Turn financial models into production infrastructure. API-accessible. AI-native via MCP. Self-documenting. Born from a platform acquired by Goldman Sachs.
NY Metro
Joined April 2013
- Tweets528
- Following2.9K
- Followers3.3K
- Likes374
Pinned Tweet
Check out our new #MCP Server in action. You'll see #Claude reading from and writing to a ClearFactr model, using it like an on-the-fly calculator, and saving scenarios.
This opens up a whole new world of possibilities for #AI #Agentic workflows, but where the calculations remain 100%:
✅ Deterministic
✅ Explainable
✅ Auditable
✅ Governed
Lastly, it bears spelling out what's in the video intro: ClearFactr's MCP Server can *also* create models from scratch, but when it does that, they go directly into ClearFactr.
They're not first created as standalone Excel files.
If you're already drowning in spreadsheets (and associated operational risks) from too many files to count, unleashing the robots to make thousands more of them might not be the best path forward. Additionally, creating them "the ClearFactr way" means they can be dramatically smaller, faster, easier to understand, and less likely to break, because the agents can take advantage of all of the native platform capabilities.
Contact us to take this out for a spin!
ClearFactr retweeted
Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead.
You guys are the frontier. By any reasonable metric — market share, revenue growth, model capability — the two of you have a duopoly on frontier intelligence. You’ve also claimed the lead is widening because of recursive self-improvement.
I don’t see what you see in the lab. If the unreleased models are scary enough that you think you should slow down, I support your decision to be responsible.
But stop pretending you need anyone else’s permission. Stop pretending antitrust law has to be suspended so you can form a cartel. Stop pretending you need a regulatory approval process that supersedes product liability. Stop pretending METR is independent when it is intertwined with Anthropic’s investors and staff. Stop pretending you need those same evaluators to police competitors who aren’t even at the frontier.
Most of all, stop pretending the motivation to slow down is purely altruistic. You face massive product-liability exposure if your products enable a truly damaging cyberattack. The market already punishes models that behave in unpredictable or unauthorized ways. After the Hugging Face episode, it is simply good business for OpenAI and Anthropic to trade some raw power for reliability and predictability. Call it alignment if you want. It is also just giving customers what they want.
Pacing the frontier would also create breathing room for a more intelligent conversation about regulation than Bernie Sanders’ “shut it all down.” China is very unlikely to join a global agreement, as you know, and that has to be taken into account as well.
So go ahead and pace the frontier. You are the ones setting it. The easiest way not to build superintelligence is for you to agree not to build it. Demanding your preferred regulatory framework as the price of that will look like blackmail of the public and the political system. So just do it.
If you do, you’ll buy goodwill for the next conversation. If you don’t, we’ll know this was just another bid for regulatory capture — or an election-season psyop.
ClearFactr retweeted
Researchers forced Claude, GPT, Gemini, and Kimi to play Civilization VI to completion.
What they discovered exposes a terrifying blind spot in modern AI.
Playing a massive 4X strategy game to the end requires something entirely different: long-haul execution. Juggling economics, science, military, and diplomacy across hundreds of turns.
The goal was to see how AI handles multi-step complexity.
Instead, they watched the models repeatedly implode due to two bizarre psychological flaws.
Flaw number one: Total situational blindness.
In one-third of the games the AIs lost, an enemy was actively marching toward an obvious victory right in front of them. The data was sitting right there. The model simply failed to look.
Flaw number two: Severe organizational ADHD.
The AIs were great at making grand strategic lists. They would meticulously write down: "Next step, build a city."
Then, 10 turns later, they completely forgot they wrote it and did nothing.
The researchers realized this isn't a lack of raw intelligence.
It’s an allocation failure.
We assume that if an AI can ace a math test, it can manage a complex, multi-day project.
It can't.
When tasks stretch across a long horizon, the model's internal attention drifts. It loses the thread of its own intentions. It drops long-term goals for immediate noise.
Everyone is racing to hand over complex workflows, financial portfolios, and autonomous operations to AI agents.
We think the bottleneck is making them smarter.
but no.
The bottleneck is making them remember what they were doing ten minutes ago.
ClearFactr retweeted
Microsoft is making moves again.
A quiet little Python tool just shot to the top of GitHub’s trending charts.
100,000+ stars.
It’s called MarkItDown.
And it does something deceptively simple:
It turns almost any file into clean Markdown.
PDFs. Word docs. PowerPoints. Excel files. Images.
Drop a file in. Get structured Markdown out.
Sounds small.
It’s not.
Because one of the biggest bottlenecks in AI workflows — especially RAG systems — is getting messy, real-world documents into a format models can actually use.
And real-world documents are brutal.
