Try Pro free

Latent Space · 5 min · Nov 9, 2026

One goodwill error can invalidate an otherwise polished deal model

A simulated banking agent builds a polished LBO model but mishandles seller goodwill, shifting cash flows by about 10%.

The episode’s best minutes

Full analysis
  1. 1:25:35One goodwill error can invalidate an otherwise polished deal model5 min
  2. 1:46:36An agent can beat an Excel grader by listing every number2 min
  3. 2:11:20Loan automation can produce illegal pricing from benign inputs5 min
  4. 5 more moments in the full episode
“It doesn't apply the knowledge during the key step.”
CSCollin Schweikerat 1:26:34 · Latent Space
1:26:34

Takeaways

  1. The agent knew the tax rule but failed to apply it at a key step.
  2. One wrong assumption affected thousands of linked spreadsheet cells.
  3. A polished deliverable can hide errors that undermine client trust.

About this segment

A simulated banking agent builds a polished LBO model but mishandles seller goodwill, shifting cash flows by about 10%. The failure shows why checking formulas alone cannot establish financial judgment.

CS

Collin Schweiker

Handshake AI

  • Shawn Wang (swyx), Host · Co-founder, AI Engineer

    Wrote “The Rise of the AI Engineer” and founded Smol AI, maker of AI News.

  • Alessio Fanelli, Host · Founder, Kernel Labs

    Partner at Decibel, backing technical founders who build developer tools.

From “What Frontier Labs Buy: A Data Deep Dive with Handshake AI — Garrett Lord & Team”, Nov 9, 2026. Watch the full episode

Transcript

From the transcript Latent Space publishes with the episode.

  1. 1:25:39

    it, let it know when it's ready for your review, like, that's, that's a great way to allocate time more efficiently, right? Also, just to jump it, is this the answer correct? Is it a successful case that we're going through? It is, it is not correct. Okay. [laughing] Like we shouldn't have been super relieved. Okay. Yeah. Uh, the, the big issue is that when it was building its model in Python, it didn't realize that it was making a decision on the existing goodwill that we talked about.

  2. 1:26:07

    And, you know, if, if it had, if it had flagged it for review or it had, um, you know, said, "I'm not sure about this. Let me think about it." Like, if you, if you go and ask this model today, how is existing goodwill on the seller's balance sheet treated from the perspective of a, of a, of a purchaser for a three three eight H ten tax treatment, it knows the answer. It's like, well, in that scenario, you would not actually use it in the basis, and it's irrelevant for this calculation. It just doesn't apply the knowledge. Excuse me? It doesn't apply the knowledge. Exactly. Exactly.

  3. 1:26:38

    It doesn't apply the knowledge during the key step. So, you know, in, in action twenty, it's supposed to, you know, basically build this, this f- calculation, you know, this, this, this whole model, uh, and it just... it- this one line here where it subtracts the excess goodwill from the excess basis for the step-up calculation basically poisons the entire valuation, the entire model, and it doesn't, it doesn't have...

  4. 1:27:04

    There's nothing in the trajectory that suggests it was, it wasn't sure about the decision it was making or, you know, going through its reasoning, and, uh, frankly, those are the worst kind of errors because if, if it knows that there's something to surface to you, like at least that's helpful, but here it's just hidden in that it didn't realize it was making a key decision. But again, this is... What's, what's ironic or interesting about it is when a human being does this, they would absolutely... This would be... If this was my, you know, job, this would be my full focus.

  5. 1:27:32

    I probably would've talked to an accountant and a lawyer, you know, two times each before I sent this to my VP. It's like, "Hey, did I get this right?" Like, "I've never done one of these before. Like, can you help me?" And they're like, "Yeah, no, this is how we did it before," right? And this information was in the environment. It was, it was in the email. It was in the OneNote. You know, it, it was a very realistic, uh, application, but it just, it, it didn't realize what it was doing, and it basically, um, you know, it shipped it. It, it... Sorry, it, it checked its work. It checked its work on the, the...

  6. 1:28:04

    It checked the Python against the Excel, and it tied it out, and it was like, "Great, I'm done. I didn't make any errors. Perfect. Like, this is, this is good to go," right? And then it, it, it mailed it to Sanjay, and it, you know, it shipped the error, and it didn't flag anything, you know, uh, as a, as a major concern. And this is the, uh, this is the actual deliverable that it created, and this is why it's so challenging today to audit this stuff, um- Mm-hmm...

  7. 1:28:32

    and, and use it because, you know, on its surface, it actually looks, you know, like a fairly, you know, robust model, right? And again, there's, there's over twenty-six hundred formulas in here and over four thousand, um, cells, but it's, it's just this line. It's just this row sixteen- [laughing]... that, like, blows up everything, and what it does is it, it... the effective impact is that it, it decreases the, the area...

  8. 1:29:00

    It, it varies the, the, the true answer by, like, ten percent in terms of cash flow, and it messes up the, the cash, you know, every, every period thereafter. So this could do two things, right? This could completely embarrass you in front of your client, and it could lose you the mandate because the worst thing that, you know, can happen to one of these advisory companies, you know, whether it's a major consultant or a major bank on the M&A side, what are they selling?

  9. 1:29:26

    They're selling trust and competency and confidence, right? Like the phrase, like, "Nobody got fired for hiring McKinsey or Goldman Sachs," right? It's like because they just have the brand equity where when they walk into the room and they tell you something, you, you trust them that they're right. So the worst thing that can happen is you go in there and the CFO and the CEO is looking at your output and they're like, "Something's weird about your net basis step. Hold on. Hold on. Don't go to the next page.

  10. 1:29:50

    Like, can we, can we talk about this?" And then, you know, you get a lump in your throat and you're like, "Oh man, like, you know, what did I do?" Mm. And they're like, "Well, you know, your competitor yesterday came in, like the- their number, your number is different. Like why, why is it different," right? And then one of you is wrong and, you know, people have lost, you know, multimillion-dollar deals for like way less than that. Yeah, sure.

  11. 1:30:11

    Or, or you're an investor and you, you know, you overpay or underpay because, you know, again, like five percent off, you know, the true number doesn't sound like a lot, but it compounds over time, and, uh, particularly in finance where everything is, is data-driven and number-backed, uh, becomes a huge issue. So it- again, it's, it's, it's functionally unusable, and frankly, like I wouldn't... You know, it, it'd be very difficult to go through this thing without some kind of attention helping you understand where you should be looking.

  12. 1:30:43

    You know, every, like the formatting is clean, like the structure makes sense, but there's these little gremlins in the model that like when they pop up, um, you know, it, it becomes a usability and a trust issue.