W
Jul 19, 2026What Fixed Our Model Latency During a High-Traffic Deploy (Production Case Study)
On 2026-03-14, during a high-traffic deploy of our consumer chat product, the moderation and reply...
Jul 19, 20265 min read0 reactions0 comments
Back to articles
Tag archive
#claude35haiku
W
Jul 16, 2026Why Do Powerful AI Models Suddenly Fail in Real Use - and What Actually Fixes It?
Many teams ship a capable model into production and watch it degrade under real traffic, unexpected...
Jul 16, 20265 min read0 reactions0 comments
W
Jul 14, 2026Why modern AI models fail to stay reliable at scale - and what to do about it
The problem is simple: sophisticated AI models promise consistent intelligence, but in real systems...
Jul 14, 20265 min read0 reactions0 comments
H
Jul 12, 2026How to Understand and Choose AI Models: A Guided Journey for Builders
During a January 2025 refactor of an analytics pipeline that served real-time recommendations, the...
Jul 12, 20265 min read0 reactions0 comments
W
Jul 11, 2026Why Model Choice Is Becoming the Product Decision
Then vs. Now: a short observation The conversation used to be simple: bigger models meant...
Jul 11, 20265 min read0 reactions0 comments
W
Jul 10, 2026When the "Shiny Model" Breaks Production: A Reverse Guide to Costly AI Mistakes
On March 12, 2024, during a migration of a customer-facing search agent for a mid-size fintech, a...
Jul 10, 20265 min read0 reactions0 comments