For the foreseeable future, if you want

[music] to make sure that your numbers

are definitely correct, you do need some

pre-processing and some built-in checks.

>> How have you thought about that

transition of the instructions from the

investor to the order?

>> You know, prompting is becoming becoming

a a lot less important. And I believe

we're the only people on the market that

that are willing to do a no

hallucination guarantee, [music]

which does give you a bit of a sense of

how much risk there is in the average

financial AI software.

>> [music]

>> All right. Welcome to the next episode

of Invest with AI, where we explore the

intersection of investing and

fundamental research. I'm really excited

to have Chris Brinati here with us

today. Chris was the co-instructor for

the first iteration of the Fundamental

Edge AI accelerator.

Um, has been, you know, someone who's

really taught me a lot about deploying

AI in investment research, and is the

founder and CEO of Hudson Labs. So,

thanks so much for being here, Chris,

and maybe start just telling us a little

bit about your background, how you got

into AI and finance.

>> Awesome. Thanks so much for having me.

As always, a pleasure.

Uh, yeah, I'm I'm Chris Brinati. I've

been around for a minute now.

Uh, I got my start

I

way back when as a data scientist at a

corporate governance advisory firm,

uh, where I focused on sort of pre-LLM

securities filing processing,

and was

building my career as AI was making

really big moves, and LLMs specifically

in the research community. And this

would be would have been back in say

2017

2018,

we started seeing auto suggest on our

phones. Uh the research community was

getting super excited about LLMs. And

yet at my workplace, I was being hailed

as, you know, like the ultimate

innovator running uh essentially all

word-based counts on Canadian corporate

disclosure. Uh

and saw that and saw, you know, sort of

recognized the fact that

often times, at least historically in

finance,

uh we're in corporate governance and in

the corporate fields we're many years

behind consumer technology uh and we

were not adopting LLMs nearly as quickly

as,

you know, iPhone,

Gmail, all of these these cool

applications, quit my job, co-founded

Hudson Labs with uh the LLM guy here in

Canada, who is Suhas Pai. If you haven't

purchased his book, Designing LLM

Applications, I highly recommend doing

it. It's published with O'Reilly. It's

now been translated into over 10

languages, including Polish. Uh and uh

Suhas does a lot of really cool uh

training and onboarding around AI

agentic uh

modeling right now. So, do give him a

follow and uh attend some of his

seminars.

Uh yeah, and then we we uh launched what

was then Bedrock AI, now Hudson Labs.

And we focus on AI for institutional

finance. Our

big contributions to AI research have to

do with materiality ranking uh and

precision. So, being able to

maintain accuracy over very large

contexts.

I'd be able to pull numbers,

pull guidance,

pull sentiment in a way that's

consistent, etc. We also

uh

started our business with a forensic

risk score

and

for for many years now have been popular

among the short community, among plenty

of class action lawyers, and D&O

insurers, as well as big buy-side firms.

>> Great. Great. Maybe um

I I I always found

um I always get like super excited on

things and then I call you and you're

like, "Well, let's talk about the

precision

of uh of these elements." And precision

is so critical

for finance use cases. You know, you can

sort of when so many AI things create

these impressive-looking

demos,

but if the numbers aren't at a level of

precision, they're just not

institutionally useful. How do you think

about just the broad challenge of

precision with large language models,

which are non-deterministic

by nature? And And what are a few of the

key vectors that you've thought about

for years about making these tools more

precise?

>> Yeah, it's a really tricky problem and

it's been a persistent problem. It's

definitely getting better

from a from a generalist perspective,

but

for the foreseeable future, if you want

to make sure that your numbers are

definitely correct,

you do need some pre-processing and some

built-in checks. It's pretty much

impossible to just take a generalist

model, apply it to finance, and be like,

"Okay, great. These This is all going to

be right."

Um for reference,

we did a test on all of the

state-of-the-art models

a few months ago now.

Uh, so

it's been before

before 5.5, whatever the the cloud and

open AI models were a few months ago,

and whenever you asked for a metric for

more than four to eight periods, you'd

get an incorrect number 30% of the time.

Uh, so when you think about

hallucination right now, there's

mostly a problem or the biggest problem

when you start

getting beyond comfortable context

limits.

Uh, and and that's one of the big

problems we focus on.

