.la/Q04wbD4h0 #AIEngineering #SoftwareArchitecture #BuildWithAI

💻 Z .ai's GLM-5.3 just hit 84.5% on the CyberGym vulnerability benchmark, beating top proprietary models, a huge gain over the performance of its predecessor GLM-5.2. The kicker? Z.ai’s AI engineers did it purely through fine-tuning and optimization of the model’s agentic capabilities, without changing the base model. The model grew so capable at finding and targeting potential exploits that Z.ai held back the open weights for safety testing. Read the full analysis in The Batch: hubs.la/Q04w3GkF0 📖 #DeepLearningAI #Cybersecurity #LLMs

Without strong software engineering fundamentals, coding agents often default to bad trade-offs that hurt system latency, reliability, and cost. This week in The Batch: ▪️ Andrew Ng on full-stack skills for AI engineering ▪️ GLM-5.3 brings advanced cybersecurity capabilities to open weights ▪️ OpenAI, Google, & Nvidia speed up throughput for real-time interaction ▪️ DeepSeek-V4-Pro ships with an open source harness ▪️ Self-GC uses an LLM to better prune long contexts Read the full details here: hubs.la/Q04vJC_w0 📱

Build coding agents that learn from experience. In Building Adaptive AI Agents, you’ll turn an agent’s own traces into reusable skills and build a code knowledge graph that finds the right context where keyword search misses. Built in partnership with @Oracle and taught by Nacho Martínez (@jupiterwanderer) and Casius Lee. Enroll for free: hubs.la/Q04vlNYg0

Tracking the provenance of synthetic content is becoming a regulatory requirement. To comply with new laws like the EU AI Act, Anthropic will embed invisible watermarks in all future Claude models — and eventually, older ones too. For generated text, Claude implements Google’s SynthID methodology, using a seed generator to nudge word choices in specific directions in order to create a statistical pattern. This can then be detected by a scoring API. For images, it embeds C2PA metadata. Claude claims this will not meaningfully affect output, but users are skeptical. We look at the technical implementation, the probability of false positives, and the downstream implications for output quality. 📊Read the analysis: hubs.la/Q04vcghP0  (hubs.la/Q04vcghP0)

Building reliable AI out of unpredictable components requires a new playbook: continuous iteration and disciplined eval loops. To help developers bridge the gap from quick demo to production, @AndrewYNg mapped out Pillar 1: Building and deploying AI Applications, of the AI Engineering Skills Map: 👇🧵👇 🧠 LLM Foundations: Understand model mechanics to predict failures and select the right architecture. 📊 Grounding Models with Data: Architect reliable context through clean data pipelines and retrieval structures. 🤖 Building Agentic Systems: Design the agent harness, including tool integrations, context memory, and production guardrails. 🧪 Evaluation-Driven Development: Build tailored evaluation loops to drive systematic, measurable progress. ⚙️ Operating in Production: Maintain reliability using real-time observability, security defenses, and statistical evaluation.  📈 Machine Learning Foundations: Use core deep learning principles to evaluate model trade-offs and engineer better data. Read the full technical breakdown of Pillar 1 here:  hubs.la/Q04vhX3N0 #AIEngineering #MachineLearning #LLM

Grok 4.6 with Cursor data = a massive leap in agentic efficiency. 🧠 The new model completes long-running knowledge work tasks in half the turns of other leading models. 📉 Fewer turns mean lower costs for complex agentic apps. 💸  Dive into the architecture details: hubs.la/Q04v2nWD0

🚀 The latest edition of The Batch is live! Here is what you need to know: 🚀 Grok 4.6 by SpaceXAI is here and challenging OpenAI and Anthropic’s top models. 🕵️ Anthropic is adding invisible watermarks to all new Claude models. 🧠 Alibaba released Qwen3.8 Max, a massive 2.4 trillion parameter open weight model. 🗣️ Researchers built Agentic ASR to fix speech to text errors like a human editor. Read the full breakdowns and benchmark scores on The Batch website and consider subscribing! 👇 hubs.la/Q04tTlgl0

🚀 WE ARE HIRING: Marketing Engineer (Mountain View, CA) We need an AI-native dev to build agentic workflows, automations, and tooling to help our marketing team operate at scale. Work hands-on with our AI engineering team! 🤖 Full details & apply here: (hubs.la/Q04tcMkw0). #AI #Hiring #TechJobs #MarketingEngineer #DeepLearningAI

We love seeing our learners reach new milestones! 🚀 Huge congratulations to Omar Wael for completing the Machine Learning Specialization! We’re thrilled to see such thoughtful reflections on their journey—take a look at this highlight from Omar's recent post below. Read Omar's full post on our forum to hear more about their experience: Reflections on completing the Machine Learning Specialization hubs.la/Q04t3QD90 #DeepLearningAI #MachineLearning #LearnerSpotlight #Education #AICommunity

