Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How Kepler built verifiable AI for financial services with Claude

claude.com

Post reply on HN
Print view View original

11–20 of 30 posts

Re: How Kepler built verifiable AI for financial services with Claude

#11

Post by hansmayer »

bjelkeman-again wrote: post #6
hansmayer wrote: post #4

> The duo’s answer was to build deterministic infrastructure that serves as a trust and verification layer for AI. On the one hand, very encouraging to see plain old deterministic infra w/o using slop machines. On the other hand, this is a recognition that LLMs are just additional friction in the system that we would better off without in the first place!

Just friction? What do you mean? What would you do instead?

Well... You have a 'tool' that you cannot trust. Present everywhere due to unholly alliance between the LLM- companies and the exhilirated office worker cretins who "use" them to do "workflows". Now they fuck up stuff. Sounds like friction to me, or do you value the LLMs as net positive? WHy should I do something to fix their problems instead?

Re: How Kepler built verifiable AI for financial services with Claude

#12

Post by hansmayer »

SpicyLemonZest wrote: post #9
hansmayer wrote: post #4

> The duo’s answer was to build deterministic infrastructure that serves as a trust and verification layer for AI. On the one hand, very encouraging to see plain old deterministic infra w/o using slop machines. On the other hand, this is a recognition that LLMs are just additional friction in the system that we would better off without in the first place!

You're misunderstanding something about the problem space they're describing. The deterministic infra is for an underlying "execution layer"; the LLMs are providing utility by figuring out how to express English language queries in terms of the primitives of that verifiable layer. That way, you can describe your results deterministically even though the process of arriving at them was not necessarily deterministic.

Oh. I may have misread indeed. Ao its like, still LLM bullshit, but with really strongly worded .md instruction files begging them to please be correct?

Re: How Kepler built verifiable AI for financial services with Claude

#13

Post by SpicyLemonZest »

hansmayer wrote: post #12
SpicyLemonZest wrote: post #9

Earlier quoted context omitted.

You're misunderstanding something about the problem space they're describing. The deterministic infra is for an underlying "execution layer"; the LLMs are providing utility by figuring out how to express English language queries in terms of the primitives of that verifiable layer. That way, you can describe your results deterministically even though the process of arriving at them was not necessarily deterministic.

Oh. I may have misread indeed. Ao its like, still LLM bullshit, but with really strongly worded .md instruction files begging them to please be correct?

No. The point of the verification layer is that you don't have to beg the LLM to please be correct.

Re: How Kepler built verifiable AI for financial services with Claude

#15

Post by hansmayer »

SpicyLemonZest wrote: post #13
hansmayer wrote: post #12

Earlier quoted context omitted.

Oh. I may have misread indeed. Ao its like, still LLM bullshit, but with really strongly worded .md instruction files begging them to please be correct?

No. The point of the verification layer is that you don't have to beg the LLM to please be correct.

[dead]

Re: How Kepler built verifiable AI for financial services with Claude

#18

Post by jochem9 »

eddiehammond wrote: post #2

Anthropic published a profile on what we're building at Kepler. Sharing because the architectural argument (LLM for intent, deterministic code for retrieval and computation, every number traceable to source) is the part I'd actually want HN to push on. Happy to answer questions in the thread.

I'm on a very similar train. You cannot dump all the data into an LLM (for many reasons) and we also already have clearly defined rules that an LLM doesn't have to figure out.

So keep organizing data (LLM powered, of course), so that you can query data as usual (multi modal, so not just graphs, but also time series, relational, etc). Feed that to deterministic computations. Let an LLM reason about the outcomes.

Give the LLM the freedom to orchestrate the retrieval and computations. Make sure the way it orchestrates it is auditable.

The key thing I want to achieve is beyond this system: I want to uncover hidden things in the system (missing in the ontology, computations, etc) and propose to add these. This will effectively give you a generic approach to create ever evolving systems aliging with reality while being fully auditable.

Re: How Kepler built verifiable AI for financial services with Claude

#19

Post by eddiehammond »

saadatq wrote: post #8
eddiehammond wrote: post #2

Anthropic published a profile on what we're building at Kepler. Sharing because the architectural argument (LLM for intent, deterministic code for retrieval and computation, every number traceable to source) is the part I'd actually want HN to push on. Happy to answer questions in the thread.

could I get a link to the Kepler finance site? googling for "Kepler financial" yields 5-6 other finserv companies

Yep! kepler.ai We're working on improving SEO here, it's a popular name
Post reply on HN