Uh, it will continue to get better, but

as you've seen so far, it's getting

better much much much more slowly than

things we've seen like reasoning, uh,

mathematical elements, all of those

things. We did, as of yesterday,

formally launch our no hallucination

guarantee. Uh, so we're pretty feeling

incredibly confident about our ability

to not pull incorrect numbers, uh,

restatement adjusted error-free numbers

across a five-year period. Uh, that's

all done using AI architecture rather

than just thinking about the last

generative step. Um, and, you know, it's

it's taken us a while to, um,

be able to do that five-year period

restatement adjusted perfectly, uh, but

we're we're feeling really excited about

that, and I believe we're the only

people on the market that that are

willing to do a no hallucination

guarantee, uh, which does give you a bit

of a sense of of

how much risk there is in the average

financial AI software.

>> What did What does that entail to

uh, gain the conviction to offer a

guarantee like that? Like you said, pre-

pre-processing and built-in checks. Like

what is that? How hard is that problem?

What are the big work streams to sort of

take the general models and convert them

to that hallucination-free layer.

>> Yeah, uh

if you want to think about

hallucination,

you I think it's chapter 11 of Suhas's

textbook.

He talks about the the place where you

end up with hallucination is when

the model doesn't know the answer and it

doesn't know it doesn't know the answer.

That is the highest risk

time when you're not feeding

the model the information it needs

and it doesn't know that.

So, as you can imagine,

when you start

moving beyond these comfortable context

limits, that's when you start seeing

hallucination in a generalist cell.

How do we overcome that? We talked about

preprocessing.

So, once you get towards more than say

four eight quarters,

you need to start using search and

retrieval

to get the right information.

And one of the reasons so many tools,

I'm not going to name names, but have

issues in that long time horizon

is because search and retrieval is

really hard.

If you're just looking for revenue and

you're searching for it again across 20

press releases,

you're going to be pulling in a lot of

noise.

And if you think about how complicated

giving getting a revenue right,

depending on what you're asking for, can

be,

you know, maybe you're looking for a sub

segment

9 month

and instead you're going to be getting

numbers

in your retrieved element that are

consolidated and three-month

Uh

so those are the long horizon complex

queries. In order to fix that problem,

you do need some pre-processing where

your embeddings need to have information

about what is this, what time period is

it related to,

uh and that allows the model to be able

to select the information it needs and

actually use it. And when we talk about

guardrails or checks, it's about making

sure

you have specific pathways

uh that exist so that the model knows

that you're asking for a KPI poll and it

should be able to expect this

information and if it's not getting it,

it just gives you an error.

>> Can I ask a uh

lazy uh layperson question?

How um if you think of I definitely

appreciate the context window challenge,

how does this like how does something

like Notebook LM

solve this where presumably it's it as a

user that doesn't understand the

technical in and out of it, it feels

like the context window is much larger.

Just Like I can give it 500 files.

It seems to be more accurate in the uh

nature of it. It's not as intelligent.

It's like pure retrieval.

Um but can you How does that compare?

Like like what's happening under the

hood in a Notebook LM versus a

generalist model versus a Hudson's uh

labs um

approach?

>> So one of the reasons that Notebook LM

feels better is because it has a more

intelligent search.

Yeah. So it's going to be it's not

finance specific. Obviously, it's not

numeric. It's not built for pulling

KPIs. You are going to still even with

Notebook LLM, you are going to Notebook

LM.

Uh you are going to run into that um

sort of eight quarter plus

failure mode. I don't know if you've

tried it.

Uh

so

for the same reasons around search.

But it is using a more advanced search

mechanism. So it's not about it's not it

doesn't have a a better context window,

it just has better search.

>> Got it.

>> Yeah.

>> And so you Hudson

you being finance experts, you can

basically customize that search process

way better than any than than a

generalist approach.

>> So if you want to think about Hudson

Labs versus Notebook LM versus just

having a Claude instance,

what's happening

the back end is a big part of the

difference. So whenever we take in an

SEC filing, a torrent script, etc., it's

we use vector databases. So we're

converting

a sentence, a word, a paragraph to an

embedding.

Are you uh familiar with or a vector?

Yeah.

>> Mhm.

>> So

there's lots of different ways that you

can do that.

>> Yeah.

>> And you should be doing that. But if

you're using Claude,

your data isn't in a vector database,

which is one of the way reasons that it

can be so expensive.

Uh

and if you're using Notebook LM, it's

uh

it's essentially search rather than a

vector database.

>> Got it.

>> But if you have a vector database or you

have a more sophisticated back end, you

can

do a lot of really cool things in

pre-processing that facilitate both

accuracy, relevance, and completeness on

the front end.

>> Got it.

>> So in addition to to be able to if you

have these things as as embeddings, you

can

give metadata to the model

in addition to

containing better information about what

that sentence is.

And you can do cool things with your

embeddings. For instance, the way that

we store embeddings, we have meta

declarations not just about is this

uh a KPI or not, is it forward-looking

historical, but also information about

sentiment.

