Duarte

Trying to understand what are good open Jevs. WTF is going on with benchmarks this days??? LESS IS MORE GUYS!! LESS IS MOREEEEEEE

There is just something about the Cursor (now X AI or whatever) team and how they design interfaces. Cursor Agent Pane and Grok Bot are just incredibly designed. Just the right amount of knobs! In the age of slopped interfaces, its refreshing to see a team do LESS!

You find a bug in a famous benchmark. Do you fix it and run it in the fixed version? Do you leave it as it for comparable results? I hate benchmarks

Until today my connectors were a mess. Hermes uses this cli in my VM, pi uses the mcp for that there, codex has the integration here, gws cli for some email accounts there. A mess. Now I just use @executorsh. 100% recommend.

People of pi - what do you do when you want it to run every 2 hours or check something 30 mins from now?

My danish accounting software has an official mcp and it's nuts. mcp.dinero.dk/

Replaced 4 mac menu bar apps with @vorssaint @SnazzyLabs mac app videos are gold

I'm so happy I bought that refurbished Hetzner server with 64GB of RAM for 30 EUR/month. It runs pretty much everything at this point.

Useful loop tip #23 Have hermes go through a busy repo from last week, make a summary, and drop the markdown in your NextCloud server so you can go through it at your own pace

80 EUR running strollers, vision language models, reinforcement learning, RSI, and dealing with becoming a father. This is Retrospectiva #12 - it's been a year of writing this! duarteocarmo.com/blog/retros...

Suspense is killing me

Used codex app for a day. Can solve Navier-Stokes but oh lord is this app buggy. Back to herdr 🐑.

The more you press "I don't like" Russ songs on Spotify - they always come back to haunt you in your Discover playlist.

Wonderful two days for Denmark. CPR? Hacked. DTU? Hacked as well? Is this a different attack? JESUS.

LLM as a judge is a great idea!

I decided to give Cursor another try today. I like this ngl

Had to use cursor today (sshing into hpc - and wanted to get an idea of files, directories, etc) One thing Cursor still nails is the review pane. Lazygit and hunk are good - but this is better.

I hate you 😂

Am I the only one that is excited about this bad boy for local use? 9B - distilled from the #1 open weight model at the moment :) huggingface.co/ggml-org/Mi...

That's what i thought

Increasingly telling models that do "long horizon tasks"

You use @herdrdev + pi - but sometimes the agent asks you a question and herdr does not show it as blocked github.com/duarteocarm...

Invoice dataset is so useful that all the invoices look the same 😂

Learning my new split keyboard is a pain. Send help and your best tips please. This is hell ahahah

I prefer deepseek v4 flash over pretty much any glm model. @Sentdex you have seen something I have not 😂

The best thing about LLMs gotten this good is that I can focus on the writing and it will handle all the other bs for me Converting images, generating thumbnails, adding links, animations, visuals ALL THAT BS!!!! (yes it gets the link wrong sometimes, but I catch the mf)

Cargo bikes, android e-reader tablets, ai-generated text classification and generating great landing pages with LLMs! This month's Retrospectiva is out! duarteocarmo.com/blog/retros...

If I can run 3 deepseek flash sessions in the same time astra is thinking about a single prompt - does this mean I cancel codex? jk

Building a slide deck today. AGI is here, but I still prefer powerpoint. -> Move logo here -> gray it out -> wtf is this font -> add this image I think it's faster if I just do it myself 😂

I have to compare two models on a benchmark. Which temp? Which max_tokens? Which top_p setting? Everywhere I look I see "we use the lab recommendation". Ok, so this is the wild west I see.

I think Casey was right. You can def. replace sleep hours with run hours.

Evals are hard I admit.

2024: Use parcel tracking apps 2026: "Check on <tracking_code> and let me know when something changes" Hermes I ❤️ you.

Hiking in the dolomites with an 8 month old, replacing Tmux with herdr, the Laguna technical report, and Tierra Whack. Last month's Retrospectiva is out. duarteocarmo.com/blog/retros...

.@spotify - explain to me why russ is always on my discover playlists? Even though I've clicked hide this multiple times?

Sick home with the flu. GLM-5.2, Scaling Laws, World Cup, and Western States duarteocarmo.com/blog/retros...

It's crazy to me how I just use Matplotlib now to look for flights. But that's just the tip of the iceberg. Here's how I use Saramago, my Hermes Agent duarteocarmo.com/blog/how-i-...

A hectic month. Copenhagen Marathon, TranslateGemma, Hoka Hopara, Deep Learning for Biology, and Sakamoto. duarteocarmo.com/blog/retros...

6 months ago I wrote a blog post saying TTS still sucked. The tables are starting to turn. Here's a quick post about options - actual options. duarteocarmo.com/blog/tts-do...

Announcing the second version of Bagaço. 37GB of European Portuguese text. 33 million documents, ~9.3 BILLION tokens. Completely open 😉 duarteocarmo.com/blog/the-la...