Creator of Athena-709M
San Francisco, CA
Joined January 2013
- Tweets1.1K
- Following308
- Followers1.2K
- Likes2.3K
Today, we’re releasing Athena (mvrko-sim-1), the flagship Large Event Model from @markopolo_ai that beats GPT-5.6, Claude Opus 4.8, and Claude Sonnet 5 in OPeRa public benchmark for Shopping behaviour prediction!
Athena introduces a completely different approach to understanding digital behavior.
Most systems record actions after they happen. Athena models the sequence behind them to predict what a shopper will do next and exactly where they will do it, before the action even takes place.
Athena vs. frontier models:
We evaluated Athena on the full OPeRA test set alongside GPT-5.6, GPT-4.1, Claude Sonnet 5, and Claude Opus 4.8.
Athena achieved 24.5% strict exact match scoring the highest among the five models evaluated.
Athena is not a general-purpose language model.
It is a Large Event Model built to understand behavior as a connected sequence. It combines the page someone is viewing, the actions that brought them there, and the goal they are trying to complete and then predicts the exact next browser action and target element.
That distinction matters.
Today’s digital systems largely react after someone clicks, abandons, purchases, or leaves. Athena creates the foundation for systems that can understand what is likely to happen before the outcome.
Together with @RubaiyatFarhan, and the team at @markopolo_ai, we built Athena from years of work on shopper behavior, digital journeys, and behavioral intelligence.
Commerce was our first proving ground. Great thing is, we’re now releasing Athena publicly so builders can adapt the model to new datasets, industries, and problems. We’re seeing early usecases in Cyber Security, Gaming, Mobile App Ecosystem, Retail and more!
Athena is now live on Hugging Face!
We built the foundation for relevance and predictability!
Now, let’s see what the world builds on top of it.
Links in the first reply.
What is OPeRA?
OPeRA is the public dataset and benchmark used to evaluate Athena’s next-action prediction.
Dataset:
huggingface.co/datasets/NEU-…
Research paper:
arxiv.org/abs/2506.05606
Tasbin retweeted
BREAKING: Starlink gets approval to export unfiltered internet bandwidth from Bangladesh to neighboring countries.
• Bangladesh approved Starlink’s bandwidth export proposal.
• Traffic will serve foreign customers only.
• Initial capacity request: 40 Gbps.
• Scalable up to 400 Gbps.
• Bandwidth expected via BSCCL
• Could turn Bangladesh into a regional Starlink connectivity hub.
Starlink keeps expanding global internet access.
🤖 Made with AI
Tasbin retweeted
Bangladesh’s Growing Role in Russia’s Pivot to Asia Strategy
russiaspivottoasia.com/bangl…
The Bangladesh and Russian Foreign Ministers have been meeting in Moscow. We provide an extensive analysis of what was discussed, including full trade details and likely bilateral developments.
Ecommerce storeowners and marketers already have useful customer behavior data, but much of it stays buried inside Shopify, analytics tools, email platforms, and ad dashboards.
These data usually come from three places:
store analytics: orders, products purchased, discounts used, inventory status
website events: product views, cart activity, searches, checkout behavior
channel engagements: email clicks, SMS clicks, WhatsApp replies, push opens, etc.
The biggest challenge is to unify these data, turn them into actionable information, and decide what should happen next.
That is where a good marketing automation strategy comes into play.
Your store should be able to collect customer behavior directly from its website, checkout, and order history instead of relying ONLY on ad pixels or platform-reported (Shopify, WooCommerce) data.
Server-side or cookieless tracking can make this more reliable when cookies, browser limits, and ad blockers make data incomplete.
The idea is simple:
1. capture what shoppers do
2. connect it to who they are
3. use it to trigger the next best action.
That is how:
- a product view becomes a browse abandonment flow
- an add-to-cart becomes a cart recovery reminder
- a 45-day purchase cycle becomes a replenishment campaign
- an out-of-stock product becomes a back-in-stock alert
- a discount-only buyer stops receiving the same offer as a full-price customer
This is the way to master marketing automation for your online store.
Here is a practical breakdown of 10 unique strategies brands can use now:
markopolo.ai/blogs/ecommerce…
Tasbin retweeted
You have no experience.
You’ve never started a company.
You’ve never had a full time job.
Nike is going to kill you.
You’re a kid.
You don’t have technical skills.
You shouldn’t build hardware.
Apple is going to kill you.
You can’t build hardware.
You can’t measure heart rate non-invasively.
Athletes don’t care about recovery.
Under Armour is going to kill you.
It won’t be accurate.
You don’t listen.
You’re an ineffective leader.
You can’t recruit great talent.
You’re going to have to pay every athlete.
You can’t measure sleep non-invasively.
It’s too expensive to research.
Athletes are a small market.
The product costs too much to make.
The product costs too much to sell.
Your valuation is too high.
Consumers aren’t going to want it.
Hardware is too hard.
You should measure steps.
Fitbit is going to kill you.
You can’t build a marketing engine.
You can’t raise enough money.
You need a real CEO.
Google is going to kill you.
You can’t be a subscription.
You can’t build a brand.
You can’t do consumer in Boston.
Your valuation is too high.
You shouldn’t make accessories.
You shouldn’t make apparel.
Lululemon is going to kill you.
You can’t predict Covid.
Stay in your niche.
You are going to run out of money.
You can’t build a health platform.
Amazon is going to kill you.
You can’t measure blood pressure.
You can’t get medical approvals.
The market is too small.
You don’t understand AI.
The market is too competitive.
It won’t work internationally.
The supply chain is too complicated.
You can’t build an AI.
You can’t raise enough money.
It’s too competitive.
Healthcare isn’t going to want it.
…
Just keep going ✌️
Tasbin retweeted
Today at Markopolo, we’re introducing ATHENA… The first behavioral foundation model built specifically for digital commerce.
Most marketing tools react after a customer leaves.
ATHENA predicts shopper behavior in real time, helping businesses respond before the moment is gone.
This is a leap toward truly AI-native commerce.
Learn more: markopolo.ai/newsroom/athena…
#ecommerce #shopify #markopolo
Tasbin retweeted
How can I recover more abandoned carts?
Start using Markopolo AI to analyze shopping patterns, anticipate what shoppers need, and send tailored reminders via email, text, or WhatsApp.
Our customers hit 25-40% recovery rates—2-3X the industry average.
What’s your top cart recovery strategy?
Tasbin retweeted
When our AI understands your customers better than your sales team 👀
Watch how our voice agent figured out why Jamie hesitated and turned a “maybe later” into a “just bought” in just two minutes!
Tasbin retweeted
More channels don’t mean more conversions.
Timing, context, and the right channel do.
That’s behavioral orchestration.
Tasbin retweeted
Connect your CRMs and customer data so our AI has all the context it needs to drive smarter campaigns for you!
Tasbin retweeted
Your brand is faking personalization❗️
You're treating your customers like clones with the same cart flow as thousands of others. That's spam, not personalization.
The taste always wins in terms of design
saaspo.com