Which is why I believe we're the only

platform where you can do

sentiment-based screening. So, ask like,

who are the most stressed out CEOs?

Those types of queries. Cuz if you're

using that like LM and it's just using

search, how does it search for stress?

There's no keyword that you can use

there.

Uh but if you had embeddings that have

information about sentiment, you can do

really cool searches.

>> This was a This was a huge

problem for the institutional finance

use cases of chatbots in default 25.

And in all of my experimentation going

into ChatGPT or Claude, almost anything

quantitative was not helpful due to this

sort of accuracy, like 60 70%

benchmark. Part of the way the ecosystem

is aimed to solve that is through MCP

and connectors into an agentic

workspace. And so now I can connect

into, rather than web searching for a

number,

I can connect into the MCP of a Dilupa

or a FactSet, etc. through my agentic

workspace. Is that How do you think

about sort of what you're doing and sort

of you you've aimed to solve this

problem in the way you just explained?

How would you evaluate the way that the

industry has tried to solve this problem

with that MCP and connector

uh movement into agents?

>> So, I know the last time we talked about

this, I had complained about the Claude

MCP introducing hallucinations into

Hudson Labs results, which had been very

frustrating.

Uh

and I would say I've been very, very

impressed with

how MCPs have evolved since. They're a

lot less brittle than they used to be.

Uh I you know, I think I think it's a

good approach. I think

um

having connectors that deal with the

vectorization, the pre-processing,

uh doing all of this back-end work for

you and pulling that into your own

universe is

is a good idea. Uh

there's

definitely some

trade-offs if you're using MCP. If

you're using Hudson Labs via MCP,

it's going to be a lot less efficient.

There's

sort of a

one of the ways that

Cloud has become less brittle is by

using more calls.

Uh so it so it is a much less efficient

way of using Hudson Labs, but it is much

better than it I don't know the last

time we talked about this, Brett, but um

but it it's

it's a lot better than it was before. I

mean, there's still

some situations where it becomes harder

to control. Uh we we don't offer uh no

hallucination guarantee if you are using

Hudson Labs through MCP because

it's it's not deterministic, right? It's

it's using another model on top of ours

and sometimes it can introduce

things that we didn't expect or you

didn't expect, but at this point we feel

that the benefits outweigh the risks,

which wasn't true a year ago.

>> Interesting.

>> Yeah.

>> And that's principally like the the

evolution has principally been been

what? Just the the the model's getting

better, the engineering around it? Like,

how has that brittleness problem been

uh uh been uh mitigated?

>> Model's getting better,

more guidance around how to set up an

MCP. I would say a lot of issues right

now with

usage of, say,

any connector,

they're not

They're mostly solvable through

better API API documentation, better MCP

documentation, facilitating more

endpoints. Uh so, it's it's

because there's a little bit more more

documentation, more flexibility, it

becomes easier to guide

these MPCs MCP servers to to make better

use of your own

own data.

>> Mhm.

And I hear, and I don't fully understand

this, I hear some people say, like, oh,

XYZ vendor has a their API's great or

their MCP's great. Their MCP's not so

good. Like, what is the skill in in sort

of like, for a neophyte, like, what's

the process of taking your data into an

MCP?

And where is the skill in that? Like,

how how do some vendors sort of do that

well? How do some vendors fail in that

in your in your assessment?

>> Like many things,

I think it's a function of

effort

and attention to detail

because it does take effort to break

down

your products and make it

agentically usable.

You're translating

essentially what is was originally a

user interface

into something that makes the most sense

to an LLM. And what makes sense to an

LLM doesn't always make sense to a human

being. I think, you know, because we

have Suhas, we're particularly good at

making

our our tools LLM readable. That is

another thing we talked a little bit

about,

you know, what's different between

Hudson Labs, what's going on in the back

end. And one of the things that we do do

differently is when you ask a question

as a human being,

we we have a translation step

and make your prompt more LLM friendly,

particularly

when we're talking about market search,

where

those search and retrieval steps and how

you you ask that question really, really

matters.

Uh and that applies to

to MCP as well.

>> Yeah. How have you thought about

you know, how have you thought about the

evolution of prompts to to skills? I

find myself really not prompting

much anymore. I have a few sort of

conversion prompts, but I find my

day-to-day investment process has really

centered around skills into an agentic

workspace.

How have you thought about that transit

that transition of the instructions from

the investor to the to the portal?

>> Yeah, the goal as a provider is

provide the thing the customer wants

with as little instruction as possible.

So, we think about that a lot. You know,

if you just type in SSS,

we will guess that you want same-store

sales and bring that back to you. And

that's not something that we were able

to do or doing

2 years ago. So,

you you're right, you know, prompting is

becoming

becoming a a a lot less important.

