Ralf Dewrich

engineering at a stealth startup & associate @huawei

[Ralf Dewrich @ralfdewrich]

https://t.co/obV084y9NV

[Ralf Dewrich @ralfdewrich]

@lucas_montano I don’t think so

[Can Bölük @_can1357]

Trick Gemini Flash into thinking it has the moves of Opus, and you get to keep quite a bit (~92%) of it's power in short to mid-range tasks. Pretty wild.

wr% leaps from 60% to 78% in my validation set made up of SWE Pro tasks. Likewise w/ Luna/Sol too.

https://t.co/v9F4gnLJVV

[Ryo Lu @ryolu_]

when the dream becomes the job

i used to think the dream was to make my hobby my work.

to spend my life close to the things i loved: computers, tools, interfaces, systems, tiny details, the feeling of making something from nothing. the things i used to do at night, after school, after work, in the margins of life, somehow became the center of my life.

and it is a dream. i don’t want to pretend otherwise.

there is a very specific happiness in getting paid to care. in meeting other people who care. in building a language around your obsession. in seeing something that lived only in your head become real enough for other people to touch.

but there is also a quiet pain in it.

because the thing that once belonged only to you no longer belongs only to you.

it becomes attached to deadlines, teams, customers, strategy, money, reputation, momentum... curiosity becomes roadmap. taste becomes decision-making. play becomes output. the thing you once used to escape the world becomes the thing through which the world reaches you.

and now there is another strange layer: the machines are getting good at the work too.

not just the boring parts. the parts that used to feel close to the heart. writing, coding, designing, reasoning, making taste-like decisions, turning vague ideas into something real. the things we once used as proof that we had something special inside us are becoming things a model can approximate, remix, and sometimes do faster.

that can feel scary in a very specific way.

not only because of jobs or competition, but because it touches the myth you built around yourself. if the thing i became good at can be done by a machine, then what part of it was really me?

i think that question is painful because it arrives at the same place.

the original love.

before the title, before the company, before the taste became a role, before the work became useful to other people, there was a small fire inside. curiosity. obsession. the feeling that the world became more alive when you understood a little more of it, or made a tiny piece of it bend to your will.

AI can make the output faster. it can even raise the floor of the craft. but it cannot want on your behalf. it cannot decide what is worth loving. it cannot protect the strange private thread that made you care in the first place.

maybe that is what becomes more important now.

not whether you can still produce the artifact by hand. not whether you can outperform the machine at every task. that game is already changing.

the real question is whether you still have a relationship with the source.

the part with no audience. no roadmap. no deadline. the part that can wander, collect strange references, make useless things. follow beauty, be wrong, be slow, be you, be true.

because that part is not separate from the work. it is the source of the work.

if you lose it, you can still operate. you can still manage the machine. you can still prompt, review, decide, ship, and keep things moving.

but the work becomes thinner. safer. more explainable. less alive.

so maybe the real discipline is not to work harder, rest more, or care less.

maybe it is to keep returning to the place where the love began – before it became useful, before it became legible, before anyone needed anything from it, before even the machine could mirror it back to you.

not to escape the work.

to make sure the fire inside is still alive.

[Ralf Dewrich @ralfdewrich]

@leodev @shadcn Nice!

[Emil Kowalski @emilkowalski]

New skill: /improve-animations

Inspired by @shadcn’s improve skill I made one specifically for animations.

Use your most capable model to audit animations in your project and hand the execution to cheaper models.

Fable is available through July 12, so make good use out of it!

[Glauber Costa @glcst]

I was going to stay silent on this, but nah.

Fully agree with Charlie here. It doesn't even matter if the contents are defensible. The tone is just abhorrent. And it is the worst kind of personal "attack": it is the cowards way. He starts by saying it is not personal, amd instead of personal attacks, resorts to personal insinuations.

The part about him trying to raise money instead of living out of donations is a very low blow, and "beginner energy"... no comments.

[Ralf Dewrich @ralfdewrich]

Tirando o Cursor, qual outra empresa tem sistema de cloud agents?

[davi @misterclayt0n]

to sum it up, in Andrew's vision:

> original bun was slop
> slop rewrite
> jarred is a bad manager and bad engineer
> he's happy bun is no longer in zig

tho I'm not the biggest fan of the rewrite, bun's blog post at least made some valid technical points (and somehow tried to praised zig quite a lot), which illustrated how lacking zig is, while Andrew is just being hostile for no reason at all

this reading feels like a complete waste of my time

[Ralf Dewrich @ralfdewrich]

@ohmypy Lol

[Ralf Dewrich @ralfdewrich]

Criador do Zig meteu essa mesmo?

[rohit @seatedro]

crazy blogpost by andrew kelley just dropped

[Ralf Dewrich @ralfdewrich]

@ImSh4yy Same thing happened to me, I didn’t understand it

[pira;) @0xPira]

Feito.

xToRage é uma PROVA DE CONCEITO para FINS EDUCACIONAIS mostrando como é possível usar a infra do X como forma de armazenamento ilimitada.

Utilizei a funcionalidade de commerce que não é muito explorada, então o arquivo não fica publicamente no seu perfil.

https://t.co/YUlacjSitV

(possivelmente eu vou apagar esse post pq minha conta ja caiu por menos kkkkkkk, mas vai ficar la no git)

[Ralf Dewrich @ralfdewrich]

@Pedrodv Muito bom!

[Ralf Dewrich @ralfdewrich]

@0xPira @zeroc00i Bora fazer @zeroc00i

[Ralf Dewrich @ralfdewrich]

Leiam esse artigo, acho que esse é o caso mais bizarro que vi do uso de AI pra refactoring

[Jarred Sumner @jarredsumner]

Rewriting Bun in Rust

https://t.co/Rl8bcaxBFc

[Ralf Dewrich @ralfdewrich]

I’m testing Grok 4.5 through @SpaceXAI / @cursor_ai, and it’s very good!!

It’s a very fast and cheap Opus 4.7/4.8, I think they nailed it with that

It makes some minor errors, but overall it’s been good

[gabriel @gabriel1]

after now having interviewed 50+ people, it's crazy how rare it is to talk about things you've done in concrete terms

always only talk with high precision about what you did and why no one else could

it doesn't mean anything that you "made X better" or "led thing Y"

examples:

[Ralf Dewrich @ralfdewrich]

@LukeberryPi Testei e está muito bom

[Ralf Dewrich @ralfdewrich]

@m9tzin está muito bom! achei melhor em certas tarefas de backend
e eles vão lançar o 5.6 terra/lua/sol

[Ralf Dewrich @ralfdewrich]

Honestidade, usei por 3-4 meses o Claude Code, mas cancelei e assinei o Codex e tenho gostado bastante!

E agora estou em dúvida, Vale a pena ter o Cursor com um plano intermediário + um Codex com plano Max 5x, ou só o Codex/Claude Max 20x?

Pessoal tem falado muito bem do Composer 2.5, e vai lançar o 3.0 também, enfim…

Opinem