---
title: "George Sims (@george-sims) | Hashnode"
description: "Senior DevOps Engineer @ Bynder. Read the latest articles by George Sims on Hashnode."
url: "https://hashnode.com/@george-sims"
---

@george-sims

# George Sims

@george-sims · Barcelona, Spain · Joined February 2026

Senior DevOps Engineer @ Bynder

## Comments

[Hi Skillselion, using subagents is a small superpower in of itself when used correctly. Good observation too, as you pointed out there's a lot more being saved by the agent than suggested by this post. Also a fair point about skill hoarders, there's certainly a threshold of being detrimental rather than useful at scale. I think you will enjoy the next one, I will get deeper into the rabbit hole about context rot.. the research is quite dense so it's taking a bit longer, but stay tuned!](https://hashnode.com/posts/looking-through-claude-s-context-window/6a833d8ec3b7bb972b00d568/comment/6a84c99099a2ee3b0e855477#reply-6a85eb5c443b90a9b39f09e1)

Reply · Article · Aug 19 · [Looking Through Claude's Context Window](https://hashnode.com/posts/looking-through-claude-s-context-window/6a833d8ec3b7bb972b00d568)

[Thanks for your feedback Kartik, much appreciated. Indeed, as the input token count grows the model accuracy deteriorates quickly depending on how vague your prompt is. Hoping to show that in some more detail in my next post, stay tuned!](https://hashnode.com/posts/looking-through-claude-s-context-window/6a833d8ec3b7bb972b00d568/comment/6a84a1b24786a4a92afe84b6#reply-6a85e9834516adf5578e673f)

Reply · Article · Aug 19 · [Looking Through Claude's Context Window](https://hashnode.com/posts/looking-through-claude-s-context-window/6a833d8ec3b7bb972b00d568)

[Hi Amit, exactly, that's the real shift here. Once observability sits at the platform level instead of being something every team has to remember to add, it stops being a "did we remember" problem and just becomes enabled by default. The OpenTelemetry Collector is what makes that practical for something as varied as CI tooling: it's language-agnostic, so it doesn't matter what a team's workflow is written in, and receivers like the one this post covers mean a new telemetry source can be added without asking anyone to touch their own code. Teams can even contribute their own receiver to the OSS project if there's a source that doesn't exist yet.](https://hashnode.com/posts/distributed-tracing-for-ci-pipelines-without-touching-a-single-workflow-file/6a771f53e42cf22dee8376a1/comment/6a7bf836ad2d3766418d40d8#reply-6a7c25115552d33e3f72aa09)

Reply · Article · Aug 12 · 1 · [Distributed Tracing for CI Pipelines Without Touching a Single Workflow File](https://hashnode.com/posts/distributed-tracing-for-ci-pipelines-without-touching-a-single-workflow-file/6a771f53e42cf22dee8376a1)
