KSKanishka Shashiinnodej.hashnode.dev·20h ago · 10 min readModern Database Access: Prisma, Drizzle, and ORMs ExplainedWhere Does Application Data Live After a User Closes the App? Imagine you're using an e-commerce application. You create an account, add products to your cart, place an order, and close the app. The n00
SSangharshainnoob6t5.hashnode.dev·Jun 11 · 4 min readPickle Deserialization RCE via Model Upload EndpointLink: https://www.ratctf.com/challenges/synapse-lab This challenge revolves around a classic but still heavily abused primitive: unsafe Python pickle deserialization exposed through a model upload API00
KMKartik Mehtainwriter.mrmehta.in·Jun 5 · 8 min readAgent = Model + HarnessIf you have ever called an LLM API, you already know the basic shape of it. You send some text, you get some text back, and the connection closes. That is a model. It is good at producing language, bu00
KMKartik Mehtainwriter.mrmehta.in·Jun 5 · 8 min readLetting Agents Run, SafelyPart three of a series on agent harnesses. Part one introduced the model-plus-harness idea, and part two split work across subagents. This piece is about the layer where agents stop just talking and s00
KMKartik Mehtainwriter.mrmehta.in·Jun 5 · 7 min readOne Agent Is Not Always EnoughPart two of a series on agent harnesses. If you have not read part one, it introduces the idea that an agent is a model plus the harness around it. This piece builds on that, so a quick skim first wil00
AAArjun Adhikariinblogs.thearjun.com·Jun 2 · 11 min readHow Temperature, Top‑K, and Top‑P Control LLM Output — A Practical GuideWhen an LLM generates text, it isn't thinking in sentences. It computes a massive list of raw scores (logits) for its entire vocabulary, converts them into a probability distribution, and selects the 00
Gguanjiaweiinguanjiawei.hashnode.dev·May 1 · 9 min readDeepSeek V4 Day: It's About Infra, Not the ModelThe AI industry feels like New Year's today. OpenAI dropped GPT-5.5 in the morning, and DeepSeek V4 went live in the afternoon. Add DeepMind's Vision Banana from a couple of days ago, plus Haoyu Cai's Anuttacon paper on digital humans. This week has ...00
SRStephane Royinflexai.hashnode.dev·Apr 27 · 5 min readHow to Benchmark Open-Source Models Before You CommitYou're choosing between Llama 4 Scout 17B, GPT-OSS 120B, and DeepSeek V3.2. The paper numbers look fine across all three. You pick the one that feels right and ship it. Three weeks later it fails on t00
ARAshikur Rahmaninashik1000.hashnode.dev·Apr 3 · 7 min readWhat Is a Neural Network — And How Does It Actually Think?100 million. That is how many spam emails Gmail filters every single day. No human is sitting there hitting "delete." A machine is making those calls in the blink of an eye. If you’ve ever wondered wh23A
KSKreeti Sharmainkreeti1210.hashnode.dev·Apr 3 · 5 min readHow can we make our RAGs Better?Ever wondered how we can calculate the success metrics of RAGs model? How we enhance the model and on which parameters especially when we have so many models? Most frequent metrics that can come to ou00
