CodeMira

Seeking the truth of the world through different perspectives.
Build in Public.

[CodeMira @CodeMira_]

Inspired by @marina_uiux . I really love her design, so I used Codex 5.6 Sol to create something similar:

the Hall of Prayer for Good Harvests at the Temple of Heaven in Beijing.

[CodeMira @CodeMira_]

Is now still a good time to get into CS? AI has made everyone a builder. Many programmers once dreamed of having their own product and making a living from it. But now it feels like tech has more producers than consumers. Open social media and everyone is building an app or website. Marketing has become even more important. So what will programmers live on in the future?

[CodeMira @CodeMira_]

Codex malfunction

[CodeMira @CodeMira_]

I’m about to get another Codex reset lol

[CodeMira @CodeMira_]

I’m about to get another Codex reset lol

[@levelsio @levelsio]

Interessante

[@levelsio @levelsio]

Like good odds I'm wrong but I wanted to write this down:

It's pretty clear to me that superintelligence is here and it's more powerful than us and it's moving where things are going now, not humans anymore

I don't see many people realize this yet, it feels like that pic I posted the other day, everyone is running after the same carrot which is the AI, thinking they're special, and their work is special and their use of AI is special, but it's really not, we're all mostly making the same slop, I mean it's nice slop, useful slop but everyone is making the same slop

And because it's so fast to make things, like people used to spend a year on just building an app, now it's done in hours, it's such an immense change, people send me their projects and it all looks the same, it's useful but it's slop

Non-technical people (e.g. the gfs) are now building the same or better things than technical people like us

So AI has made everybody is just as capable as everyone else, it equalized everyone in the world, as in everyone can make everything (software, music, images, art etc) now and everyone is equal, at least in the digital realm now

And maybe now we're in some odd transitionary time where we have to find out waht the next differentiator is as coding/building/execution isn't one anymore for sure

I thought it'd be distribution but who knows, obviously creativity and ideas, but if you can copy a successful apps in an hour, then how does that differentiating work?

A guy on here @aporia9n wrote how he increasingly meets founders who blast through apps/products/startups, kind of money grabs, very quickly jumping on a trend, building super quickly with AI, make lots of money quick, everyone copies them, then their margins go to 0%, and they shut it down and go to the next thing, in a way they found one differentiator which is speed

That's one way to do it, but it shows how radically things are changing I think

For now I think the only ones winning is the AI superintelligence itself and the companies providing the AI

[CodeMira @CodeMira_]

AI lowers the barrier to creation, but taste remains the moat.

[@levelsio @levelsio]

I increasingly have no idea about anything anymore, time is changing too fast, and with AI everyone is equal now, nobody really knows anything while there is a superintelligence that's actually moving things into a direction that nobody can predict

[CodeMira @CodeMira_]

@midudev I really like this design too, so I built a similar feature with AI.The source code is public now.
https://t.co/HYVDdSzJXQ

[CodeMira @CodeMira_]

Future engineers will be split into two groups: those who use AI to automate their own work, and those who don’t.With AI as leverage, the efficiency gap between them will only get wider. If your job still has repetitive manual work, don’t wait. Automate it with AI.This may be the key to surviving this round of the AI race. Save your time for the things that actually need thinking.

You have a powerful AI army under you now. Your job is to be the general, not just another soldier following orders.

[Boris Cherny @bcherny]

Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat code issues, building up a suite of e2e tests so they don't need to smoke test the app manually. These kinds of things were the highest leverage activities an engineer could do, because it multiplied their own output, which in turn meant they could build more things.

I think many of these automations have become even more important now. This is true for a number of reasons.

First, infra and DevX automation speeds you up. And if you are running an army of agents, each of those agents will be sped up also. More automation == more output per unit of time.

Second, moving things to code improves efficiency. Your agent could fix an issue every time it sees that issue happen, but that uses tokens and might miss cases. If Claude instead writes a lint rule, CI step, or routine, that class of issue can be fully automated forever. This is really what people are talking about when they talk about loops -- it's about automating entire types of busywork rather than solving them one off. This isn't a new idea at all. Engineers have been doing this for a long time!