PDFs are chaotic.
Word docs are full of hidden formatting junk.
PowerPoints are messy and often image-heavy.
Spreadsheets can be a nightmare to parse cleanly.
That’s where this gets interesting.
MarkItDown strips away the friction and gives you something LLM pipelines can actually work with.
In other words: less preprocessing, less pain, faster AI implementation.
Even better, this isn’t some random side project.
It’s an official Microsoft open-source tool.
Free. Commercially usable. Practical.
I tested it on a 200-page PDF.
A few seconds later, I had Markdown that was shockingly clean.
And that’s what big tech does at its best:
They take an annoying, universal problem that everyone has been duct-taping together…
and turn it into a simple standard.
That’s why this matters.
It’s not just a file conversion tool.
It’s infrastructure for the next wave of AI applications.
Get it here: github.com/microsoft/markitd…
===
🚨 Want to learn how to build + ship AI and Data Science projects (that businesses actually want in 2026)?
I am hosting a free workshop to help you get started with AI + DS projects in Python.
Register here (500 seats): learn.business-science.io/ai…
ClearFactr retweeted
China published the most uncomfortable paper on vibe coding.
ETH Zurich tested 100 developers in a controlled, commercial-grade vibe coding environment to see who actually succeeds.
The findings are brutal.
The researchers tracked computer science achievement, written communication skills, and general cognitive reasoning.
They wanted to see what actually predicts vibe coding proficiency when you never touch a line of source code yourself.
Two major predictors emerged.
Written communication proficiency mattered. The ability to structure thoughts and articulate intent unambiguously in text directly impacts what the AI builds.
But that wasn't even the main takeaway.
Computer science achievement was a massive, dominant predictor of success.
Even when researchers controlled for general intelligence and reasoning skills, CS background still heavily dictated who built working software and who completely crashed.
In fact, CS knowledge contributed roughly twice the unique predictive variance of writing skills alone.
Why? Because vibe coding isn't about writing code. It’s about debugging logic.
When an AI agent builds a complex application and quietly breaks an edge case under the hood, a non-technical user looks at the glowing UI and assumes it works.
They don't know what questions to ask. They don't know what logic to challenge. They lack the mental models to recognize architectural catastrophe.
You can prompt your way past syntax.
You cannot prompt your way past a fundamental lack of engineering intuition.
The hype told us that learning to code is dead because language is all you need.
The data just proved the opposite.
To truly master the vibe, you still need to understand how the machine thinks.
A 10x+ better way to do scenario analysis, in a familiar spreadsheet. A tall claim, but here’s the proof:
linkedin.com/posts/deanzarra…
ClearFactr retweeted
Your entire life will change when you realize energy is the most attractive human trait. Not looks, wealth, or status. Energy. Start walking into rooms with genuine enthusiasm, curiosity, and interest. Watch what happens. You become a magnet for the highest quality people. Energy is contagious. Spread the kind you’d want to catch.
ClearFactr retweeted
What is a model?
At a bank, it is the math behind almost every decision: who gets a loan, how much capital to hold, which transactions look like fraud etc etc etc.
In April, the Fed, OCC and FDIC sunsetted the guidance banks have used since 2011 to check that math. The new rules cover traditional models but explicitly carves out generative and agentic AI, because it is moving too fast to freeze into guidance. Essentially, each bank is now responsible for governing the fastest moving part of its own technology by itself...but will still have to explain it to examiners when asked.
If that exam were tomorrow, most banks would find it difficult to reproduce an accurate record of how AI was used, in which way, with which artifacts, for every decision where AI was involved.
This is where 8090 Software Factory helps: carry audit trails and evidence with the software itself, so every change and every model decision ties back to a requirement someone approved.
Learn more here: bit.ly/46q2SOe
ClearFactr retweeted
People will find this interesting as to why that debt will be the tail wagging the dog:
linkedin.com/pulse/us-federa…
ClearFactr retweeted
Underrated life advice: Just be easy to work with. Show up on time. Do what you said you'd do. Bring solutions, not problems. Never create drama. Be responsive. Be emotionally consistent. Be kind. People will always want to support someone who just makes their life easier.
RT @PeterSchiff: The national debt is above $39.9 trillion. So there is less than $100 billion to go to his $40 trillion, which will happen…
ClearFactr retweeted
Mark Cuban on the next job wave.
Customized AI integration for small to mid-sized companies.
"Software is dead because everything's gonna be customized to your unique utilization. Who's gonna do it for them... And there are 33 mn companies in the US."
That person is called a Forward Deployed Engineer.
And it's the hottest job in tech right now and most people have never heard of it.
Here's the no-BS guide to what it is, what it pays, and how to become one ↓
Bookmark this.
