News
How Transformers Work Inside an LLM (Step by Step)
41+ min ago (261+ words) The full LLM pipeline looks like this: " The Transformer is the brain of the LLM " All context understanding and relationship modeling happens here LLMs don't process words'they process tokens. Each token is converted into a numerical vector: This is a…...
I Built an Adaptive AI Feedback Platform with Gemini 3 in a Weekend
1+ hour, 2+ min ago (473+ words) What if a questionnaire could learn what to ask? I built Dyadem for the Gemini 3 Hackathon to find out. Questionnaires are notoriously tricky to develop. Community outreach relies heavily on focus groups because simple surveys often miss the point. There's…...
What Existed Before Transformers and Why Responses Are Generated Step by Step
1+ hour, 42+ min ago (415+ words) Large Language Models (LLMs) like ChatGPT feel almost magical'but under the hood, they are built on clear mathematical and architectural principles. In this article, we'll break down how LLMs actually work, why models like ChatGPT weren't possible before Transformers, and…...
Learning Tech as an Intern
9+ hour, 31+ min ago (134+ words) This blog is basically my tech notebook. I write about what I'm learning, what I'm working on. Most of it comes from my day-to-day work with code, projects I build. I'm learning in public and sharing the journey as it…...
Evidence Briefing – Monólito vs Microsserviços
14+ hour, 43+ min ago (1248+ words) Diante desse contexto, este trabalho tem como objetivo analisar e sintetizar evid'ncias existentes sobre arquiteturas monol'ticas e de microsservi'os, buscando responder "s seguintes quest'es: Em seguida, foi conduzida uma busca automatizada no IEEE, utilizando uma string de busca definida a…...
IA, carreira e ansiedade
23+ hour, 17+ min ago (761+ words) As coisas est'o mudando muito r'pido o tempo todo. Tenho a sensa'o de que quem est' se saindo melhor " justamente quem consegue fluir de acordo com essas mudanas. Eu " como engenheira de software j'nior " me sinto no meio do furac'o....
Learning about WCAG Compliance
1+ day, 6+ hour ago (206+ words) In my entire carrier it was very rare situation when WCAG Compliance was a serious topic. Few years ago nobody care about it (my experience). Today it almost standard for serious pages and "must have". I decided to learn more…...
Why I Built Locademy: A Local-First Video Learning Hub
1+ day, 18+ hour ago (405+ words) I have a confession: my "Downloads" folder is a graveyard of tutorial series, conference talks, and screen recordings. Navigating through nested folders to find the next video in a sequence is a friction point that often kills my motivation to…...
Why I Close Your Portfolio After 10 Seconds (And How to Keep Me Reading)
2+ day, 2+ hour ago (450+ words) I recently reviewed 50 junior developer portfolios for a role. I rejected 45 of them in less than a minute. It wasn't because the code was bad. (I didn't even look at the code yet). It was because the projects were generic....
Quincy Larson’s freeCodeCamp updates are invaluable. This week: Harvard CS50 2026, a free CS course, now on their YouTube channel:
2+ day, 9+ hour ago (48+ words) ... Tagged with computerscience, learning, news, resources. Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the…...