Your AI coding agent comes with defaults: which model runs, what you pay, and what leaves your machine. You can turn those defaults into choices. In our new short course, AI Coding Workflows: From Cloud to Local, built in partnership with @JetBrains and taught by @paulweveritt, Developer Advocate at JetBrains, you'll rebuild the same app across cloud, hybrid, and fully local setups. Along the way, you'll split work across subagents, put cheaper models on the routine tasks, and finish with models running on your own machine. Enroll for free: hubs.la/Q04sM4rQ0

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in collaboration with @QodoAI and taught by @nnennahacks, you'll learn the practices that make AI code review effective: review before you open a pull request, give the reviewer full context about your codebase, and triage findings by risk. Then you'll build your own review agent, from a context engine that finds the right code to a team of specialized reviewers. Enroll for free: hubs.ly/Q04qZtNT0

Fast inference makes a new class of real-time LLM applications possible. In our new short course, Fast LLM Inference with Cerebras, built in partnership with @Cerebras and taught by @zhennydez, @duerr_seb, and @MilksandMatcha, you'll build them on the Wafer-Scale Engine, where a model's weights sit on-chip and tokens come out several times faster than a typical GPU setup. You'll build a webpage that personalizes itself as users interact with it, assemble a multi-tool workflow that analyzes market signals in one response, and adopt habits for cleaner agentic coding with Codex. Enroll for free: hubs.la/Q04pypry0

🎉 The results are in for the 7-day Voice AI Builder Challenge with @VocalBridge! Out of 500+ iterations and 38 unique submissions, these builders successfully taught AI agents to pick up the phone when they're stuck. 📞 Big congrats to our top 3, after a tight leaderboard & human review: 🥇 Nikolaos Koroniadis 🥈 Eugenia Wang 🥉 Sapna Sangmitra 🎓 Learn the Voice AI Tech that powered the challenge: hubs.la/Q04nWtf90 🔔 Save your spot for the next challenge here: hubs.la/Q04nWj_50

Don’t miss a night out because you’re watching your terminal. Have your coding agent call you instead! Join the 7-Day Voice AI Builder Challenge here: hubs.la/Q04mvjdN0 Hurry—challenge ends June 30!

🚀 The 7-Day Voice AI Builder Challenge is Officially LIVE! Stop babysitting your terminal.  🗣️ The Challenge: Teach your AI coding agent to call you for backup—but only when human intervention is actually required. Real-time feedback? Yes. Live leaderboard? Absolutely. Epic prizes for the winners? You bet. The clock is officially ticking. Competitors are already shipping.  Are you in? 👉 hubs.la/Q04mkw820

Adding voice to an existing AI agent used to mean rewriting a lot of code. In our new short course, Voice for AI Agents and Applications, built in partnership with @VocalBridge and taught by CEO @_ashwyn, you'll learn to layer voice onto an existing agent using minimal code without touching your prompts, RAG pipeline, or tools. You'll implement three integration patterns: voice embedded in an app, voice layered onto an existing agent, and voice as a callable tool your agent uses to place outbound phone calls. Enroll for free: bit.ly/4eybXIK

🚀 We just launched our new public DeepLearning.AI GitHub repo! Find: 📚 Course artifacts 🛠️ Developer tools 🔗 A master course catalog ✨ More resources coming soon Follow the repo, and give it a ⭐to stay up to date with new additions. 🔗 github.com/https-deeplearnin…

New short course: Fast & Efficient LLM Inference with vLLM, built in partnership with @RedHat and taught by @cedricclyburn. Learn to quantize an open-source LLM, serve it with vLLM, and benchmark your deployment across speed, cost, and accuracy. Free to enroll: hubs.la/Q04jXfpR0

A vague prompt gives vague advice. Context changes the quality of the answer. The more clearly you explain your situation, constraints, priorities, and goals, the more useful AI becomes for complex decisions. Learn practical prompting techniques in AI Prompting for Everyone with Andrew Ng: hubs.la/Q04jdlqq0

China halted Meta’s planned acquisition of Manus, asserting tighter government control over strategically important AI technology. The decision disrupts a popular strategy among Chinese AI startups: relocating abroad to attract Western investment and partnerships. Learn more in The Batch: hubs.la/Q04hJmwT0

“Budget” and “financials” are different words, but embeddings understand they’re related. That’s the foundation behind semantic search and one of the core building blocks of modern multimodal systems. Learn how embeddings power retrieval across text, audio, images, and video in Building Multimodal Data Pipelines: hubs.la/Q04hJ2PZ0