YYash Singh·19h agoBuilding BPE from Scratch: How a Tokenizer Learns Its VocabularyBuilding a Transformer from Scratch, Part 223 min read·yashksingh.hashnode.dev
JJeff Schomay·Nov 11Replacing my game engine with a neural netHow I trained an AI model to predict next game frames to play my game inside a neural net8 min read·blog.jeffschomay.com2
PPelloran·Nov 9Why Temperature 0 Does Not Make LLM Inference DeterministicSampling determinism is not the same as computational determinism.4 min read·pelloran.hashnode.dev
DDaniel Powley·Nov 6The A-Z Weekly Wrap: 6th November 2026Latest Azure platform updates for the 6th November 2026, covering key announcements across networking, security, compute, databases, and AI5 min read·blog.atozazure.com12S
SShakil Ahmed·Nov 2I possessed an LLM by editing its hidden layers, then exorcised itActivation steering on Qwen 2.5 7B, an exorcist that doesn't need to know the dose, and the day my model graded itself too kindly5 min read·build-mcp-with-ai.hashnode.dev
AAjay Kasi·Oct 24Your Forecast Says 90% Confidence. But Does It Actually Deliver?Your Forecast Says 90% Confidence. But Does It Actually Deliver? Conformal Prediction Explained with Python, Time-Series Forecasting, and Four Experiments What happens when a model promises 90% covera18 min read·ajaykasi.hashnode.dev
MMolly Sohaney·Oct 19CTF Writeup: After Hours | AI/ML Security | CSS CTF 2026: Return of NexusDescription It's past midnight at Northstar Tower. You have no staff badge, no appointment, and absolutely no business being in the server room. Between you and the door stands Morgan, the building's4 min read·mollysohaney.hashnode.dev
GGeorge Ezejiofor·Oct 17Brownfield Kubeflow on RKE2: Swapping Dex & SeaweedFS for Keycloak & Ceph RGWUpstream Kubeflow assumes a greenfield cluster and ships its own Dex, SeaweedFS and MySQL, with its own oauth2-proxy in front. My homelab already had better versions of most of those. This is the brow50 min read·georgeezejiofor.com2Y
SSahil Shaikh·Oct 15AI/ML for Developers: Demystifying Embeddings and Vector SearchHow to move beyond basic keyword matching and build intelligent semantic and visual search into your applications.7 min read·sahilshaikh.hashnode.dev1
FFeroan Mothy·Oct 6Why Does Machine Learning Need So Much Math?A look at the math behind machine learning, from vectors and matrices to calculus, probability and why each actually matters when building models14 min read·feroan.hashnode.dev