CCoda One38m ago · 5 min readA Detector Score Is a Classifier Output, Not a Verdict: Reading AI Detection Like an EngineerImagine a teacher sees a hypothetical "87% AI" on a student's essay. It reads like a measurement. It is not. It is the output of a classifier built on proxy features, with a threshold someone chose, ecodaone-ai.hashnode.dev
SScrapeMole47m ago · 4 min readGetting 200 top-level YouTube comments took 60 s and 1,346 rows with a DIY library, versus 4.5 s with an Actor (plus a transcript test)Maker disclosure: I build ScrapeMole, which publishes the YouTube Comments and Transcript Actors used below. The open-source libraries I compare against are good. This is where they differ, measured oscrapemole.hashnode.dev
NNishanthan Karunakaran6d ago · 7 min readHow Query, Key, and Value (QKV) Work in TransformersEvery Transformer-based language model, from BERT to GPT, relies on a mechanism called attention to determine how different tokens in a sequence relate to one another. At the heart of this mechanism anishanthan.hashnode.dev
WWord LegionOct 20 · 4 min readHow every word becomes a troop: turning a dictionary into game units with embeddings and an LLMWord Legion is a free browser game by Alexis Bonnafont: a real-time 1v1 duel where you spell words from letter tiles and each word spawns a unit. This post explains the pipeline behind it. It's writtewordlegion.hashnode.dev
DDetectGPTOct 17 · 5 min readChecking a Web Page for AI-Generated Text: Free URL-Based Detectors, ComparedMost AI detectors assume you have the text in your clipboard. In practice, a lot of the questions I get are about pages: a freelancer's published article, a competitor's landing page, a guest post thadetectgpt.hashnode.dev
PProofAIOct 15 · 6 min readHow AI Content Detectors Actually Work (and Why They Sometimes Get It Wrong)Every week someone asks us the same question: "How does an AI detector actually know?" Teachers ask it about essays, recruiters about cover letters, and developers about the content flowing through thproofai.hashnode.dev
JJacob Edgar-AndersonOct 12 · 20 min readJev handed our LLM the wrong page a tenth as often as our embeddingsHere's a question from our test set. A caller rings a multi-trade maintenance company. "Hi, I had a plumber round last week and there's a problem with what he did, it's still leaking. Who do I contacsayora.ai
LLibrarymindsOct 5 · 24 min readSemantic Search Over Transcripts in Python: What Embeddings Fix and What They Don'tShort answer: keyword search finds the words you typed, and vector search finds paragraphs that sit close to them in meaning. I built both in about 120 lines of Python, ran them on a made-up talk tran15KAlibraryminds.hashnode.dev
IIbrahim Kedir BedruOct 5 · 4 min readWhy our Amharic AI searches before it speaksHow we built Bini, an assistant that answers Ethiopians' everyday questions in Amharic, and what we learned about the real cost of the Ge'ez script. Ask a general-purpose AI assistant how much it cost2AIbinasmart.hashnode.dev
MMinaruzzaman ShovonOct 1 · 7 min readI Trained an Open Decision Model on a Free GPU in 46 Minutes. On My Tests, It Beat Laya.TYPIC answers typed questions in a single forward pass, with no text to parse. Here's how I built it, what worked, and where it still falls short. A lot of software now asks an AI model tiny questions1Aminarsvn.hashnode.dev
