Guilherme Rosado

- Fullstack Web Development
- DevOps
- Web Components

@muxit_studio

[Guilherme Rosado @odas0r]

just launched my agency website https://t.co/LGaePNJ3yy

[Guilherme Rosado @odas0r]

@thdxr So many abstractions... GPT-5.5 really is an abstraction boy

[Guilherme Rosado @odas0r]

@mitsuhiko Great article. I think "ownership" of the system you built is a feeling that's embedded in engineering and "looping" takes that away. Right now, LLM's are not trustworthy, and I don't think they ever will be. I think it will go down badly, just a matter of time.

[Armin Ronacher ⇌ @mitsuhiko]

Why do people think there is more clarity in their communications when they throw their thoughts into an LLM before sharing? I’m so sick and tired of engaging with people who send me regurgitated clanker slop :-/

[Guilherme Rosado @odas0r]

@mitsuhiko Trueeeeeeeeee. Imagine having this at your job 😅

[Flue @flueai]

NEW: Evals

Model output can change over time. Evals give your Flue agents a repeatable set of scenarios and expectations, so you can catch regressions before they ship.

Powered by vitest & vitest-evals, a testing library by @zeeg & the @sentry crew.

https://t.co/DfJ5HR9Srj

[Mitchell Hashimoto @mitchellh]

I’m a huge proponent for AI. You can see how much I use it and others in my projects do too. Plus my writing on it. I’m not anti AI. I’m anti idiot. I’m pushing people to recognize that AI is still a tool, and bad AI outputs aren’t because AI is bad but because the person is an idiot.

[Adam Wathan @adamwathan]

Feels like we're all just building "things for building other things" and not a lot of "things" anymore.

[Guilherme Rosado @odas0r]

@cramforce @vercel Was just messing. I love you guys! 💪

[terminal @terminaldotshop]

New benchmark just dropped

[Guilherme Rosado @odas0r]

@ctatedev Similar ideas! https://t.co/wDtVdYMwe2

[Guilherme Rosado @odas0r]

@zeeg @RedBuildsThings The crazy part is that I don't know if these are actual people or bots. You're probably answering 95% to bots 😂

[Guilherme Rosado @odas0r]

@wesbos @itsolelehmann Oh man, you're just murdering them at this point

[Guilherme Rosado @odas0r]

@BrettFromDJ ragebait master

[Deno @deno_land]

Deno 2.8.3 is out!

Deno.serve() is faster: we shipped a new HTTP/1.1 fast path, plus fixes for streaming bodies, header handling, and compression negotiation.

Also a big LSP cleanup, 170 fixes in total.

`deno desktop` is coming soon!

[Guilherme Rosado @odas0r]

@deno_land Let's gooo!! Rooting for you guys.

[Guilherme Rosado @odas0r]

@Amin_Ankward @Aurelien_Gz Damn, great work on that demo wtf. 👏

[Guilherme Rosado @odas0r]

@DavidSHolz Maybe I'll try that farmer life, someday ... in the future

[Guilherme Rosado @odas0r]

@DavidSHolz Yeah, and I'm all for that. But still, scared that in the future companies will just out scale you because they have access to LLM's so powerful that you can't even compete with 😂.

It just won't matter if you're more skilled.

It's insane... Wild times

[Guilherme Rosado @odas0r]

@DavidSHolz I can't even believe that I'm writing this 😂

What the fuck.

[Guilherme Rosado @odas0r]

@DavidSHolz What about the average person...? Who cannot "afford" that "intelligence"?

It's completely unfair to put a price on something like this.

Completely dystopian 😅

This means that teams with more cash, can pay to be faster than others... Unfair.