>> Can I Can I ask [clears throat] about on

the MCP uh

>> Mhm.

>> kind of uh creation and evolution.

I'm going to put my like power user open

claw hat on, so it's not maybe directly

relevant to financial services and a

but there's a big push even in that

community from MCPs to commit to CLIs.

So, like even more like And again, it's

going to be beyond my my technical

understanding, but CLIs being more

efficient and even more

friendly for

um agents to communicate with.

I I just my question for you is like is

that

is that true? Is that um

how do you see that playing out? I as an

example, like in my own workspace I've

been using the Google CLI instead of the

Google connector. It's like so much more

efficient and so much faster. I've been

using a Notion CLI instead of the MCP

server. Um and the results are much

better.

Um and so I'm wondering

uh if that's something that you are all

are thinking about or how you kind of

think of that evolution or the

relationship between MCP and CLI.

>> It's not something that I've spent a lot

of time thinking about. I'm sure our

technical team has.

And the one thing I would also say is

you'd be

surprised by

you know, we're all on Twitter a lot. We

see sort of

the the the the coolest things that

everyone's doing

with AI. A lot of our customers

don't even know what an MCP is.

So,

it's going to be

hopefully a minute before we prioritize

doing a CLI

given

it it it's tough. I think it's there's a

there's a huge range of where consumers

are are at right now, and you've got to

cater to to all of them, but

we're

we're okay with where we're at right

now.

Yeah.

>> How how have you thought about the in

sort of business model perspective about

the around the agent path and sort of my

experience having demoed many dozen of

the the the sort of chatbot finance

chatbots last year.

I sort of ultimately found like three or

four that were really good that I liked

and Hudson Labs was one of those.

And

that was a good news. The bad news is it

sort of remained this cumbersome

exercise to log in to portrait and

Hudson Labs and Alpha Sense and

>> Yeah.

>> sort of trying to remember where to go

to ask what question wasn't a

a great

user experience

contrasted to now an agentic workspace

with my skills embedded. I don't have to

sort of copy and paste prompts and my

connectors.

It's a much more delightful seamless

experience.

Um

And so how But how do you think about

sort of shifting what what Have you seen

that as well amongst your user base? And

how do you think about sort of shifting

the Hudson Labs

business model to align with that agent

path?

>> Yeah.

My perspective is in 2026 integrate or

die. You have to be

the future analyst is coding they're

building their own tools.

I'm relatively technical. I would never

buy a product that doesn't have an API.

That's going to become everyone going

forward.

So you have to offer integrations. You

have to offer a product that works for

people who are building their own

dashboards, building their own skills.

And we

we're doing that. We're we're including

all of that uh functionality and making

sure that we have connectors that work

for

a variety of

of use cases.

Um

The other way we're thinking about it is

we have this bifurcation in the market

right now, where there's a lot of users

like you, Brett,

who are

really excited about their skills, being

able to pull things from other all these

different places. They're using

perplexity computer, doing all of the

cool stuff. They love the MCP

experience. And we have these big

enterprise contracts with people who can

only use co-pilot.

Uh they've

never tried any of this before, and they

are looking to us

to become

the the place where where they

collect information and bring bring

information into us and and our thinking

about us

as

that place where you go to collect

everything and almost be the server

itself.

>> Mhm.

>> So, we're prioritizing integrating with

other people right now, um but also

thinking about how do we make sure

uh that our users who don't have access

to these more powerful tools can take

advantage of Hudson Labs in a more

extensible way, so that we also have

connectors coming in, not just going

out.

>> Got you. So, almost sort of a

bifurcation where in some like I think

everyone's searching for a single pane

of glass

right now. So, in some instances, you

would be that single pane of glass, and

you would have a sort of ingress MCP

connectors in that. Is that Is that Is

that right? And then you'd also sort of

have egress MCP into another single pane

of glass?

>> Yeah. And not just MCP, API, everything.

All all of the integrations, yeah.

>> How How do you sort of think about the

the durable advantage of of Hudson Labs

in that sort of, you know, single pane

of glass elsewhere? Like what are the

key We can talk about Friends of

Glassdoor, obviously, which is sort of a

differentiated uh data. What What do you

sort of, like I'm trying to sort of

figure out what the institutional grade

stack of connectors

looks like, how many that is,

uh where where do I get my all data

transcripts, etc. Like where do you

think What do you see as the TAM or the

market share of Hudson Labs in that

institutional grade fundamental agent

stack?

