Esa Firman | 🇮🇩 in 🏳️‍⚧️

Fractional CTO Wannabe. Eternal Epic on Mobile Legend. My life is average at best. 🇯🇵

[ALUTHEDON @Mbakaza4L]

DO NOT TURN A BLIND EYE TO THIS. HOLY SHIT.

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@aakashgupta Dredd was phenomenal! I rewatch it a few times and this post just make me want to rewatch it again!

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@barinkayaoglu @aakashgupta Wow I just noticed this

[echantech @echantech1]

I think that speaks less to token costs and more to the fact that there’s never been a good singular sellable metric to show developer productivity. That is the original sin.

Many leaders have cited and still cite “number of diffs” as the metric which has been known to be a bad metric for 30+ years.

So when that metric fails and costs go up, I’m not surprised you get these headlines.

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@hlcaptain @Zhuinden This ☝️👆

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

In my experience, too much context degrades the output quality. My most used agent skill is "/clear"

[Muhammad Azamuddin @azamuddin91]

Diskusi back and forth dengan agent, sampai 18 pertanyaan deep terkait fitur yang mau dibuat.

Habis itu pake skill buat dibikin PRD nya

Habis itu dibikin plan file nya.

Ekseksusi -> hasil ampas

Malah lebih baik hasilnya pas prompt langsung implementasi 😂

[Robin Syihab @anvie]

Kalau gitu namanya harusnya jangan “BRI Venture”, lebih cocok jadi “BRI Paylater”.

Berani pakai nama Venture harus berani resiko.

[Chris Krueger @ChrisKruegerDev]

Getting Liquid Glass in Compose Multiplatform 🎉

[Gogo | Dota for Toxicity @lwastuargo]

Bayangin u rekomen buat masukin $MANTA

Atau u secara publik mengakui ngorbanin follower u jadi exit liquidity biar bisa mengeruk duit dipucuk

Nah sekarang bayangin ada team yang proper, doing proper due diligence, terus bikin rekomendasi investasi

Sekarang tebak yang masuk penjara yang mana?

Bayangin dulu aja, kali2 ini semua cuma mimpi

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@zakkafm ETF or individual stock Mas?

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@rintoprie @levifikri Iya karena pake Flutter harusnya 🐦

[Jaewoong Eum @github_skydoves]

Introducing Android Performance Analyzer : The Next Evolution in Profiling for Android

https://t.co/Ysf0isY8ap

[Torch @writingtorch]

TIMELAPSE 100x: IHSG VS MR PRESIDENT'S SPEECH

[Export-Import Guy @DjawatanKopi]

@Jakartalk Sekali lagi gambaran raja dari Ba Sing Se ini benar adanya...
"Tidak ada perang di Ba Sing Se..."

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

@echantech1 I thought the analogy will use Invoker 😅

[YUDHA SI TAAT PAJAK @yudhakhel]

Mau tanya ke Pak Anies deh, sekarang masih 11/100 apa makin merosot nilainya? 😂😂😂

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

I feel the same way with the updates. Not just because it becomes more iOS, but I think the liquid glass UI/UX is sucks overall (I use iPhone too)

[Dy 🌸🌈 @evowizz]

At this point, @Telegram is just giving up on Android.

The latest Telegram beta for Android introduces a new app bar, (or header as they call it) bringing the app's overall design even closer to what iOS offers, completely disregarding what Android users want.

Let it be a reminder that the beta that introduced liquid glass in Telegram remains the most disliked beta they've ever released.

[Faris Afif @Apeeeeep]

Ini yang ngusulin bikin IKN harusnya ditangkep KPK

[Sergey Nazarov @sergeynazarovx]

We used to go to a special website, ask strangers for help with programming, and get humiliated in return

[Esa Firman | 🇮🇩 in 🏳️‍⚧️ @EsaFirm]

Claude + HTML > Canva

[Andrej Karpathy @karpathy]

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.

More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage:

1) raw text (hard/effortful to read)
2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default
3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default
...4,5,6,...
n) interactive neural videos/simulations

Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral https://t.co/z21CP5iQfu

There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen.

TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.