ClearFactr retweeted
Amazon is putting $1 billion into hiring thousands of engineers to go sit inside other companies and build AI systems for them.
Friday the stock had its best day since 2012. Up 15.3%, AWS growing 37%.
And this is the clearest signal yet that implementation is the business. Anthropic launched Ode two weeks ago. OpenAI stood up the Deployment Co. before that. Palantir has been running the model for over a decade. Amazon is the biggest cloud provider on the planet and the first hyperscaler to formalize it, and they're doing it while they've cut 30,000 corporate roles since 2022.
We've been running this exact model at Boom since before it had a name, 87 clients in.
And this is the opportunity right now.
The work is walking into a company, mapping how it actually operates, consolidating everything into one system, and layering AI on top of processes that hold. Priced on outcomes instead of hours. Weeks instead of quarters. That's the whole business.
There's a lot of noise around this right now. Agencies selling agents to companies whose underlying processes are broken. You can drop an agent into chaos and all you get is faster chaos. The adoption rates there are less than 50%.
The other thing that people are missing here is the partner motion. AWS is credentialing outside firms to deliver this work under their own engineering bar. Invite-only right now while they validate it, opening up after. A company with thousands of engineers and a billion dollars in budget is out looking for help because the demand is bigger than what they can staff.
The accounts they're taking themselves look like what you'd expect. The NFL, Cox Automotive, The Allen Institute, etc.
Meanwhile there are hundreds of thousands of companies doing $2M to $50M a year running on 20 disconnected tools with full access to the best AI ever built and no idea how to apply it.
Nobody at AWS is calling them and nobody at Ode is either.
Amazon is showing you what every company is going to be buying over the next several years.
Go be the one who builds it for them.
ClearFactr retweeted
I’m convinced that intelligence is overrated.
Intelligent people are more likely to overthink, overplan, and overanalyze. They hide behind motion that doesn't create progress. They fear the judgment of others if they're proven wrong.
The truth is that intelligence is abundant. Especially now. AI is making it a commodity. Courage is not. And it can’t be replaced. The people you admire are the ones who had the courage to act. They aren’t more talented than you. They aren’t smarter than you. They just took action when you didn’t.
I often wonder how many extraordinary people wasted their entire lives waiting for permission that never came. Permission isn't granted. Permission is taken. You get to tap yourself in whenever you want. You can just do things.
Courage beats intelligence. Remember that.
ClearFactr retweeted
Best article about how the tech behind AI drives the business of AI, that I’ve ever read
open.substack.com/pub/thealg…
Late last Friday afternoon, I was on a call with a customer who wanted to build a ClearFactr model from scratch based on his eye-wateringly large and complex #Excel file. Where he previously had a liability filled with operational risk, he’d be integrating a highly-governed, leveragable software asset into the rest of his system.
Watching him encounter a few ‘paper-cuts’ was eye-opening, but we also agreed some new capabilities would help tremendously. I said to him “No promises, but I think I’ll be able to get this done quickly.”
Saturday morning, we shipped the following:
✅ When importing an Excel file, you can now choose which sheets in the workbook you want to import, or skip.
✅ When specifying a range parameter for a formula, clicking a spanning header will automatically fill in the associated column names. ClearFactr automatically makes these spanning headers when adding time-based columns to your model.
✅ The dropdown menu on any spanning header now includes a Rename item. This was always possible – now it’s just easier.
✅ In the process of testing this work, a number of edge-case bugs were discovered that had been there for some time. All of those were fixed and our test suites were increased accordingly, which will pay permanent dividends to all users across all future versions.
h/t to Claude’s new Opus 5. Its handling of the spanning header range-selection feature, in particular, was astonishing. This was complex UI coding involving some of the most intricate aspects of the system. It was shippable on the first try.
Got an Excel-driven workflow that you know is fraught with risk and wasting everyone’s time? Contact us and we’ll help you replace it in a way you never thought possible.
#RiskManagement #AI #Claude #Opus5 #Excel #Spreadsheets
ClearFactr retweeted
.@pmarca's advice to college students: "Gain AI superpowers. I think it's actually very straightforward."
"You have the enormous stroke of luck that you have arrived at the moment in which there is this new capability for augmenting human ability on a thousand fronts at the same time, that's just dropped into our laps, and it's going to get much better from here."
"You are gonna have the opportunity to have this be something that is absolutely key to your skill set and key to everything that you can accomplish as a professional or as a creative for the next 50 years."
"I would just lean in incredibly hard on that. Walk into every job interview with, 'Here's my portfolio, resume, whatever. Here is how I use this technology. Here are the capabilities that I'm bringing to the table.'"
@eriktorenberg @MTSlive