Arshia Seda

I have nothing to sell you

Founder of

[Arshia Seda @SedaArshia]

day 4.5 of using @OpenBot_ instead of @bot

added a second $20 claude account. switched all agents to it + sonnet 5.5

full throttle using it for 5 hours straight and barely hit the 5 hour limit

$20 claude > $200 Grok Ultra

[Arshia Seda @SedaArshia]

@OpenBot_ + opus 5.5

Get a full blood panel test at @function and have 8 different AI doctors analyze it using the most recent research and scientific papers

they will recommend custom supplements, foods, lifestyle changes custom to YOU

they will check in with you everyday and adjust based on how you feel for free.

[Arshia Seda @SedaArshia]

just figured out how to connect @OpenBot_ to almost all the tools seamlessly

you can connect your tools to your claude account. @OpenBot_ will use the CLI to interact with them however you want

just tested meta ads MCP and it worked

[Arshia Seda @SedaArshia]

@argooco @OpenBot_ @bot if you can connect things to your Claude account it can still pull and push and interact with the tools

[Arshia Seda @SedaArshia]

day 5.5 of using @OpenBot_ instead of @bot

my productivity app tracks every single thing I do throughout the day

once it sees a pattern repeat more than 3 times

it extracts it into a skill md file that is so precise and detailed, with the exact tools used, clicks etc

then I can drop it into any LLM and have it repeat the same workflow

** it extracts the patterns and the underlying "why", not the exact things I do which is game changer

[Arshia Seda @SedaArshia]

@norbertbodziony dont stop

[Arshia Seda @SedaArshia]

@PakaJoe @OpenBot_ no I built a custom app for myself with openbot

[Arshia Seda @SedaArshia]

use @OpenBot_ + opus 5.5 to replace yourself (Not BS)

thank me later

[Arshia Seda @SedaArshia]

@argooco @OpenBot_ @bot you can ask your grokbot to package everything up in a zip file and just drop it over in openbot

[Arshia Seda @SedaArshia]

@thezerokage @OpenBot_ @bot fable 5.2 came out yesterday. i'm using my claude subscription.

[Arshia Seda @SedaArshia]

day 5 of using @OpenBot_ instead of @bot

switched all the agents to fable 5.2 Max

[Arshia Seda @SedaArshia]

@merunas @OpenBot_ @bot how much is what?

[Arshia Seda @SedaArshia]

@ArmandasPuckus Clone

[Arshia Seda @SedaArshia]

wouldn't it be a waste of potential if the bots that literally run your business and livelihood couldn't use these frontier models?

my @OpenBot_ bots have already been switched to fable 5.2

what about your @bot's?

[Dr Singularity @Dr_Singularity]

We won't slow down. We won't stop. We'll keep accelerating until ASI arrives and ushers in an entirely new era of human civilization.

Claude Fable 5.2 and Mythos 5.2 are here

Anthropic has released two powerful new AI models, reporting amazing advances across scientific discovery, mathematics, coding, robotics, and hardware engineering.

Major achievements:
- Physics: Solved two previously open theoretical physics problems involving black holes and quantum gravity.

- Mathematics: A team of 1,000 AI agents fully formalized Fermat's Last Theorem in just 30 hours, with minimal human intervention.

- Engineering: Designed three fully functional electronic devices from scratch, including circuit boards, enclosures, and software.

- Coding: Built a working operating system from scratch using more than 1,000 coordinated AI agents.

- Biology: Developed a new method for predicting complex viral protein structures, potentially accelerating gene therapy research.

- Robotics: More than doubled its predecessor's performance on a simulated robot-control benchmark.

- Scientific computing: Optimized materials science calculations to run approximately 36 times faster.

The models also generate outputs up to 30% faster than their predecessors, with lower API pricing.

[Arshia Seda @SedaArshia]

@RAYAN_MERCER @bot personal, business ops, design, contents generation, paid ads, CS, dev ops

[Arshia Seda @SedaArshia]

even if @bot usage and model improvements go live today imo its still not worth it if you're on the ultra plan, here's why:

- You dont get to pick smarter and/or dumber models for different agents

- You don't really know how many tokens you get weekly so it can go up and down without notice

- In 1 year time anthropic and openai will come out with more insane models but you still have to wait for grok to drop theirs

- You can't upgrade your bot's computer to have a higher RAM, Storage and CPU (iykyk)

with @OpenBot_ you can do all of that and stack multiple claude ultra accounts as your work expands.

Remember that the $200 Claude ultra plan gives roughly $12,000 worth of equivalent API inference per month

$20 Claude Pro plan gives roughly $1,000 worth of equivalent API inference per month

[Arshia Seda @SedaArshia]

@StableStriker @bot its not against their policy at all. they encourage it.

[Arshia Seda @SedaArshia]

day 4.7 of using @OpenBot_ instead of @bot

all 14 of my agents live in a real 3D house, every one has its own room, and you can tap any room to look inside

when they’re idle they throw a party. lasers, disco ball, the whole thing.

Opus 5.5 still feels unlimited, so instead of stressing about usage i’m building my agents a house

[Arshia Seda @SedaArshia]

@__johnfuller @bot the minimum plan on grok bot is $30 and it can't even compete with a $20 claude plan. A dumb model orchestrating the frontier models doesn't seem like a reasonable trade.

[Arshia Seda @SedaArshia]

@jonvolio @OpenBot_ @bot currently self host. ask it to figure out a manual way to connect. 99% of the time it does (opus 5.5)

[Arshia Seda @SedaArshia]

day 4.5 of using @OpenBot_ instead of @bot

added a second $20 claude account. switched all agents to it + sonnet 5.5

full throttle using it for 5 hours straight and barely hit the 5 hour limit

$20 claude > $200 Grok Ultra

[Arshia Seda @SedaArshia]

I fucking agree.

[Abyssus @AbyssusErigo]

Grokbot isn't enough.

Because everyone has access to it.

Burning the most tokens isn't a moat anymore.

The top mfs are the ones that spend tokens on whatever the biggest bottleneck is right now.

As they can consistently find where the constraint to scale actually is.

Your Grokbot, Claude Code, Hermes agents etc. are only as good as your ability to decide what to build first, and your process for executing it.

There's no $300/m subscription for critical thinking. Or for understanding how a business (or department) works as a high level system.

That shit's still 100% on the human.

So talent is the real moat (always has been).

And if you focus on getting and keeping the right people, while everyone's crying about Grokbot getting nerfed, you'll be too busy scaling to give a shit.

[Abyssus @AbyssusErigo]

Grokbot isn't enough.

Because everyone has access to it.

Burning the most tokens isn't a moat anymore.

The top mfs are the ones that spend tokens on whatever the biggest bottleneck is right now.

As they can consistently find where the constraint to scale actually is.

Your Grokbot, Claude Code, Hermes agents etc. are only as good as your ability to decide what to build first, and your process for executing it.

There's no $300/m subscription for critical thinking. Or for understanding how a business (or department) works as a high level system.

That shit's still 100% on the human.

So talent is the real moat (always has been).

And if you focus on getting and keeping the right people, while everyone's crying about Grokbot getting nerfed, you'll be too busy scaling to give a shit.