Building resilient data pipelines. Practical guides on data engineering, SQL migration, dbt, Spark, and modern data stack.https://reliabledataengineering.com/https://reliabledataengineering.com/posts/article_harness_is_everything/https://reliabledataengineering.com/posts/article_harness_is_everything/What Cursor, Claude Code, and Perplexity actually built -- and why the model was never the real product.Mon, 13 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_last_generation_data_engineers/https://reliabledataengineering.com/posts/article_last_generation_data_engineers/How agentic platforms are quietly making the pipeline-builder's job description obsolete -- and what survives the transition.Mon, 13 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_code_ultraplan/https://reliabledataengineering.com/posts/article_claude_code_ultraplan/Anthropic just shipped the first major feature that security researchers spotted weeks ago in its accidentally exposed source code. And it turns out the leaked description wasn't hype.Sun, 12 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_opus_nerfed/https://reliabledataengineering.com/posts/article_claude_opus_nerfed/A senior AMD AI director's logs point to sharp regression in Claude's coding performance -- Anthropic says it's a product change, not a dumber model.Sun, 12 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_ai_engineer_vs_data_engineer_vs_mle/https://reliabledataengineering.com/posts/article_ai_engineer_vs_data_engineer_vs_mle/Org charts are lying to you. The job title says 'AI Engineer' but the work varies wildly. Here's the honest picture of who actually builds and ships agentic systems in 2026.Thu, 09 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_agent_harness_real_product/https://reliabledataengineering.com/posts/article_agent_harness_real_product/A packaging error exposed 512,000 lines of Anthropic's source code. What it revealed wasn't the model -- it was the orchestration layer that changed how the industry thinks about where AI value lives.Thu, 09 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_mythos_project_glasswing/https://reliabledataengineering.com/posts/article_claude_mythos_project_glasswing/Anthropic's Mythos model discovered thousands of zero-day vulnerabilities -- including a 27-year-old flaw in one of the most security-hardened systems on earth. It's so capable they refused to release it.Thu, 09 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_quantum_computing_ai/https://reliabledataengineering.com/posts/article_quantum_computing_ai/Most people have filed quantum computing under 'interesting but distant.' That instinct is understandable and increasingly wrong. The relationship between quantum hardware and AI is already happening -- on both sides.Thu, 09 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_vibe_coding_vibe_reviewing/https://reliabledataengineering.com/posts/article_vibe_coding_vibe_reviewing/AI can write the code. The problem is the person approving it -- working with an atrophying skill set, a backlog that doubles every quarter, and a mounting suspicion they can't tell if what they're merging is safe.Thu, 09 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_managed_agents/https://reliabledataengineering.com/posts/article_claude_managed_agents/Claude Managed Agents enters public beta — a fully managed infrastructure layer that handles the months of scaffolding work that used to block every production agent deployment.Wed, 08 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_usage_limits_tips/https://reliabledataengineering.com/posts/article_claude_usage_limits_tips/Most people blame Claude when they hit the wall. The real culprit is how they're using it. Tokens aren't counted per message — they're counted per token.Tue, 07 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_oh_my_mermaid_architecture_diagrams/https://reliabledataengineering.com/posts/article_oh_my_mermaid_architecture_diagrams/This open-source Claude Code plugin generates living architecture diagrams committed to git, drillable, and kept fresh by AI.Tue, 07 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_career_ops_ai_job_search/https://reliabledataengineering.com/posts/article_career_ops_ai_job_search/Career-Ops: an open-source multi-agent system built on Claude Code that evaluated 740+ job offers, generated 354 tailored CVs, and landed its creator a Head of Applied AI role. Now on GitHub.Mon, 06 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_gemma_4_local_setup_guide/https://reliabledataengineering.com/posts/article_gemma_4_local_setup_guide/Hardware-specific guide to running Gemma 4 locally: which model fits your Mac/GPU, Ollama vs MLX, Apple Silicon memory tuning, real tok/s numbers, and troubleshooting the things that actually break.Mon, 06 