>> We're gaining popularity in model

building

and hope to corner that market with the

no hallucination guarantee, being able

to pull all of the the the information

you actually need. Obviously, there's

lots of tools like Delupa that do where

out of the box modeling, but for people

who are doing it themselves,

um but generally, where we think about

our notes versus others. So, we've got

the no hallucination elements, which is

a

a precision element, which is something

institutional users really care about,

whether that's single company or

multi-company. Uh but we do expect

eventually generalist models in the next

5 years to catch up from a hallucination

perspective, and we don't think that,

you know, 10 years from now, we can

still be competing on a a precision

element, particularly from a single

company perspective.

Uh so, really, where we provide a lot of

value is in situations where you need to

be doing

really good search and retrieval. Right

now, that does apply to single company

workflows, cuz you can't get good

results over, you know, a a longer time

period and pull those numbers accurately

if you want the more statement adjusted.

If you don't want it to be full of of of

junk.

Uh but

where we offer a ton of value

now and in the future is being able to

retrieve information across

10,000, 20,000 companies.

Uh I think we have

52 million data points in our our vector

vector database at this point. And you

can do things with AlphaSense that you

literally cannot do with any other

platform like pull out uh cool

sentiment-based elements, be able to

find the things you're looking for

quickly using materiality ranking, using

our uh

our declarations around metadata, etc.

So,

uh

To some extent, mostly right now big

firms

don't have sophisticated search and

retrieval. They're using the out of the

box brute force force methodology, and

you mentioned the fact that they don't

care about spend.

And it's okay that these big firms are

spending like $30,000

uh every couple weeks trying to create

information without a back end.

But, the problem is that it's not just

about cost when we're thinking about

search and retrieval and and and using a

a brute force mechanism across a large

data set.

It's also about accuracy. Um you know,

if you try to use a brute force

methodology to

you know, I'm an accountant, look up

accounting policy changes using Claude

right now, you end up missing so much

information because it's hard to find.

Uh so, there's this this big demand for

how do we do not just single company

deep dives, but how do we do

AI-based

screening, dataset creation,

high-precision dataset creation

uh go the extra step

uh in these multi-company workflows.

>> Is it fair to say that the brute So, the

brute force cuz presumably like with

every new model release, the brute force

powers gets get better? Is it If I'm

hearing you correctly, brute force can

give you like

like it might improve your breadth like

your breadth capabilities, but you still

have to manage the accuracy. Like brute

force is not going to be as helpful to

maintain that accuracy component. Is

that

>> Brute force is

So, what's a topic you want to learn

about right now? Okay.

>> What's a topic?

Um

let's see.

I'm trying to learn about

uh data lakes and data warehouses, like

the distillation of information across

different structures.

>> There is a lot of information out there

on the web about data lakes. There's a

lot of information in SEC filings.

Let's say data lakes

there's

15

articles about

not data lakes, but other types of

databases that are competitors and don't

have the word data lake in them.

If you want to use the brute force

approach right now, you're only going to

be able to effectively search for things

that are easily findable.

Got it. Right?

>> Yeah.

>> So, if you're thinking about getting a

complete of the land using AI search,

you need a way to to discover

information that is related but not

easily searchable.

And that's true

for a lot of AI style search.

One reason I often point to sentiment

is because it becomes really clear in

that that example. If you go, "Okay,

find

frustrated managers" or find managers

that are show evidence of deflection.

That's not something

that you can type in and search for.

And if you think of the AI model, how is

it going to find it if if you can't

search for it either?

And you need some way of making that

information findable so that when you

pull that into the context window,

there's the model has something to work

with.

Yeah.

>> Talk to us a little bit about um

you you're an accountant the forensic

accounting score, which is um part of

the

one of the delightful capabilities of AI

is to take uh

a previously highly cumbersome process

like doing a deep forensic accounting

analysis and sort of distill that into a

a score which has the quantitative

elements but also the unstructured data

elements.

Uh so this was sort of something that

caught my attention

very early on and I've been a big fan of

the the Hudson risk score approach. Can

you sort of just crack that open for us

and and walk through uh what you've been

doing there?

>> Yeah.

So

just to to take a quick step back,

people have been trying to predict

securities fraud since the beginning of

time.

And historically

uh when we used to try to do fraud

protection, we would use

generally things like days sales

outstanding, how quickly is revenue

growing, accruals,

these financial metrics.

Have you ever tried doing that, Brett?

>> Oh, yeah.

>> Yeah. Yeah. And the problem is that it

does

find fraudulent companies, but it also

finds a ton of just normal companies.

It's a very noisy way of predicting

fraud. It's a the reason why when you

read, you know, a Hindenburg report or

when you're pitching a short to your

boss, you're not going to say days sales

outstanding increased by X percentage.

