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
GOODBYE MEDIA BUYERS. HELLO CLAUDE FABLE 5.2.
⠀
I turned a whole Meta ads team into one engine. 1 router and 8 agents that scrape, make, launch and scale, and all of it is free.
⠀
Spy | rival ads
Scrapes the Ad Library for ads
live 60+ days. Steals the angle,
never the ad.
⠀
Angle | who buys
Turns 1,000 rival ads into
3 angles to test this week.
⠀
Hook | 50 per angle
Questions, confessions, POVs,
pulled from your buyers' own words.
⠀
Static | made in HeyOz
Reviews, us vs them, bad news.
Your proof, turned into static ads.
⠀
Script | UGC briefs
Hook, problem, proof, offer.
8-15 seconds, product by 0:03.
⠀
Studio | made in HeyOz
Video ads rendered in
Kling 4.0 + Seedance 2.5.
⠀
Buyer | launch
One test campaign, one angle
per ad set, named the same way.
⠀
Scaler | day 1, 3, 7
Cuts losers on day 3.
+20% on winners by day 7.
⠀
One router asks first: worth testing?
You approve every change.
⠀
Eight agents.
Open the one you need.
Hand it to Claude.
The team starts working.
⠀
Free access to the full engine. The word is on the card.
I'm deleting this soon because it's lowkey unfair.
25 WINNING ADS.
All still running for Shopify stores making $150K+/month. Copy the hook, swap the product, and you have your next ad.
Comment "ADS" and I'll DM you all 25 with the store behind each one for FREE.
FREE for 48 hours.
day 6 of using @OpenBot_ + fable 5.2 instead of @bot
I press record and yap about everything on your mind.
In real time different topic cards get loaded with relevant context and skill md files on autopilot
my bots go to work for me before Im done speaking. have legit cleared a to-do list of 23 with this in 6 minutes and 23 seconds
the beauty of it all is that my bots are connected to all the tools I need and have complete context over every department of my business and personal life
so they actually do the job for me instead of delivering a slop response
@norbertbodziony@AKolere_@bot he means like a central place that makes interact with different bots, host your tools and just a UI layer on top of your agent infrastructure
Here we go again with @bot 's usage rants literally 2 days after the fix
- Can't use frontier models like fable 5.2 in the gold rush era of AI for the only thing that matters the most in your world, your business and livelihood.
- Long term planning is obliterated since usage and intelligence of grok bot models go up and down on a 48 hour cadence
Your competition will 1000% beat you while you're entangled with figure out what is @elonmusk's mood today
Switch to an open source model like @OpenBot_ + frontier engine ( like opus or fable or some miracle AGI model that will come out on a Tue afternoon in march )
Own your servers, workflows, memory and infrastructure
This is literally renting vs buying in 1960's housing. wake up.
@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.
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
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
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?
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.