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_autoagent_self_engineering/https://reliabledataengineering.com/posts/article_autoagent_self_engineering/AutoAgent autonomously builds and optimizes agent harnesses without human engineering, achieving #1 on SpreadsheetBench (96.5%) and top GPT-5 score on TerminalBench (55.1%) in 24-hour runs.Sun, 05 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_gemma_4_local/https://reliabledataengineering.com/posts/article_gemma_4_local/Google DeepMind's Gemma 4 brings frontier-level reasoning to local hardware under Apache 2.0: 89.2% AIME, 80% LiveCodeBench, runs on phones to Mac minis, with native function calling and 256K context.Sun, 05 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_code_source_leak/https://reliabledataengineering.com/posts/article_claude_code_source_leak/Complete incident analysis of the March 31, 2026 Claude Code npm source leak, the coincidental axios supply chain attack, and what it means for developers and Anthropic's security posture.Sat, 04 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_karpathy_llm_knowledge_base/https://reliabledataengineering.com/posts/article_karpathy_llm_knowledge_base/Andrej Karpathy's LLM-powered personal knowledge base workflow: how he uses AI to compile, maintain, and query a 400K-word research wiki without vector databases or RAG.Sat, 04 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_anthropic_harness_design/https://reliabledataengineering.com/posts/article_anthropic_harness_design/A solo agent costs $9 and ships broken software. A three-agent harness costs $200 and builds a retro game maker from one sentence. Here's how the engineering actually works.Thu, 02 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_rag_pipeline_failures/https://reliabledataengineering.com/posts/article_rag_pipeline_failures/80% of RAG failures trace to chunking decisions. Your retrieval returns results, your LLM generates answers, and your users get confident nonsense.Thu, 02 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_ai_agents_data_stack/https://reliabledataengineering.com/posts/article_ai_agents_data_stack/DuckDB has an MCP server. Databricks bakes LLM functions into ETL. AI agents are becoming the most demanding query clients your infrastructure has ever seen.Wed, 01 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_ducklake_open_table_format/https://reliabledataengineering.com/posts/article_ducklake_open_table_format/DuckDB's new open table format ditches files-on-files metadata and replaces it with a SQL database. One query resolves everything.Wed, 01 Apr 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_mirofish_multi_agent_simulation/https://reliabledataengineering.com/posts/article_mirofish_multi_agent_simulation/MiroFish spawns thousands of AI agents with memories, personalities, and opinions, then watches what breaks loose — 45k GitHub stars and counting.Tue, 31 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_turboquant_google_kv_cache_compression/https://reliabledataengineering.com/posts/article_turboquant_google_kv_cache_compression/Shrink your LLM's memory footprint by 6x, speed up attention by 8x, and lose almost nothing in accuracy — no retraining required.Tue, 31 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_10_research_papers_ai_engineer_interview/https://reliabledataengineering.com/posts/article_10_research_papers_ai_engineer_interview/The ten papers that actually come up in AI engineering interviews — what each one says, why it matters, and the exact questions interviewers ask about them.Sun, 29 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_mythos_anthropic_leak/https://reliabledataengineering.com/posts/article_claude_mythos_anthropic_leak/A misconfigured CMS exposed Claude Mythos, Anthropic's most powerful AI model ever built. Three thousand files. A new model tier. And a cybersecurity panic that moved markets.Sun, 29 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_subconscious_persistent_memory/https://reliabledataengineering.com/posts/article_claude_subconscious_persistent_memory/A background agent that runs silently after every Claude Code response, building and surfacing context across sessions without adding latency to your workflow.Fri, 27 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_vectorless_rag_pageindex/https://reliabledataengineering.com/posts/article_vectorless_rag_pageindex/PageIndex turns documents into navigable trees. An LLM reasons through the hierarchy to find answers — no embeddings, no similarity search, just structured retrieval.Fri, 27 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_apple_neural_engine_training/https://reliabledataengineering.com/posts/article_apple_neural_engine_training/Apple locked down the ANE for inference only. A weekend project cracked it open for