Agents and LLMs with judgment
39 posts on LLMs and 30 on agents: sandboxes, guardrails, cost per task, and running your own benchmarks instead of trusting screenshots.
Recommended reads
View moreApache Spark won't melt down when your data doesn't fit in RAM anymore
Apache Spark has been the de facto standard for processing data at scale for over a decade. We go over why it's still alive, how it works under the hood, and when you should NOT use it.
Oct 08 2026 · 5′ · Experiments · java · big data
Mem0 Doesn't Fix an Unbounded Agent, It Complements It
I designed a small experiment to see if Mem0 reduces context bloat in long Cline sessions. Short answer: it helps with repetition, it doesn't replace limiting the agent's scope.
Sep 27 2026 · 8′ · Tutorials · agentes-ia · cline
Claude API Key Security: Why .env Is Not Optional
Pasting a Claude or DeepSeek API key straight into your code "just to test it quick" leaves a trail in your git history and your logs. A no-nonsense guide to environment variables, rotation, and what to check before sharing a repo.
Sep 09 2026 · 7′ · Tutorials · nextjs · anthropic
Sniffnet and AI agents: a measurement protocol still to run
A proposed method for observing network traffic during an AI agent task. No measured results or automatic attribution to individual processes.
Sep 07 2026 · 2′ · Tutorials · agentes-ia · networking
DeepSeek Reasonix: A Technical Read on a Native Coding Agent with Aggressive Caching
DeepSeek Reasonix shows up as a native coding agent with aggressive caching and low cost. Before you adopt it or dismiss it, there's a more useful question: what specific problem does it actually solve in a real stack, and what reproducible experiment confirms that?
Sep 03 2026 · 9′ · Opinion · LLM · ia
Noroboto: Lying Fonts and Rust Mitigation — A Technical Read Without the Hype
Fonts lie. Noroboto documents how the text subsystem can return incorrect metrics and proposes mitigations in Rust. Before you copy it into production, you need to understand what problem it actually solves, where the common recipe breaks down, and what reproducible experiment is actually worth runn
Aug 17 2026 · 8′ · Opinion · linux · sistemas