You're saying, "Hey, look, the CFO quit.

They're selling the product to their

mom.

There's millions of dollars of

off-balance sheet debt.

The the market thinks

is is really excited about this

contract, but the contract's actually

with a related party and the market

doesn't know that. So, those are the

things that that create a good short

thesis. So,

uh we take that information, integrity

of the management team, turnover at the

top, you know, the number of times

they're changing their segment

disclosure,

um

aggressive accounting policies,

off-balance sheet risk, related party

transactions,

uh

dependence,

uh

governance.

Fun fact, uh dual class governance is

highly predictive of both growth and

fraud. Uh all of these elements and

using LLMs, we're able to take all of

these previously very qualitative

elements of risk that, you know,

maybe you'd be able to look at and go,

"Hey, that's sketchy." But, we can

convert that into a mathematical

representation of

of risk. How important is this weird

family-related party relationship? And

then use those quantifications to

predict fraud. So, uh our model looks at

all of these different types of

qualitative risks and gives says, "Given

that they restated once in the last 3

years and the CFO

uh

quit

and they changed their useful life

estimate, what's the likelihood they'll

be subject to an SEC enforcement action

or uh litigation related to the

securities fraud?"

>> How have you um

And a part of part of the reason I love

that is sort of like heretofore, like

tracking segment, you know, disclosure

changes over time at scale,

there was just like no way to

there's no way to do that. Like all

these little signals into a into a

collective mosaic. Like yes, you get

this sort of footprint of like

this feels like, you know, there's some

obfuscation here,

right? And there was no way to scale

that scale that before before.

Um

How do you think about, like the actual

like algorithm of like putting that into

a score? Like how do you how how have

you thought about weighting those

various components?

>> We let machine learning do the

weighting. So,

we have

a forensic model

that

classifies or or represents the

underlying risk.

And then we take those and create

variables,

quantitative variables,

and then we run

a standard ML process where we have

a big database of companies that were

demonstrably fraudulent either because

they had an SEC investigation

or a settled class action lawsuit

related to fraud and we let the machine

machine learning model figure out the

weights.

Which are often not the weights that

a human short seller would apply which

is is somewhat interesting.

>> Interesting. How have you tried How How

long has that model been live for and

how do you track like efficacy? Is there

any way to sort of distill that down

into a batting average or hit rate or

alpha, etc.?

>> Yeah, so

it's been a while since we've done a

backtest versus

share price. Um

but I believe there's about a 14-point

differential

uh in performance. So uh underperforming

by about 15% for for high-risk companies

back back when we did it, but uh we've

been doing this since 2019.

Uh very popular among actual teams at

D&O insurers. So we

do a lot of tracking based on

SCA securities class actions which is

the most important the fraud indicator

for them. Uh so high-risk companies are

three times more likely to be subject to

an SCA of any type of any kind. And

every company that has a score of 70 or

higher has about a one in three chance

of SEC enforcement. So it's it's very

high precision.

Uh yeah.

And of course the other two out of three

also likely frauds just not subject to

to SEC enforcement.

>> Yeah. Yeah.

>> Yeah.

>> Conversation we had one time is is um

just how sort of natively good good LLMs

have been at identifying risk and I

think the sort of conclusion was there's

a lot of evidence in the training corpus

to sort of pattern recognize like am I

am I remembering that conversation

correctly like why why why have LLMs

been sort of why why is this been

sort of a a strong native skill of of AI

the sort of risk dimension dimension?

>> We've had mixed results actually with

out-of-the-box LLMs.

>> Okay.

>> So

some things that have worked well are

you find headwinds those types of

requests. Where we've seen issues

is with more complex elements.

So

I've actually been somewhat disappointed

with

out-of-the-box LLMs and being able to

understand say a

bank's risk

or off-balance sheet risk in a way

that's a bit more nuanced.

So

yeah. I think there's still a couple

gaps in understanding that personally I

would have expected to be fixed by now.

Yeah. I I yeah I think

the reason for that though is that there

is just not a lot of good forensic

information on the web to learn from.

>> Okay.

>> Where there is a lot of good information

about general risks like operational

risks etc. But there's not a ton of good

forensic accounting stuff out there.

Up until two years ago when we until we

wrote a blog post on it if you googled

what is a critical audit matter it would

tell you the wrong thing.

>> Yeah. There's sort of a weird circ too

like when I'll search for things about

buy-side and AI like it'll bring my own

blog post back to me so you probably

>> [laughter]

>> Yeah. Yeah, no.

>> no, I want someone smarter than me

telling [laughter] me

Yeah, I don't want to read my own.

>> Yeah.

