Duarte O.Carmo's articles

Duarte O.Carmo

A podcast version of my personal website. All the episodes are generated from a text to speech model.

  1. 2 APR

    #65 Retrospectiva #6

    Marking my 100th post from an airplane seat, I share a new-format roundup of tools, reads, listens, and watches that shaped my month. I dig into Pi.dev as my main agent harness, lean on Codex for low-risk tasks, and highlight Hevy and Snapseed, plus books on AI and inference engineering, practical research resources, and a few standout tracks, podcasts, and videos. Also, I’ll be at AI Engineer London next week—say hi if you’re there. Relevant links: Original article AI Engineer London Pi.dev Talk on using Pi Agent skills collection Agent extensions Agent theme Agent harness article Local models config Codex Hevy Running dashboard Snapseed Photos Darkroom Empire of AI — Karen Hao Inference Engineering — Philip Kiely Goodbye Kindle (Palma) An unsolicited guide to good research — Eugene Vinitsky (PDF) How Kimi, Cursor, and Chrome Train Agentic Models with RL — Phil Schmid The Roving — Bonny Light Horseman Reverie — Jule (SoundCloud mix) Decoder: Confronting the CEO of the AI Company that impersonated me Rich Roll: The Handyman of High Art — Tom Sachs Everything We Got Wrong About Research-Plan-Implement Living in the Matrix — Casey Neistat

  2. 24 MAR

    #64 An opinionated running dashboard

    As you get older, life becomes complicated. Not in a bad way. There’s just more going on. We don’t all want to run marathons. Maybe you want to run a parkrun. Maybe you want to gradually increase your volume. Maybe you don't want to run at all. Whatever …

  3. 8 MAR

    #63 Portuguese variety identification: The bitter lesson

    Given some text in Portuguese, how easy is it to determine if it's from Brazil or Portugal1? For native speakers, this is pretty easy – it's almost a feeling. But for machines: not so much. This might seem like a useless problem at first. But in the age of language …

  4. 28 FEB

    #62 Retrospectiva #5

    Happy February! Just like that, we are close to wrapping up the first quarter of 2026. After quite some time roaming around, we finally flew back home to Copenhagen. It's cold, windy, and grey, but it's also calm, organized, and cozy. Most of all: it's home. Another good thing about …

  5. 22 FEB

    #61 Bagaço: A pretraining dataset for European Portuguese

    Let's say your goal is to train a Large Language Model only on European Portuguese. Where do you start? What datasets are out there? What websites are being scraped for the large black box? Bagaço - named after the popular Portuguese moonshine - is a small step in that direction. In June …

  6. 27 JAN

    #60 Retrospectiva #4

    Well—that was quick. Just like that, the first month of the year is gone. Winter blues would normally peak around this time. But not this year. We're spending time with family in my favorite place on Earth, somewhere along the Adriatic coast of Italy, in the Marche region. It's …

  7. 22 JAN

    #59 How to police your agents

    Let's face it. It might just be the year of agents. If you work in tech and your workflow hasn't changed in the last year or so - you're probably doing something wrong. For those of you who have. It's fun. We're building more than ever before! But there's a dark …

  8. 4 JAN

    #58 Limpa: Ad-Free podcasts powered by LLMs

    I get up feeling sleepy. I lace up my running shoes and head out the door. I fire up my favourite podcast. "This show is brought to you by..." I hate ads. I understand the attention economy. Companies are capitalizing more and more on everyone's time. I have nothing against …

See All (25)

About

A podcast version of my personal website. All the episodes are generated from a text to speech model.

Information