codemilli @codemilli

Turn an idea into a working onchain app with Arc Studio. Describe what you want to build, then generate, review, test, and export the code with your own tools and infrastructure. → Smart contracts → Frontend UI → Tests → Docs → Deployment workflows studio.arc.io

80 132 545 50K 49

0 1 1 45 0

View Details

lauren @poteto

2 weeks ago

volume does matter look, i get it. if you were an engineer before agents came along, you're rightfully skeptical about lines of code and number of PRs being used as a metric for any kind of productivity. and i agree! or at least, i used to. for ease of explanation i will talk about this from the perspective as being an engineer on a large team of at least 50. volume didn't matter before because we focused on impact. you could have high impact even with a few PRs: for example you could make a one line config change and save the company millions of dollars. but before agents, the times where i saw volume come into the conversation were for the outliers. on the negative end you might have someone who is struggling to perform, on the other end you might have someone who was a "coding machine" archetype. a coding machine was someone who could just lock themselves in a room and emerge with a stack of PRs that solve a huge number of problems. so volume did matter, but only at the tail ends of the distribution, and combined with impact. if you've ever worked at a large tech company before, you'll get what i mean. the thing about agents is that big tech co problems are now small-medium co problems as well. how do agents change this calculus? well, everyone now has the ability to become a coding machine. you have incredibly capable frontier models that can write code better than any of us, at a rate much faster than we can. in this world, if you're still producing the same number of PRs as before, why wouldn't you pause to wonder why you're not being more productive? alien intelligence is here, and yet you can't outship a human coding machine? this brings me back to why i keep talking about trust (x.com/poteto/status/…). if you haven't put in the work to trust your agent's output, it is very difficult to scale up your productivity. and yes, this approach does require more tokens, but i think about this in terms of cost per intelligence. before agents, this cost was very high - you needed to hire many software engineers with high 6 figure salaries to do the work. tokens are still expensive today, but are likely to get cheaper over time (x.com/theo/status/21…) factoring in the cost of intelligence. what looks exorbitant today will likely be affordable in 6 moths to a year. a single engineer with agents can do the work of tens if not hundreds of engineers, at a fraction of the cost. the reality that i don't think has hit yet is that job of the software engineer has truly changed. our job is not merely to produce software any longer (well tbh it was never only about the code, but bear with me for the sake of the explanation), but the machine that writes the software. this idea of a software factory, or a Michelin kitchen as i like to call it, is still a topic of research. and it's the type of stuff i like to share, not to flex, but to show you what's possible when you put a lot of rigor into using agents at scale

Emil Kowalski @emilkowalski

2 weeks ago

Can someone help me understand how shipping 100s PRs a day makes sense? Why do you need to ship so many PRs in the first place? I might just not be AI-pilled enough to understand the need for it yet, so I’m genuinely trying to understand it.

271 66 3K 417K 454

225 248 4K 379K 3K

View Details

codemilli @codemilli

2 weeks ago

ㅇㅇ

Thariq @trq212

2 weeks ago

working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this

301 415 6K 357K 930

0 0 1 35 0

View Details

codemilli @codemilli

2 weeks ago

@poteto @bot When post? 🧐

0 0 0 41 0

View Details

codemilli @codemilli

2 weeks ago

@mark_k Too true

0 0 0 9 0

View Details

codemilli @codemilli

2 weeks ago

Hey @bot

0 0 1 28 0

View Details

codemilli @codemilli

2 weeks ago

Except oai one

Elon Musk @elonmusk

2 weeks ago

Important note regarding Grok @bot: Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs. Whatever is most likely to give you the best outcome.

7K 8K 108K 79.7M 10K

0 0 0 37 0

View Details

Thariq @trq212

2 weeks ago

working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this

301 415 6K 357K 930

View Details

codemilli @codemilli

2 weeks ago

@poteto How's the token usage though? I've been suspecting voice mode as the culprit behind my recent token spikes

0 0 0 8 0

View Details

codemilli @codemilli

2 weeks ago

😌

John Ternus @johnternus

2 weeks ago

The way Steve taught us to care about every detail, every experience, every person, still guides our work today. Forever grateful.

1K 3K 52K 1.6M 2K

0 0 0 34 0

View Details

codemilli @codemilli

2 weeks ago

@poteto @PSkinnerTech This resonates a lot. Since LLMs are fundamentally pattern-driven, narrowing the scope and reducing the number of possible paths often feels much more effective than giving them broad, high-level tasks.