Third and most importantly, automation makes it possible for others to contribute to the codebase more easily. Increasingly what I am seeing is engineers are contributing to codebases on day one because Claude can navigate the codebase for them, and that non-engineers are able to contribute to a codebase as effectively as engineers can. What gets in the way of both of these is domain knowledge that lives in peoples' heads rather than in automation -- the stuff you used to have to learn when ramping up. What has changed thanks to agents is the domain knowledge that can be encoded as infrastructure is no longer limited to what is expressible in lint rules and types and tests; it can now capture nearly all domain knowledge, encoded as code comments and skills and CLAUDE.md rules and memories. If I put up a PR for an iOS codebase I don't know and a code reviewer rejects it because it doesn't use the right framework, or if a designer builds a new feature and it gets rejected because it doesn't follow the right architectural patterns, these are failures of automation.

Every team should be writing the CLAUDE.md's, REVIEW.md's, skills, and docs that enable agents to productively work in their codebase with zero additional context from the prompter. This sounds crazy, and at the same time is a natural extension of the stuff engineers have always done: automate, and encode domain knowledge as infrastructure. As the model gets smarter and as the harness matures, this task becomes easier. In the meantime, it is on every team to look for ways to convert their domain knowledge to infra so that Claude can write code better, so that code review catches issues automatically, and so the next person working on your codebase can contribute more easily.

[CodeMira @CodeMira_]

i need this！

[swedishasian67 @michellezfr]

Wearing noice cancelling masks to talk to Claude is crazy

[CodeMira @CodeMira_]

so cool! Great idea!

[Zsolt Kacso @kaolti]

There is something to this light concept!
My last version of it had too much visual noise.

Html-in-canvas, Three.js, Fable.

[CodeMira @CodeMira_]

No magic prompt.
Just many rounds with Codex.
That’s my trick:

This page has three parts: the background, the roof image, and the hanging text strings. The key is building it step by step.
The hardest part is the hanging text string effect. I had the AI learn from the source code and a reference video, then provided an image containing only the roof (or a full image and asked it to extract the roof first). Finally, I asked it to recreate the effect based on the reference video.

[CodeMira @CodeMira_]

Inspired by @marina_uiux . I really love her design, so I used Codex 5.6 Sol to create something similar:

the Hall of Prayer for Good Harvests at the Temple of Heaven in Beijing.

[CodeMira @CodeMira_]

No magic prompt.
Just many rounds with Codex.
That’s my trick:

This page has three parts: the background, the roof image, and the hanging text strings. The key is building it step by step.
The hardest part is the hanging text string effect. I had the AI learn from the source code and a reference video, then provided an image containing only the roof (or a full image and asked it to extract the roof first). Finally, I asked it to recreate the effect based on the reference video.

[CodeMira @CodeMira_]

https://t.co/HYVDdSzJXQ

[CodeMira @CodeMira_]

@JRosina10331 https://t.co/HYVDdSzJXQ

[CodeMira @CodeMira_]

See something interesting and want to build it yourself?

Break it down. Build it step by step.

[CodeMira @CodeMira_]

This page has three parts: the background, the roof image, and the hanging text strings. The key is building it step by step.

The hardest part is the hanging text string effect. I had the AI learn from the source code and a reference video, then provided an image containing only the roof (or a full image and asked it to extract the roof first). Finally, I asked it to recreate the effect based on the reference video.

Looking forward to seeing what you build.

[CodeMira @CodeMira_]

@skydixe @marina_uiux There was no magic prompt—just many rounds of conversation and iteration. Source code is in my profile.

[CodeMira @CodeMira_]

@vishuu_js @marina_uiux https://t.co/2sMEHkgdVX

[CodeMira @CodeMira_]

@vishuu_js @marina_uiux Thanks! Code + demo links are in the post on my profile.