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

Brex’s Prompt Engineering Guide

github.com

Post reply on HN
Print view View original

21–30 of 112 posts

Re: Brex’s Prompt Engineering Guide

#21

Post by travisjungroth »

uoaei wrote: post #15
BoorishBears wrote: post #11

Earlier quoted context omitted.

Startups are their bread and butter, Brex spends a lot of money mingling with the space, and AI is currently driving most companies in the space

Ah so it's just marketing? Brex doing a "how do you do, fellow kids" move?

The release is marketing, both to customers and for hiring. I have zero doubt they made this because they're using LLMs themselves, not just faking it like for fellow kids.

LLMs are valuable to all companies of any significant size, just for knowledge management. Then for a bank specifically, there a ton of text classification and summarization tasks when it comes to expense management, bill pay and all the other services they offer. There's also internal stuff. Fraud and KYC would be helped a lot.

Re: Brex’s Prompt Engineering Guide

#24

Post by nico »

typpo wrote: post #18

Are there established best practices for "engineering" prompts systematically, rather than through trial-and-error? Editing prompts is like playing whack-a-mole: once you clear an edge case, a new problem pops up elsewhere. I'd really like to be able to say, "this new prompt performs 20% better across all our test cases". Because I haven't found a better way, I am building https://github.com/typpo/promptfoo , a CLI t…

Amazing, so useful, thank you

Re: Brex’s Prompt Engineering Guide

#25

Post by tjr225 »

jeron wrote: post #4
voz_ wrote: post #3

Earlier quoted context omitted.

Perhaps, but this space suffers from the Armageddon astronaut/fire figher problem. It is easier to teach a Computer Science Major good english, than it is to teach an English Major computer science.

I always thought this problem was better thought of as software engineer/farmer problem - it's easer to teach a software engineer about agriculture than the other way around

[dead]

Re: Brex’s Prompt Engineering Guide

#26

Post by rvz »

morgante wrote: post #22
uoaei wrote: post #9

This is a question borne of ignorance: why does Brex, a bank, care about AI like this?

Brex is launching AI-enabled products: https://www.brex.com/journal/press/brex-openai-ai-tools-for-...

After looking at their 'AI-enabled' products, it looks more like pure gimmickry.

But at least this isn't a product they would expect to make the majority of their money from since Brex makes its money elsewhere and can afford to waste it on gimmicks and experiments like this.

Unlike the thousands of new so-called AI startups which are just a thin wrapper around OpenAI's API and have no moat.

Re: Brex’s Prompt Engineering Guide

#27

Post by sitkack »

typpo wrote: post #18

Are there established best practices for "engineering" prompts systematically, rather than through trial-and-error? Editing prompts is like playing whack-a-mole: once you clear an edge case, a new problem pops up elsewhere. I'd really like to be able to say, "this new prompt performs 20% better across all our test cases". Because I haven't found a better way, I am building https://github.com/typpo/promptfoo , a CLI t…

Seems like you would want to apply some NLP to the prompts themselves

Take the gradient of the prompt wrt adjectives, verbs, nouns, etc. I forget the technique, but they add garbage words to the prompt to effectively increase the temperature.

Re: Brex’s Prompt Engineering Guide

#28

Post by sitkack »

voz_ wrote: post #3
game_the0ry wrote: post #2

I wonder if linguistic and English majors would end up benefiting in this trend of "prompt engineering."

Perhaps, but this space suffers from the Armageddon astronaut/fire figher problem. It is easier to teach a Computer Science Major good english, than it is to teach an English Major computer science.

Cite.

Re: Brex’s Prompt Engineering Guide

#29

Post by sitkack »

jeron wrote: post #4
voz_ wrote: post #3

Earlier quoted context omitted.

Perhaps, but this space suffers from the Armageddon astronaut/fire figher problem. It is easier to teach a Computer Science Major good english, than it is to teach an English Major computer science.

I always thought this problem was better thought of as software engineer/farmer problem - it's easer to teach a software engineer about agriculture than the other way around

Substantiate your claim! A farmer is much better generalist than a "software engineer". FFS, the engineer doesn't even use science and the farmer does.

Re: Brex’s Prompt Engineering Guide

#30

Post by velavar »

Is it me or is the bot's output in the section "Give a Bot a Fish" incorrect? It states that the most recent receipt is from Mar 5th, 2023 but there are two receipts after that date. This is what worries me about using ChatGPT - the possibility of errors in financial matters, which won't go down well I fear.
Post reply on HN