Ricardo Lopes
ricardolopes.net
Ricardo Lopes
@ricardolopes.net
Software engineer focused on architecting and building secure and scalable services
8yo asked for a maths game, so I vibe coded one. In 1-shot (and 1 fix) we got a nice game that he loved.

Tried later on a different PC. Never worked, going in circles with fixes.

This perfectly illustrates LLMs: they either work like magic, or feel useless. No in-between
October 16, 2025 at 4:44 AM
That's a great article! Too bad that proposed "vibe engineering" goes so against what you argue for in there.

I'm still hoping "vibe" doesn't get to be known for the exact opposite of what it actually means
October 8, 2025 at 1:36 AM
I thought "vibe" was a special case of AI-assisted coding where we don't look as much to the generated code and just "trust the vibes". Not really "uses AI". If the name is getting misinterpreted, propagating that misunderstanding sounds less than ideal IMO
October 7, 2025 at 9:23 PM
I think he's saying he's been suggesting bun to serious professional people and is now cringing at the non-professional anime memes and doesn't want to be associated with them
October 6, 2025 at 7:26 PM
I increasingly feel more like an AI anti-centrist: it either feels magical and game-changer, or it outputs complete shit. I never see an in-between those extremes
August 9, 2025 at 10:15 AM
External display? Is that a Mac thing? My external display flickers all the time and I just assumed it's shit, didn't imagine the problem could be the Mac
July 5, 2025 at 8:10 AM
Yes. I've been playing with coding agents, and they're impressive, but challenging requirements, code review, e2e manual testing, etc is still 100% on us
June 27, 2025 at 10:22 PM
Portuguese here. From my experience, that's likely what happens. The startup scene is minimal, and the best salaries are in working remotely for foreign startups.

Bigger international companies usually have local offices with locally adjusted salaries. And government has no money.
May 27, 2025 at 7:32 PM
Reposted by Ricardo Lopes
Some of the anti-AI stuff feels a bit like when people would say "don't use Wikipedia as a source." It's just like anything else, a piece of information that you weigh against multiple sources and your own understanding of its likely failure modes
April 26, 2025 at 1:23 PM
Thank you!
March 4, 2025 at 1:42 PM
What are the best places we can donate to at the moment? This may be one of the most important times to step up, after the start of the invasion.
March 4, 2025 at 9:23 AM
The deepseek app is topping charts, but it uses V3, not R1, which is the new breakthrough everyone's talking about.

Am I missing anything? V3 was released last month and doesn't use CoT, so it's closer to 4o than o1. Why are people using it now?
January 27, 2025 at 8:28 PM
Reposted by Ricardo Lopes
If AI development stopped this week we would have 5-10 years of absorbing the impact of current models on education, culture, healthcare, and business.

But this week has also suggested that development is not stopping.
December 11, 2024 at 11:03 PM
Blue screens too 🙂
We've always been a fan of blueskies.
December 6, 2024 at 11:18 AM
Pair programming is your chance to have others listen to your "uh this is weird" and "oh it's a different error now"
December 5, 2024 at 10:03 PM
Remote rubber ducking is wild. You write paragraphs of text in a slack DM, only for the writing chain of thought to deliver you the answer, so you delete everything, ship the fix, and the dev who saved your day won't even know about it!
December 5, 2024 at 10:00 PM
Whoa, OpenAI's new o1 model looks mindblowing!
Here is a fun o1 test. I gave it this XKCD comic & the prompt: "make this a reality. i need a gui and clear instructions since i can't code. that means you need to give me full working software"

It took less than 15 minutes and it didn't get caught in any of the usual LLM loops, just solved issues.
December 5, 2024 at 9:24 PM
Hello, world!

Trying out bluesky in case it takes off.

I'm c.im/@ricardolopes on Mastodon and x.com/ricardoplopes on ex-twitter
November 21, 2024 at 1:50 AM