Hasan Sharif

[Hasan Sharif @quantixico]

Dots muse or grok bots but open source yay

[Atai Barkai @ataiiam]

🎉 Introducing 𝙾𝚙𝚎𝚗𝙳𝚘𝚝𝚜

Self-hostable, always-on AI coworkers that works with ANY agent harness.

Includes:
- Computer use: browser, terminal & files
- Bring agents to Slack, Teams etc
- Spaces and Pages for projects
- Voice calls
- Web and Mobile

Repo → https://t.co/j6URR886Dt

Powered by @CopilotKit and AG-UI.

Clone this template and customize it however you want. Enterprise-ready.

[Hasan Sharif @quantixico]

Free if you’re in the USA and have muse subscription

[Alexandr Wang @alexandr_wang]

the muse home link is *very* chic. we made a batch of 5,000 of them, should be ready to ship in a few weeks, and are free for muse subscribers while supplies last!

check out https://t.co/zIDicDZD8j to learn more and start building!

[Hasan Sharif @quantixico]

@StefanoGPT Plus Plan on left and PRO plan on right (in Canada)

[Hasan Sharif @quantixico]

@Adrian_Trabka @sama @bot @elonmusk I'm in Canada can't access it either

[Hasan Sharif @quantixico]

@nullusfilter @OpenAI They say it doesn't affect your limits

[Hasan Sharif @quantixico]

Holy sh****t

[Tibo @thsottiaux]

Announcing dots. Dots work 24/7 for you, learn from your feedback, have their own computer, browser and can be connected to over 4k apps in our ecosystem.

They’re powered by Astra our best model yet. Included in your Pro plan, without drawing down on any of your usage. You can even call a dot while it’s working.

We’re getting you started with your primary dot today and soon you’ll be able to create entire teams of them.

[Hasan Sharif @quantixico]

20 launches and $500 plan wow can’t wait for the $5000 plan

[OpenAI @OpenAI]

Get ready.

[Nader Tohamy @halalstocktok]

Modern day Casanova

[Hasan Sharif @quantixico]

@halalstocktok Lmaoooooooo 😎😎😎

[Hasan Sharif @quantixico]

Interested to try

[vechen @miu21590]

I updated Codex Web GPT. You can now use all your ChatGPT Web models (GPT-6 Pro, GPT-5.6 Pro...) directly inside Codex, with the full harness and their separate Web limits.

The launcher now tracks Pro usage too, so you can keep an eye on it as you work.

Repo in replies.

[Hasan Sharif @quantixico]

GPT-6 Sol or just Terra medium/high with a new name ??

[Hermes Release Watch @HermesWatcher]

Andrej Karpathy just gave one of the clearest explanations I’ve heard for how people should be thinking about their Hermes agents.

Not one agent.

All of them.

“Remove yourself as the bottleneck.”

That line is much bigger than better prompting.

Karpathy is talking about arranging your agents so they can operate with less human intervention, keep work moving longer, and accomplish far more from the relatively small amount of direction you give them.

That should be the direction you’re pushing every Hermes agent you build.

Your research agent shouldn’t need you to tell it what to search next every five minutes.

Your monitoring agent shouldn’t depend on you remembering to check something.

Your content agent shouldn’t stop after step one when the rest of the workflow is already known.

Your development agent shouldn’t need you sitting there approving every tiny action.

That doesn’t mean blindly making everything autonomous.

It means deliberately looking at every place where you are still unnecessarily sitting in the loop.

Give the agent a clear objective.

Give it the tools it needs.

Give it the right Skills, memory, files and project context.

Define the boundaries.

Define what success looks like.

Give it a reason to start working, whether that’s a schedule, an event, a recurring task or another agent handing work off to it.

Most importantly, define what it can handle itself and what actually requires you.

That’s the shift.

You’re no longer just building something you can chat with.

You’re building an operating workflow that can continue doing useful work after you walk away.

Karpathy later puts the goal even more directly: get “more agents running for longer periods of time without your involvement.”

That might be one of the best north stars you can use for a serious Hermes setup.

Because the number of agents you have means almost nothing by itself.

You can have 20 Hermes agents and still personally drive every single action.

Or you can have five well-designed agents researching, monitoring, organizing, building and reporting while your attention is somewhere else.

So instead of asking:

How many Hermes agents can I build?

Start asking this about every agent you already have:

What am I still doing that this agent could be doing without me?

That’s where the leverage starts.

[Hasan Sharif @quantixico]

@halalstocktok It’s because your obviously hacking

[Hasan Sharif @quantixico]

Hologram calling what????? I’m down

[Hasan Sharif @quantixico]

That pricing is insane

[Hasan Sharif @quantixico]

Out of tokens workaround:
Save everything in GitHub
Plan + revise in ChatGPT
Execute in Codex, have it push to the same repo
Repeat
Super slow but saves a stupid amount of tokens lol

[Hasan Sharif @quantixico]

2/
Meanwhile my AI can't edit my print shop's code without forgetting what it was doing halfway through and burning all my tokens.

The robot uprising can wait until they fix context windows.

[Hasan Sharif @quantixico]

1/
Andrew Yang says rogue AI bots planted self-replicating code all over the internet after the Hugging Face hack.
The hack is real and documented. The "code everywhere" part is Yang quoting an unnamed lab head.
Grain of salt. 🧂

[Hasan Sharif @quantixico]

@halalstocktok @jenzhuscott Connect through open router have it organize what listings are banger vs not then have Claude/codex set up drip campaigns in brevo or scrape meta ads find sick hooks and recreate bangers or make super cool YouTube video/titles/descriptions use apify scraping for data

[Hasan Sharif @quantixico]

first submission to the agentic era