Khalid
338 posts


@kimmonismus When are we gonna get a single software that we just describe the game we want to play and you almost instantly get a generated ready to play game.
English

Most "AI makes games" demos are just a clip that plays back the same way every time.
PixVerse Game is chasing the harder version: you describe what you want, that intent gets turned into game mechanics and an AI agent, and a real-time video stream responds to it. Player intent, mechanics, a generated video response, back to you.
This is the direction I've been waiting for AI video to take. Real-time interactive video is the part most projects skip, and PixVerse is building straight at it. Can't wait to see where this goes.
PixVerse@PixVerse_
Every game world you've ever played in was built by someone before you arrived. Every room, every character, every possible outcome -- designed in advance, waiting for you to discover it. We think that's about to change. PixVerse Game is here. RT + Follow + Reply = 300 Creds & Early Access in DMs (72H ONLY)
English

Here's GPT-5.6 Sol vs Fable asked to build the exact same app (prompts in the article!)
What do you think? I have my opinions, but I'd like to hear yours.
Both built complete, working apps, but with very different approaches:
- Sol took less than half the time at the same (high) reasoning
- Sol spent much less time on frame analysis. Fable dumped sheets of frames for every transition and scrutinized them multiple times; Sol only checked twice, and both times was just like "looks great, continuing"
- At first, Sol intentionally ignored my request to use image generation! It went with procedurally generated food images "for simplicity" (they looked terrible)
- On the second prompt, Sol generated images, but intentionally ignored my suggestion for transparent image backgrounds, saying full photos "preserve shadows more convincingly"
- Sol's used its built-in GPT Image 2 integration, which saved cost; Fable had to use the Gemini API
- Sol didn't seem to know how to use Liquid Glass at all
- Fable was more restrained; Sol wanted to add extra labels and detail
- On the other hand, Fable decided to add an extra detail page for foods, while Sol did not
- Both had nice haptics on device
- Fable added a pinch dismiss gesture; Sol did not do gestures
Anshu@anshuc
English

Hey everyone, I fully localized Hermes Agent into Arabic about a month ago, and I’ve been keeping the PR updated ever since.
I’d really appreciate it if someone could take a proper look at it. I’m also happy to own the Arabic localization long term and keep it updated whenever anything changes.
Please check the latest version, especially the last push from about an hour ago. I cleaned everything up, added what was missing, and honestly think it’s now ready to merge.
Feel free to reach out if you need anything from me. And thank you all for building so many cool things with Hermes Agent.
github.com/NousResearch/h…
@NousResearch @Teknium @phragg @witcheer
English

@nateherk Claude code is dying Nate, there are better tools now.
English

I put a ton of work into this Claude Code course for normal people.
It's completely free and 6 hours of content.
I'll take you from complete beginner to actually building your own agents and automations.
I put a lot of work into making this the path I wish I had when I started. No technical background needed.
If you've been wanting to get into this but the whole thing feels overwhelming, this is a structured path you can follow start to finish.
👇 Link is in the replies
English
Khalid retweetledi

@nateherk Amazing content bro thanks
Hermes agent next ?
More and more people using it and no real content like yours explain it
English
Khalid retweetledi
Khalid retweetledi

I can’t believe I’m saying this, but when it comes to web research and finding accurate information, Sol crushes Fable.
I tested several scenarios, and Fable kept giving me reports full of hallucinations, and outdated information, while GPT corrected them completely. OpenAI absolutely nailed this model.
English

What OpenAI has done over the past few days is exactly why I keep demanding transparency.
They claim GPT-5.6 is more token-efficient and uses a new architecture that lowers text inference costs. In actual subscription use, I found it practically unusable. I started one task and burned through two five-hour limits before it even finished. On the second attempt, it ran for less than eight minutes and stopped again.
When many users reported the same issue, the response was basically: lower the reasoning, reduce this, avoid that mode.
Then what is the point of all this intelligence if subscribers cannot actually use it unless they pay for the API?
They mock Claude and Fable with arrogance, but the truth is simpler: they are pulling the same tricks and sitting in the same boat.
English
Khalid retweetledi

✨In the 11th century, the famous Muslim polymath Al-Biruni figured out the Earth's radius using nothing more than a mountain and a bit of trigonometry. 📐
The insight was brilliant:
Stand on a mountain, and the horizon dips below the horizontal. That dip isn't an optical illusion; it's a geometric signal. It creates a right triangle where the mountain's height (h) and the Earth's radius (R) are the only variables.
Measuring the mountain's height without climbing down:
He used a simple trigonometric trick: from two points on the plain, he measured the angle to the peak. Knowing the distance between those points, he calculated the mountain's height with a formula surveyors still use today:
H = D / (cot A1 – cot A2)
From the peak, he measured the dip angle to the horizon: α = 34′ (just over half a degree):
R = h * cos(α) / (1 - cos(α))
How did he compute the cosine of such a tiny angle?
Without modern calculators, he used a sophisticated technique: he started with the known value of cos(60°) and used the half-angle formula to work his way down to the required value for his 34′ angle.
He calculated the Earth's radius as 6,340 km. The modern value is 6,371 km.
An error of less than 1%. In 1030 CE.


English

I'm a total maverick.
But in my early 40s,
given my unusually horizontal background,
combined with a lifetime loving computers and electronic gadgets,
I feel on top of an AI-empowered world.
The breadth of life experience we can now put in tech is mind-blowing.
Garry Tan@garrytan
The founder in their 40s with taste and discernment is the new gentleman unicorn founder Because there can be 100x to 1000x of them working at their beck and call via agents and software factories all the time
English

What a strange coincidence. Fable 5 will remain available to us until Friday.
Since GPT-5.6 was not released today, it will presumably be released on Thursday.
So Fable 5 can be used for one day longer.
Strange coincidences do happen.
Chubby♨️@kimmonismus
Let’s go: 5 more days of Fable 5 until July 12. Let’s hope Anthropic has enough compute by then to keep it in the subscription tier.
English







