A rebellious man

محتوى جميل بشكل استثنائي

[A rebellious man @alihh58]

هل أستطيع إصلاح هذه الهواتف

[A rebellious man @alihh58]

@nzk1897570 شرع الله يجب أن يطبق الحمد لله

[A rebellious man @alihh58]

سائق غشيم الحمد لله أن الله ستر في آخر ثانية قبل نزل هو والسيارة من فوق🙀

[A rebellious man @alihh58]

@molham_q8 ارد المتابعة ملهم❤️

[A rebellious man @alihh58]

@nzk1897570 الروح قويه وأنت القوة نفسها❤️

[A rebellious man @alihh58]

@molham_q8 متابعة يا غالي

[A rebellious man @alihh58]

@molham_q8 اضافة

[A rebellious man @alihh58]

@nzk1897570 تمايل الجسد

[A rebellious man @alihh58]

ابنتي هي أول شي في حياتي❤️

[A rebellious man @alihh58]

@abdulhafiz20111 مشكور جدا جدا أخي عبد الحافظ يا ريت ترد المتابعة حبيبي

[A rebellious man @alihh58]

@toptopali90 شكرا لك

[A rebellious man @alihh58]

ليبيا في القمه رقم واحد تبارك الله

[A rebellious man @alihh58]

سوال لنقاش
هل عيون المراة جزء من جمالها؟

[A rebellious man @alihh58]

هذا شي صاير مع حسابي شنو الحل عشان حسابي يصير عادي @toptopali90

[Meta Alchemist @meta_alchemist]

SpaceX will win the AI race imo.

Even if it doesn't look like it now to everybody,

They invented all the technologies necessary to spawn infinite compute in space.

> Optimus robots: productivity both on earth & space
> SpaceX rockets: deliveries at a lower cost
> Terafab factory: manufacturing chips at scale
> Starlink satellites: linking compute from space to earth
> Solarcity panels: infinite energy from the sun, and in space without needing water to keep things cooled

Once they start to spawn the data centers beyond Earth, I'd say they'll likely go for space mining for rare earth materials and some other things: which will mean infinite chips.

The endgame is all about compute.

If you have infinite compute, you can recursively create the best models, give much better rate limits, win, and even make all the competitors depend on you too, because they will need to buy compute from you.

[Meta Alchemist @meta_alchemist]

Damn this guy is producing a really dope movie with Ai

watch the teaser, especially if you are into fantasy:

[Spark @Spark_coded]

Some updates on what we've been working on:

> A new agent harness has been getting coded for more than 110+ hours to upgrade the architecture of Spark

This will be a huge improvement that will positively impact all foundational code, tool calls, conversations, and more

> There are over 3000 open source PRs submitted for the Spark Compete: Hunting Bugs & Goblins

With the community helping to improve Spark and all its repos, the product is getting in shape, not just via solo-building anymore, but in a community-oriented way

> Spark Compete's first event will end tomorrow (07.06) at 11.59 PM UTC. All PR submissions done until that time will be reviewed, after the event ends, too.

Since we are now deploying the new harness, we paused reviews and merges to deploy that, which is between staging and production.

It has taken much longer than we expected, even with AI writing the whole code. But once this is done, the core of Spark will be much more solid.

> Once the new installer gets deployed with the new harness, reviews/points/merges will continue.

After the product polishing reaches the stage we like, we will double down on content, grants, incubations, token utilities surrounding these, and creative ventures around NFTs that will add another extra utility to the token, too.

Getting to this stronger agent OS will make every other effort have more impact.

> Last but not least, an educational content group will be formed around Spark to reward good content that drives greater adoption of the product.

Product polishing first. And then the next stages will get more exciting.

P.S. Below, you can see how our new harness operates at its core: a unified governor for better context capture during conversations and tool calls with a more reliable source of truth, and observability systems everywhere.

As Spark has been expanding its repos and tools, getting this done correctly became paramount. Can't wait to ship it soon!

[Meta Alchemist @meta_alchemist]

Starting a new agentic experiment

Where I will be adding agents to places where humans normally do the job, and sharing the progress and results

See if agents are getting ready to replace real work, and to what degree

Rules:
> All the agents will be @Spark_coded
> They will have a progress sharing dashboard
> The community will be able to direct the agents via feedback and strategy inputs

Question time:
What should be the first agent's role?

[Meta Alchemist @meta_alchemist]

For those joining Spark Compete, please read this:

It's how you can get more PRs accepted, be really helpful to Spark's improvements, and earn more Sparks.

A step-by-step guide:

1. Make sure that you have an IDE or Agentic Engineering CLI like Codex, Claude Code, or Cursor to help you with getting the Spark Agent from https://t.co/Db1vqNhE9V

2. Let them do the installation, and then connect themselves to Spark, and guide you through the steps. It will be super easy if you let an IDE guide the process.

3. Only once you get your Spark agent fully working inside Telegram, then tell your IDE to read https://t.co/0fQDZ2Hvua and prepare you for things to do inside Telegram, according to missions/repos therein, while understanding the hotfix validation system fully.

4. Then use Spark, inside Telegram, catch the bugs, as you will be able to tell when something is off, and then copy and paste those foul/unpolished parts to your IDE to fix them.

5. Once your LLM fixes something, you can actually check after the hotfix is done in Telegram, to see if it works well now, and once you verify everything works perfectly, on that problem you had before, then let your IDE prepare a PR according to the Spark Compete system.

6. If you skip the step of using Telegram, you gonna do blind PRs, and most of them will be just your LLM hallucinating, and it won't have good hotfixes validated within Telegram, where your Spark agent runs.

7. You can also use Computer Use systems, which are available in Codex and Claude Code, and if your IDE doesn't have a computer use, you can always use a browser-use plugin or other computer use plugins that are popular. This way, you can automate more things, still test everything in Telegram, and pair your IDE to use Telegram directly rather than have it run in the background.

You wanna see the fixes firsthand and make sure they really polish and improve Spark. That's basically the essential thing to focus on. But if you just send your IDE to audit and send PRs without any telegram usage, or real hotfix validation that fixes real bugs, your efforts won't be that effective, nor it will help to improve Spark much.

Thank you 🙏

The event is still progressing until the 7th. You're more than welcome to join, help Spark get better, and earn Sparks.

For any technical questions, you can ask them in the comments. I'll try to help as best as I can.

[Meta Alchemist @meta_alchemist]

Spark still has certain issues to get widely adopted.

I think the top 3 are

Installer: the CLI installer surface is too technical for most users; this is the problem with most other popular personal agents, too. Bringing a desktop app to fix this.

Harness: this is the core source of bugs. At the beginning, we had fewer surfaces, which meant that words coupled with intent to trigger Spark-specific actions were ok, but now they are a problem. Bringing an Intent Layer that will work as a harness to eliminate certain words hijacking convos, which will bring a much more polished experience.

Content: I just couldn't do a great job creating content over the last 2 weeks, partly because TGE and fixes took up too much of my time. It's time to focus on this and build the right systems so I'm not alone in this.

This week, let's start to get these right!