Featured post what's this? ✨ Dharmateja Samudrala Software Engineer — building things on the internet.
It's OK to Use Coding Assistance Tools To Revive The Projects You Never Were Going To Finish I tried to use Claude Code with Opus 4.6 to implement a connector between Youtube Music and opensubsonic. The end result was a fairly short amount of time to get a working project.
Making the Rails Default Job Queue Fiber-Based I tried Async::Job for my LLM apps, hit its limits, and patched Solid Queue to run jobs as fibers instead.
congrats on failing to launch; weirdfriends log 1 7 months, 221 commits, and I still haven’t told anyone to try my app. A reflection on what went wrong.
Context Is Finite. Who Maintains It? Context in LLM systems is finite. Today, developers maintain it. What happens if the agent learns from its work and takes on part of that responsibility?
Naming Things Is Easy Now “There are only two hard things in Computer Science: cache invalidation and naming things.” - Phil Karlton I don't think naming things is hard anymore (cache invalidation is about the same)....
GPT-5.5 is a biased evaluator: authorship and order effects - Guillaume Valmont's Weblog While comparing medium, high, and extra-high reasoning modes on the same task, I uncovered consistent authorship and presentation-order effects in GPT-5.5’s evaluations.
From $200 to $30: Five Layers of LLM Cost Optimization A walkthrough of how I cut an LLM-based product classifier's token usage by ~92% through compression, two-stage prompting, exact-match lookups, similarity caching, and batching.
The Satisfaction of a ChatGPT Plan The goal of AI providers isn't to impart you with knowledge. It's to keep you entertained while they expose you to ads and spend your tokens. Use it wisely.
quantumslop/URANDOM_DEMO.md at 25ad2e76ae58baa96f6219742459407db9dd17f5 · yuvadm/quantumslop This repository contains the code and submission detail for the QDay prize challenge by https://www.projecteleven.com/ - yuvadm/quantumslop
There Will Be a Scientific Theory of Deep Learning In this paper, we make the case that a scientific theory of deep learning is emerging. By this we mean a theory which characterizes important properties and statistics of the training process, hidden representations, final weights, and performance of neur...