>> I don't want to read my own blogs, so

but a lot of Hudson Labs stuff shows up

there, too, so that's funny sort of like

getting your own documents fed back to

you.

Um

>> Honestly, the reason we created a blog

post about critical audit matters is

because it was

it was bothering me because I kept

reading short reports that would have

referenced the Google result for

critical audit matter, which had clearly

been written by AI.

Uh

and there's all of these short reports

going out being like, "Oh, you know,

this company has a critical audit matter

related to revenue. Ergo, fraud." And

I'm going, "You know, every single

software company has a critical audit

matter related to revenue. This is

we need to we need to clear this up."

So, yeah. Uh

I I do think there is still

still a few gaps in understanding.

Much, much better than it was

a year ago, but in some of the more

nuanced disclosure

there's

I'm still finding

some reasoning error.

>> Okay, makes sense.

>> Yeah.

>> What um super super super interesting

um

and I think sort of like a very

low-calorie way for investors to just

make better decisions, like having some

sort of like systema- system Like if I

sort of think about like the agent path

in the agent stack, like you know, some

sort of like forensic accounting risk

element in that agent stack is is

critical. Like if I if I can do this in

a seamless way before I make a trading

decision, having sort of a risk

checklist, forensic risk score

Like hey, this you know, there's a one

in three chance of this thing being a

fraud, like I'd like to know that before

I make the trading decision instead of

after I make the trading decision. Like

odds of restatement risk, etc., which

those are sort of very painful aches to

sort of wake up to

having the systematizing your decision

dashboard just seems like an absolute no

no brainer to me.

>> Agreed.

And one of the things that's cool, we

talked a little bit about cost and

efficiency

and

it's

if you

try to run Hudson Labs risk scores

out of the box even for us

uh

it costs hundreds of thousands of

dollars to run the Hudson Labs forensic

risk score over a 10-year period.

Um

which is a sort of somewhat interesting

elements of AI and one of the reasons

that we're now finding it harder to

support quant funds, which I think is a

pretty

just because you know, whenever you're

updating something in that stack, if you

have to re run 10 years of data uh

it's it becomes harder to to offer the

state-of-the-art functionality to to

purely quant funds who need that

backtesting, which I think is a pretty

interesting development in AI where

we've all been thinking about like oh

aren't LLMs amazing for quant funds? Uh

but we end up running into these cost

constraints where we're really only able

to offer state-of-the-art functionality

to

people who don't need 10 years of data.

>> Yeah.

How's it work? I mean

how's it work? I mean so I haven't tried

this yet, but you know, this is a

conversation is inspiring me to try

this. So I'm a healthcare investor.

Um can I create like a risk skill where

it's like a three-page risk checklist on

the name pulling in

all of my underlying research on those

companies, but also pulling in the you

know, the Hudson Labs forensic risk

score pulling from the 52 million you

know, data point vector database via

MCP.

Like is that something where I could

sort of use press that button and get a

get sort of a custom made risk risk

report on any of my companies?

>> We should we should chat. Let's chat

about trying to get you set up.

>> Cool.

>> All right.

>> Sounds great.

>> Can I ask about on this cost question?

The

there's so much happening, right? So you

have Fable that is 10x more expensive

than Opus. You have all these a lot of

my clients have become heavy co-work

users and guess what? That's not a cheap

harness.

Turns out.

Then you have Chinese models, open

weight models. How are you seeing this

kind of

cost like and and also people care about

like people stopped caring about people

didn't care about cost three months ago.

And now a lot of people maybe some of

the mega funds excluded

don't care.

What's your take on the shifting token

tokenomics landscape as it relates to

investment decision-making?

>> Yeah, it's

it's going to be interesting.

One thought I have is

let's all max out our subscriptions in

the short term because

they're not going to stick around.

Um

one thing that we

tell our customers, which is a a funny

thing to be telling customers, is Hudson

Lab subscriptions are profitable for

Hudson Labs. So you can, you know, trust

that we're not going to

randomly hike your prices.

Um

Yeah, it's it's it's it's it's going to

be interesting and it and it does come

back to this

we're creating these really

extraordinary outputs in part by using

very inefficient

very inefficient ways of of using AI,

very inefficient search, very

inefficient like using

a million calls instead of one

in order to get something you want. And

I don't think the fact

that it's so expensive and we're not

seeing any of the cost

matters. It just means that when this

starts to

collapse on us and our our prices start

to go up, there's going to be a lot more

a lot of people are going to start

thinking a lot more about AI

infrastructure, AI architecture, and

what's actually happening on the back

end instead of just thinking about that

top level LLM, the top level model. It's

going to be that's going to be the next

push is we're going to move beyond the

generation step and really think about

how are we storing data, where are we

getting data from?

