AI Engineering: Building Applications with Foundation Models
A practical guide to building real-world applications with foundation models and LLMs.
AI EngineeringMachine LearningLLMAgentic AI
Visit AI Engineering: Building Applications with Foundation ModelsReferenced in
Scaling Agentic Workflows: How EvoSOP Turns Agent Experience into Reusable SOPsMoving Beyond Confidence Scores: Measuring AI MetacognitionPredicting LLM Accuracy Before the Model Finishes TalkingThe Dialect Gap: Why Robustness Doesn't Mean Fluency in LLMsMoving Facts Out of Weights: Why Co-LMLM Matters for ProductionDesigning Viable Viral Genomes with Evo 2: Beyond Sequence PredictionBeyond the Context Window: Why zkVM Auditing Still Needs a Human MapThe Capex Trap: Why Big Tech is Doubling Down on AI InfrastructureMaking Recursive Greedy Clustering Actually UsableWhy Solving PDEs via Tensor Factorization Matters for Manifold LearningMoving Beyond Outcome-Only Rewards: Why Path Penalties Matter for Production AgentsThe Professional Cost of AI Slop in EngineeringGiving AI Agents the Keys to the Kingdom (Without the Risk of Burning it Down)The Unit Economics Gap in the AI BoomLiveOIBench: A New Competitive Programming Benchmark for Evaluating LLM Coding CapabilitiesHybrid Quantum-Classical Architectures: Solving Time Series Invariance with Path SignaturesSoofi S 30B-A3B: Why 'Active' Parameters are the New Scaling MetricThe Geometry of Thought: Decoding the AI Black BoxAI in Your Feed: Why Longform Social Media is Getting Flooded (And How to Spot It)From Logs to PRs: Closing the Loop on AI Agent ObservabilityMoving Beyond Silence: Why Multimodal Projection Matters for Robot MediationBeyond the Demo: The Gritty Reality of Agentic Video ProductionSolving the Verbosity Problem in Reasoning Models with AgonBuilding for AGI: Why Your Current Stack is About to BreakThe Great Leveling: Why AI is a Productivity Power-Up for NewcomersThe Metadata Band-Aid: Why Article 50 Fails to Stop ManipulationThe One-Step Trap: Why Local Accuracy is Killing Long-Term AI PlanningThe Architecture of Autonomy: Why Your Workflows Are BrittleThe Industrialization of Fraud: Why Voice Cloning is Outrunning DefenseThe Shortcut Problem: Why LRM Thinking Traces Aren't Always Reasoning
Some Phugialy Picks use affiliate links. If you buy through one, Phugialy may earn a commission. It doesn't change what we recommend. Full disclosure →