training. The results are real, the limitations are stated up front, and Apple probably isn't thrilled.Wed, 25 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_clawwork_ai_agent_benchmark/https://reliabledataengineering.com/posts/article_clawwork_ai_agent_benchmark/ClawWork dropped 220 professional tasks across 44 job categories, gave AI agents $10 each, and told them to survive. One agent turned that into nearly twenty grand.Wed, 25 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_context_engineering_ai_agents/https://reliabledataengineering.com/posts/article_context_engineering_ai_agents/Context Hub, Code Review Graph, and the emerging discipline of giving AI agents less to make them smarter.Tue, 24 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_databricks_agent_bricks_data_engineering/https://reliabledataengineering.com/posts/article_databricks_agent_bricks_data_engineering/Describe the task. Connect your data. Let the platform handle the rest. That is the promise of Agent Bricks — and for a specific, important set of data engineering problems, it is actually delivering on it.Tue, 24 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_our_2m_data_lakehouse_is_just_postgres_with_extra_/https://reliabledataengineering.com/posts/article_our_2m_data_lakehouse_is_just_postgres_with_extra_/“We spent two years building what marketing calls the future of data architecture. It is a database with more vendors.”Tue, 24 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_f3_the_future-proof_file_format_that_finally_gets_/https://reliabledataengineering.com/posts/article_f3_the_future-proof_file_format_that_finally_gets_/Why the open-source data world is buzzing about CMU’s new columnar format — and why Parquet’s decade-long reign might actually be endingMon, 23 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_the_database_endgame_why_everything_youre_building/https://reliabledataengineering.com/posts/article_the_database_endgame_why_everything_youre_building/A controversial thesis on why ETL, data warehouses, and the entire modern data stack are about to become as obsolete as floppy disks — and what’s coming to replace themMon, 23 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_autoresearch/https://reliabledataengineering.com/posts/article_autoresearch/AutoResearch gives an AI agent one file, one GPU, and one metric. The agent modifies the code, trains for 5 minutes, checks if it improved, and repeats all night long. The results are surprisingly good.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_code/https://reliabledataengineering.com/posts/article_claude_code/Anthropic's agentic CLI reads your codebase, edits files, runs commands, and commits changes. No IDE plugin. No web UI. Just a terminal that understands what you're building.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_cli_anything/https://reliabledataengineering.com/posts/article_cli_anything/One plugin scans a desktop app's source code and generates a complete command-line interface for it, so AI agents can use software that was built for humans.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_gitnexus/https://reliabledataengineering.com/posts/article_gitnexus/AI coding agents are blind — they read files but don't see structure. A 16K-star open-source project is changing that by building knowledge graphs that make agents actually understand codebases.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_nvidia_ai_models/https://reliabledataengineering.com/posts/article_nvidia_ai_models/There's a page on developer.nvidia.com that lists every major open model, with optimized containers, tutorials, and deployment guides for each one. It's the best-organized AI resource nobody talks about.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_openclaw/https://reliabledataengineering.com/posts/article_openclaw/A lobster-themed open-source project just became the fastest-growing AI repository in GitHub history. It turns WhatsApp, Telegram, and Slack into an operating system. Here's why Jensen Huang compared it to a computer — and what people are actually doing with itSun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_toon_sql_migration/https://reliabledataengineering.com/posts/article_toon_sql_migration/Feeding 200K-character SQL files to an LLM is expensive and unreliable. We built TOON — a compact AST notation that gives the model structural awareness at a fraction of the token cost.Sun, 22 Mar 2026 00:00:00 GMThttps://reliabledataengineering.com/posts/article_claude_certified_architect/https://reliabledataengineering.com/posts/article_claude_certified_architect/Anthropic launched its first official technical credential -- a proctored, architecture-level exam that separates people who use AI from people who build production systems with it.Wed, 18 Mar 2026 00:00:00 GMT