There's so many ways to make make all of

this more efficient, which is one of the

reasons why Hudson Labs can run data

sets using long running agents and it,

you know, it only costs us 100 bucks.

But if you just went to an Opus 4.8

API, you're going to accidentally spend

13 grand. You know, it it it all of

these problems

are are solvable.

They just require they require more.

>> I wonder too, right? Cuz

these you mentioned like it's at the app

layer, like this this cost decision's

going to have to be made at the

individual contributor layer, the app

layer, the model layer, the model

selection layer. Like do you think one I

mean you you a horse in the race, but do

you think like one of the levers matters

most on like

optimizing against cost or optimizing

for cost?

>> There's a reason open source tools like

open code are having such a big moment

right now.

People who are thinking about cost don't

want to get locked into one model

provider. It doesn't make sense.

Um open code is a uh they're good

friends of ours and and and they're

getting huge because developers are

frustrated with oh if you you're using

quad code, only getting to use Anthropic

models, Anthropic probably won't be king

forever. So, yeah, if if if if you're

thinking about cost, it's

a good idea to to make sure that you can

you can switch providers, you're not

locking into to one model provider in

perpetuity. We know a lot of bigger

banks, bigger enterprise customers that

have built their own routers rather than

relying on somebody else's MCP, so they

do have more control.

Uh when we think about AI and where

we're going, it's yeah, it it's all

about being able to control your own

outcomes and make your own choices.

>> We've covered a lot of uh ground, Chris.

Any other, you know, core debates that

you're having with clients or peers or

friends or

um sort of big questions that you think

still need to be resolved that we should

talk about?

>> One thing that's somewhat interesting

is uh

have you tried using any of the big

models for extracting soft guidance?

>> No. Tell me about it.

>> Or do it, yeah. So, we built a guidance

model 2 years ago now

that we thought would only have a moat

for about 9 months.

The reason we bought built the guidance

model is because LLMs are brilliant, but

when they think about tense, they focus

when they think about whether or not

something's future or past, they focus

on the tense of the verb.

So, we talked about this before brought

where, you know, American Eagle

frequently says CapEx is now expected to

be.

And if you run state-of-the-art models

and say get me all management guidance,

it's missing a bunch of guidance.

Um

and that appears to still be true. Which

I find absolutely fascinating,

especially because so many of these big

model providers haven't been investing

in finance-specific training.

Now that I've said it on this podcast,

it'll probably be

fixed tomorrow, but [laughter]

>> No, I'll I'll I'll I'll tell the nerds

to the invest what they have to invest.

>> invest in it. Yeah, yeah.

>> Although it's probably being scraped

into many many agents, I'm sure

probably. Um

that's interesting. Um

>> Yeah.

>> Yeah, fast fascinating. Okay, great. Um

Yeah, what why do you think like I hear

this a lot like the Opus model of agents

have more been more specifically finance

trained than the ChatGPT? Like do you

have any sense of like why that's been

the case?

>> Why

>> Has that been your experience?

>> are more finance?

>> Yeah, like is it just the intention of

the training process? Like

>> I think a lot of the big firms are as

now specifically focusing more on

finance because A, they realized it was

a major gap before and B, realizing it

that this is a consumer base actually

willing to pay.

>> Yeah.

>> Yeah.

>> Yeah, I think it was a little bit of

galvanizing moment when Anthropic did

their a finance day and showed the

finance was the second largest vertical

behind tech.

Um

So, and finance

>> Complexity as well. It's Yeah,

obviously.

>> Finance AI is definitely having a

moment. We even have a We even have a

specific finance and investing podcasts

out now. Invest with AI, available on

all podcast platforms. Wherever you get

your podcasts, like and subscribe as the

kids say. So, uh

thank you so much for for being with us,

Chris. This has been really uh really

helpful and uh

part of what we're trying to sort of uh

do in this podcast is uh so sort of like

a flashlight on a dark evening, just see

3 ft in front of us.

I don't really know. I don't think any

of us know what what what lies around

the bend, but um we hope to continue to

have you on to

sort of see a little bit further down

the road and under stand at least

understand where we're at in the moment.

So, thanks for Thanks for everything

you've you've shared and what's the best

way for people to get in contact with

you if they want to learn more about

Hudson Labs?

>> hudson-labs.com

Come and give us a view. And I'm Chris

Pennati, you can find me on LinkedIn, X

everywhere.

>> Great. Well, thanks so much for the time

today.

>> Thank you.

>> I'll bother you soon with uh more

questions, I'm sure.

>> Can't wait.

>> Mhm.