Newsletter
The architecture corner newsletter is a bi-weekly publication that provides you with a list of relevant curated articles, videos on software architecture, design and development.
Understanding Why Jev Won't Replace All Your AI Needs
In Jev We Trust (But Should We?)In a market that sees versions of LLM models being announced every two weeks, a new contender usually means it is a bit better / cheaper than its predecessor in a given benchmark.Then comes Jev, which claims to be 200x faster and 400x cheaper than traditional LLMs.…
HTTP Integrity: Can You Trust What You Receive?
RTK increases token usage instead of reducing itAs the industry shifts from TokenMaxxing to TokenMining, several approaches have appeared to offer significant reductions. One of these is Rust Token Killer (RTK), with advertised reductions varying from 60 to 90%!To understand why it would provide…
The Illusion of Safety: Auto Mode vs Prompt Injection
The History of Postgres ShardingAs your application grows, whether it’s a SaaS or not, talking about sharding is bound to happen.This article provides an interesting presentation about how this topic evolved, specifically for the Postgres ecosystem.I could relate to it thanks to my experience with…
Open Knowledge Format to Manage Your AI Context
Understanding Open Knowledge Format Value PropositionFoundation models keep being released at a neck-breaking cadence. Each release improves, even if marginally, on the previous version’s benchmark results.The result: stronger models with capabilities for longer and longer sessions. Yet, they are…
Evolving Spec-Driven Development
Structured Prompt Driven DevelopmentAI-assisted development speeds up the code development task, with individuals being able to create and refactor code much faster than the traditional approach. And while we know that typing (coding) is not the only part involved in the SDLC, it is easy to get…
The Marginal Cost of Correctness in the AI Era
DeepSeek cut prices 75%. The 100x problem remainsThe focus on managing AI-related costs has increased, and it finds an interesting landscape:Anthropic newer models (Opus 4.8, Sonnet 5) generate more tokens than their predecessorsOpenAI claims their newer models are more token-efficientChinese…
Token Inflation is Real
Client-Side Load Balancing at a Million Requests Per SecondLoad balancing is a standard approach used for both high-availability and scalability, allowing the traffic to be distributed among a fleet of services (application/persistence).The “traditional” approach is to implement this at the serving…
What Loop Engineering Actually Requires
Loop EngineeringWe truly are living through strange times. Not too long ago, we were talking about prompt engineering, context engineering, and just as I was about to write about harness engineering, I stumbled across the new kid in town: loop engineering. That is a lot of engineering in so little…
Domain Knowledge Is the New Force Multiplier
This Substack is reader-supported. To receive new posts and support my work, consider becoming a free or paid subscriber.Whether you are using Microservices or a modular monolith, getting the boundaries right is key to leveraging the benefits those architectural choices are meant to bring. Yet, it…
Learnings From Being Part of Project Glasswing
Anthropic drew equal parts fear and frustration when it announced it would not release its Mythos model because it could autonomously uncover security vulnerabilities and create exploits.Cloudflare was one of the companies invited to join Project Glasswing and to access a preview of the new model.…