Marco Rodrigues @dadhalfdev

50% parenting 👨‍🍼 50% building 💻 https://t.co/005ZU2BFFY blog.dadhalfdev.com Visit my newsletter → Joined September 2014

Tweets

1K
Followers

545
Following

481
Likes

1K

Marco Rodrigues @dadhalfdev

3 days ago

@NaithanJones That's great @NaithanJones , how scalable do you think Obsidian is has a second brain? Also how expensive are the crons, ingestion? I'm using Gbrain, and not only is it way more complex than it should be, it also burns a lot of credits.

0 0 1 34 0

View Details

Marco Rodrigues @dadhalfdev

3 days ago

I've never seen such bearish sentiment toward $ETH in the seven years I've been in crypto. Is this a buy signal, or is this asset going to zero this time?

0 0 1 47 0

View Details

Marco Rodrigues @dadhalfdev

4 days ago

Funny that one year ago, companies would use Looker Studio or Power BI to make PoC dashboards. Now it's way faster to just vibe-code production-grade dashboards instead. What used to be the time-consuming approach is now the faster solution (and better).

0 0 1 33 0

View Details

Marco Rodrigues @dadhalfdev

6 days ago

Microsoft just woke up 😅

0 0 0 19 0

View Details

Marco Rodrigues @dadhalfdev

6 days ago

@jpschroeder When Linux? And is it compatible with the Hermes Agent? 🙃

0 0 0 86 0

View Details

Marco Rodrigues @dadhalfdev

7 days ago

The new "Boards of Canada" album is giving me Hermes Agent vibes.

0 0 0 47 0

View Details

Marco Rodrigues @dadhalfdev

7 days ago

@surface Good. I will buy and install Fedora.

0 0 0 30 0

View Details

Marco Rodrigues @dadhalfdev

a week ago

I've been long waiting for the new MiniMax model 🙏 Let's make agentic tasks cheap again.

0 0 0 28 0

View Details

Marco Rodrigues @dadhalfdev

a week ago

@Teknium Oh this is great! My @apify MCP was adding 3 seconds more to each response.

0 0 1 60 0

View Details

Marco Rodrigues @dadhalfdev

a week ago

@NousResearch This is cool. But one thing I've realised with MCPs is that they increase the response time. I would like to use MCPs, but I'm almost forced to only use SKILLs with REST APIs, to not compromise speed.

0 0 0 283 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

Install the Hermes Agent now! The new v.0.15 release just made it super fast (and cheaper). > %50 reduction in load time. > Session search 750x faster

0 0 0 42 1

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

X API with the Hermes Agent? 🤔

@levelsio @levelsio

2 weeks ago

Feature request for @xai I'd love to see my usage per API key because that's kinda how I separate my projects

44 7 636 57K 43

0 0 0 44 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

Session search for free 🤗

Nous Research @NousResearch

2 weeks ago

Hermes Agent v0.15.0 - “The Velocity Release” Changelog below

133 205 2K 342K 615

0 0 2 149 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

Debugging gbrain is super expensive.

0 0 0 34 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

The best skill for vibe-coding is being critical of the outputs. LLMs are often only 40–50% correct in their suggestions. Your job is to guide them clearly, not blindly approve everything they generate. That’s why having a developer mindset is still a plus.

1 0 2 34 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

I'm setting up the Hermes Agent by @NousResearch for companies. It's all about sandboxing and customizing it from top to bottom rather than building from the ground up The results have been impressive so far. And I don't need to build agents from scratch.

0 0 0 70 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

I thought AI would replace developers by 2030. I was wrong. It already started. I closed more Upwork contracts in 2025 than in 2024, and my yearly revenue increased by more than 2x. So I thought that growth would continue this year. But I was naive. AI is now doing 60% of what I used to do. Clients are using Claude, Codex, and other harnesses to handle data, create dashboards, build pipelines, and much more. On top of that, invitations on Upwork dropped significantly. So I found myself in a difficult situation during the first months of the year. I had two options: 1. Accept the daily LinkedIn invitations to work for companies. 2. Try something new. The first option seemed like the easiest path, but at the same time, I’m concerned about the longevity of programming positions. Even if I applied for one, there’s a good chance it could become obsolete within a year. Instead, I decided to learn more about “Harness Engineering”, in other words, learning how to orchestrate agents like Claude, Cursor, and open-source frameworks such as OpenClaw and Hermes Agent by @NousResearch. It took me two months, and things shifted. Now, instead of coding, I’m mostly vibe-coding, setting up agents across multiple fields, creating second brains, building workflows, debugging, and customizing agents. I have so much demand that I’m even thinking about hiring my girlfriend, who recently lost her job as a web developer (due to AI). If you’re a jobless developer in 2026, maybe it’s time to think about alternatives. New domains are emerging, and we need to ride the wave.

0 0 2 72 2

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

@ellev3n11 Improve code quality, without me having to tell it to organize the code in multiple scripts and classes every time 😅

0 0 0 159 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

@rezoundous It's good to build fast. Not to build well. But if you give it the right instructions, it can fix the mess (a bit).

0 2 8 1K 0

View Details

Marco Rodrigues @dadhalfdev

2 weeks ago

@HDonda It's super fast and free!

1 0 1 27 0

View Details

Marco Rodrigues @dadhalfdev

3 weeks ago

📌 Tip of the day. If you're debugging something related to a platform, tool, etc. Don't ask Claude or ChatGPT. Go to the platform's docs page and Ask AI. Most companies have this nowadays, and there's no better place to debug than querying the actual Knowledge Base.