Latest Articles
698 posts from Alex's blogs and newsletters, newest first. Thoughts on tech, data, policy, and philosophy.
How to Build a Golden-Question Benchmark for Your Data Agents
Build a golden-question benchmark for data agents: frozen Iceberg tags, execution-based scoring with Arrow, and CI gates....
When a Data Agent Gives a Wrong Number: Incident Response for Agentic Analytics
A plan for when a data agent gives a wrong number: severity levels, containment, Iceberg time travel reproduction, and blast radius queries....
Multi-Tenant Data Agents: Serving Many Customers From One Lakehouse
Serve many customers from one lakehouse without leaking between them: isolation models, Polaris grants, and tenant-scoped agent state....
Release Management for Data Agents: Shipping Prompts, Tools, Models, and Metrics Without Breaking Answers
Ship prompts, tools, models, and metric changes without breaking answers: agent manifests, shadow mode, canaries, and rollback....
Semantic Caching for Data Agents Without Serving Stale or Leaked Numbers
Cache data agent results safely with canonical query keys, Iceberg snapshot freshness checks, and permission-aware cache keys....
Small Language Models for Data Agents: Where They Win and Where They Fail
Where small language models win inside a data agent and where they fail, plus a routing architecture that escalates only when needed....
Apache Data Lakehouse Weekly: September 23 to 30, 2026
Apache Data Lakehouse Weekly: September 23 to 30, 2026
Sonnet, GPT Sol and a Shelved Astra - AI Weekly September 23 to 30, 2026
Two labs shipped their mid-tier workhorse models one day apart, and both landed at $2 per million input tokens and $10 per million output....
Sonnet, GPT Sol and a Shelved Astra — AI Weekly September 23 to 30, 2026
Social Security: The Retirement Promise That Was Never Kept
TL;DR Social Security is facing a documented, actuarially certain fiscal shortfall....
Turning an Analytics Question Into a Verified Agentic Graph
A complete AGS 1.0 graph for governed metric questions, with verification gates, deterministic check scripts, and reconciliation against a semantic la...
Keeping Audit Snapshots Alive While Iceberg Snapshot Expiration Runs Every Night
How Iceberg snapshot tags keep audit snapshots alive through nightly expiration: retention calendars, RETAIN semantics, compaction cost, and erasure c...
Twelve Queries That Pass Every Schema Check and Still Return the Wrong Number
Twelve query patterns that pass schema validation and still return wrong numbers, with detectors, required metadata, and tested code for each....
Apache Data Lakehouse Weekly: September 15 to 23, 2026
Release managers ran the show this week, and license files kept tripping them....
Apache Data Lakehouse Weekly: September 15 to 23, 2026
Release managers ran the show this week, and license files kept tripping them. Iceberg 1.12.0 went to a second release candidate after… Continue readi...
AI Weekly: Opus 5.5, GPT-6 Sol and Luna, and MCPA
Week of September 16 to 23, 2026...
AI Weekly: Opus 5.5, GPT-6 Sol and Luna, and MCPA
Week of September 16 to 23, 2026 Continue reading on Medium »...
The Drug War's Real Body Count: Fifty Years of Policy Failure
TL;DR The United States has spent over one trillion dollars and imprisoned millions of people in a fifty-year campaign to eliminate drug use....
Fast Classification Models, LLMs, and the Apache Iceberg Lakehouse
Fast Classification Models, LLMs, and the Apache Iceberg Lakehouse
Open the bill for any team that has put a large language model into a data pipeline and look at what the calls are doing....
Why the Iceberg DataFusion Integration Is Moving to Apache DataFusion
Why the Iceberg DataFusion integration moved to the DataFusion project, and what the split means for users, Comet, and iceberg-rust contributors....
What Iceberg v4's Proposed FILE Type Means for Multimodal Tables
Iceberg v4's proposed FILE type brings first-class media references to tables, via Parquet's FILE logical type, ranges, checksums, and pre-signed URLs...
Fast Classification Models, LLMs, and the Apache Iceberg Lakehouse
How fast classification models like Jev alongside open alternatives such as GLiClass compare with LLMs, and how to run both together inside an Apache ...