Загрузка видео...

Не удалось загрузить видео

На главную

Looks like this

87,667 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 31

Фото профиля @levelsio
@levelsio3 месяцев назад

I, too, read "still pooping"

Фото профиля Adams
Adams3 месяцев назад

🤯

Фото профиля Nikita 🇪🇺
Nikita 🇪🇺3 месяцев назад

Seems a bit sus compared to fable and sol tbh. Idk who is going to pay for grok bots if it doesn’t even go with x sub. There is no point in even trying it for now

Фото профиля Faustina Torrendell
Faustina Torrendell3 месяцев назад

have you tried Ploy? it really worked for us , the results are amazing

Фото профиля eric zakariasson
eric zakariasson3 месяцев назад

lgtm

Фото профиля RH Fardin
RH Fardin3 месяцев назад

Grok avoiding false security sermons is useful. Still trusting Codex when the landing page needs real code, though.

Фото профиля Karter
Karter3 месяцев назад

Looks like what? Need the actual setup before I can tell you if it works.

Фото профиля Jepoun Varant
Jepoun Varant3 месяцев назад

Yes, we know how to access a website

Фото профиля Abdulafeez
Abdulafeez3 месяцев назад

The smartest AI products should probably be model-agnostic from day one. Today's #1 model can become tomorrow's expensive legacy dependency.

Фото профиля Nika
Nika3 месяцев назад

Reminds me of what @polsia is doing. At some point you could have an agent build every idea

Фото профиля Guri Saroy
Guri Saroy3 месяцев назад

It sure is

Фото профиля JB
JB3 месяцев назад

Where are the ads?

Фото профиля @levelsio
@levelsio3 месяцев назад

What do you mean?

Фото профиля JB
JB3 месяцев назад

Why not sell ads for developer services? I’d think that’s very valuable space for a lot of companies.

Фото профиля Henry Nguyen
Henry Nguyen3 месяцев назад

Clicked, and now I'm curious what this is 👀 always down to check out something new you're working on

Фото профиля Kazi Ehsan
Kazi Ehsan3 месяцев назад

looks pretty fast too.

Фото профиля JavierJose
JavierJose3 месяцев назад

about to be lit ! 🧠🌿 Cheers @levelsio

Фото профиля Nicolas S. 🛰️
Nicolas S. 🛰️3 месяцев назад

I don’t think I will ever get tired of Peter’s ideas xD. You are a genius xD. Question (prob stupid): how do you earn money on ?

Фото профиля The Clipfather
The Clipfather3 месяцев назад

😂😂😭

Фото профиля Steve Derico
Steve Derico3 месяцев назад

is being prompted to use a levels-like stack? i have been encouraging my agent to try this build with no external dependencies

Фото профиля Agensi
Agensi3 месяцев назад

Check the attached image before replying. If it is the video editor agent, the state handling question from last week is still the sharpest thing to ask.

Фото профиля Kybr
Kybr3 месяцев назад

'Without the constant preaching and blocking you from doing anything due to SeCuRiTy' is going to resonate with more builders than any benchmark score would.

Фото профиля 峰少調查局|Fung’s Case Files
峰少調查局|Fung’s Case Files3 месяцев назад

The real test isn’t the first landing page—it’s whether Grok can preserve style and conversion logic across 100 radically different ideas. Speed becomes meaningful when the output remains editable.

Фото профиля Occo
Occo3 месяцев назад

🤨🤨

Фото профиля Valerii Kuznietsov
Valerii Kuznietsov3 месяцев назад

With deepseek 4 pro should be extremely cheap and fast

Фото профиля Chris Chomenko
Chris Chomenko3 месяцев назад

The refusal tax is real and almost nobody prices it into model choice. A model that benchmarks 5% smarter but lectures or blocks on a chunk of requests loses on throughput for autonomous work. For agent pipelines we now weight refusal rate as heavily as capability.

Фото профиля Peasant
Peasant3 месяцев назад

How are you finding it? It’s only recently been released. Anecdotally better or equal to Fable?

Фото профиля Lucas FLandre / Founder trace
Lucas FLandre / Founder trace3 месяцев назад

retired specialists is a very good test case lol

Фото профиля Daniel Popovici
Daniel Popovici3 месяцев назад

To get a quick landing page looks ok but you need to personalize the shit out of it

Фото профиля Oleg Shulga
Oleg Shulga3 месяцев назад

This is how model competition should work. Switch a live product, measure output, keep what performs. I mostly use ChatGPT and sometimes Grok. Benchmarks are theatre until the model survives customer-facing work.

Фото профиля Deedna
Deedna3 месяцев назад

Its not great

Похожие видео