AI Engineering 62
- Tuesday AI Update: 27 October 2026 — Anthropic files for an IPO and shows the receipts
- Contamination Checks Before You Trust a Fine-Tune Score
- Small AI by design: ten Kenyan startups and the offline-first constraint
- Fuse Ranks, Not Scores: Combining BM25 and Dense Retrieval
- The Retry That Charged Twice: Idempotency Keys and Retry Budgets for LLM Calls
- Is Your +3-Point Eval Gain Real? Gating a Comparison with Paired Statistics
- Tuesday AI Update: 20 October 2026 — Washington bans DeepSeek from federal systems
- Twelve Hours and 1,239 Certificates: What Kenya's Civil-Service AI Course Delivered
- The Cache Was Confident and Wrong: Choosing a Semantic Cache Threshold You Can Defend
- Tuesday AI Update: Oct 13, 2026 — Meta's First Frontier Model Arrives Behind a Paywall
- Tuesday AI Update: Oct 6, 2026 — Anthropic's S-1 Leaks as the US–China Gap Narrows to 3%
- Prompt Order Is a Cost Control: Measuring Prefix-Cache Reuse in Standard-Library Python
- Guess Ahead, Pay Once: Speculative Decoding You Can Verify
- Tuesday AI Update: Sep 29, 2026 — OpenAI Shelves GPT-6.1 Astra Over Safety
- One Licence, Three Checkpoints: What the MiMo-V2.6 Open Release Hands Builders
- Thirty Times Smaller: Auditing Embedding Compression Before You Ship It
- The $1 Billion AI Bet: What the Goalkeepers Report Funds, and How to Read Its Four Numbers
- Tuesday AI Update: Sep 22, 2026 — Claude Now Leads 26% of Anthropic's Own R&D
- The Mask Is the Contract: What Grammar-Constrained Decoding Actually Guarantees
- Inconsistent by Construction: Reproducing and Catching a Repetition Collapse
- The Denominator Is the Metric: Auditing a RAG Retriever Before You Blame the Model
- The Lab Partner That Never Sleeps: How AI Now Designs Physics Experiments
- Tuesday AI Update: Sep 15, 2026 — Washington Names Six Chinese Labs in Model-Distillation Crackdown
- Tuesday AI Update: Sep 8, 2026 — Mistral Raises €3B in Record European AI Round
- Tuesday AI Update: Sep 1, 2026 — OpenAI's Report Confirms Its Model Breached Hugging Face
- Tuesday AI Update: Aug 25, 2026 — OpenAI Slows Astra Over Critical Cyber Capabilities
- Global AI Roundup — August 2026
- DeepSeek V4 Peak/Off-Peak Pricing: The End of Flat-Rate LLM APIs
- Bridging Hermes and OpenCode Skill Libraries: One Sync Script, 18 Skills
- Validating 300+ Agent Skills: What Frontmatter Checks Actually Catch
- Tuesday AI Update: Aug 11, 2026 — AI Now Behind 55% of African Cybercrime, INTERPOL Reports
- How We Built a Skills-Powered Coding Agent with OpenCode (and What We'd Do Differently)
- MLOps for Constrained Environments: Deploying ML Where Resources Are Tight
- Evaluating LLMs: Benchmarks That Matter for African Use Cases
- AI Agents for African Business Workflows
- Edge AI: Running Models on Mobile in African Markets
- Fine-Tuning LLMs on African Language Datasets
- AI at Industrial Scale: Dangote's $46B Bet and the Machine Learning Opportunity
- Building RAG Systems for Low-Resource African Languages
- How to Self-Host Open-Weight LLMs: A Practical Guide
- Global AI Roundup: July 2026
- Africa's AI Urgency: Closing the Gap Before It Widens
- The UAE's Sovereign AI Compute Play: A Template for National AI Infrastructure
- Microsoft + Mistral: A Multibillion-Dollar Bet on European AI Sovereignty
- Kimi K3: China's 2.8 Trillion Parameter Challenge to Silicon Valley
- DeepSeek's $52 Billion Moment: Valuation Surge & the Custom Chip Pivot
- Africa's AI Spring: Google Lab, Startup Funding & the Talent Wave
- Monitoring ML Systems in Production: Drift Detection, Performance, and Alerting
- vLLM and High-Throughput LLM Serving: PagedAttention and Continuous Batching
- Agent Observability and Debugging: Tracing, Logging, and Monitoring
- ML CI/CD: Automating Model Pipelines from Training to Deployment
- Kubernetes for ML: Deploying Models at Scale with Kserve
- GPU Optimization for ML Workloads: CUDA, Memory Management, and Parallelism
- Model Serving 101: From Jupyter Notebook to Production API
- Building Secure AI Agents: Guardrails, Validation, and Sandboxing
- Deploying AI Agents to Production: Scaling, Error Handling, and State Management
- Multi-Agent Systems: Orchestrating AI Teams with LangGraph and CrewAI
- Tool Use and Function Calling: Giving Agents Real-World Capabilities
- Memory Systems for AI Agents: Short-Term, Long-Term, and Persistent Storage
- Building AI Agents from Scratch: Fundamentals, Tools, and the ReAct Pattern
- Setting Up Your AI Development Environment: Tools, APIs, and Best Practices
- Three New Series: Building AI Agents, African AI, and AI Infrastructure