This is a question borne of ignorance: why does Brex, a bank, care about AI like this?
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
Brex’s Prompt Engineering Guide
11–20 of 112 posts
Re: Brex’s Prompt Engineering Guide
#12YAML is just as effective at communicating data structure to the model while using ~50% less tokens. I now convert all my JSON to YAML before feeding it to GPT API's
do you also get it to return responses in YAML?
Re: Brex’s Prompt Engineering Guide
#13Earlier 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
Now I'm really wondering if that's true or not.
Software engineering can be self-studied very cheaply, lots of free resources, mostly you just need time and motivation. Failure is usually cheap.
Farming on the other hand requires more local, implicit and hands-on knowledge, capital requirements are high, feedback cycles are slower and failure is expensive.
Re: Brex’s Prompt Engineering Guide
#14Earlier quoted context omitted.
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
Now I'm really wondering if that's true or not. Software engineering can be self-studied very cheaply, lots of free resources, mostly you just need time and motivation. Failure is usually cheap. Farming on the other hand requires more local, implicit and hands-on knowledge, capital requirements are high, feedback cycles are slower and failure is expensive.
Yeah one doesn’t sound obviously easier than the other to me
Re: Brex’s Prompt Engineering Guide
#15This is a question borne of ignorance: why does Brex, a bank, care about AI like this?
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?
Re: Brex’s Prompt Engineering Guide
#16Earlier quoted context omitted.
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
Now I'm really wondering if that's true or not. Software engineering can be self-studied very cheaply, lots of free resources, mostly you just need time and motivation. Failure is usually cheap. Farming on the other hand requires more local, implicit and hands-on knowledge, capital requirements are high, feedback cycles are slower and failure is expensive.
I really, really doubt any of these examples.
Re: Brex’s Prompt Engineering Guide
#17I 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.
I don't think prompt engineering shares a whole lot with humanities higher education, but the argument that English is easier seems very non-obvious to me.
I'd expect the relative skill floor for English to be significantly higher because everyone in the anglosphere gets a minimum of 12 years of intensive English education. Moreover, the starting point for additional higher education is usually native fluency/mastery and even then jobs requiring actual English credentials will usually require a graduate degree on top.
Contrast that with programming, where most developers will have learned their first language in college and those 1-3 years of introductory education were enough that they're usually considered hireable by the end of undergrad. Some (few) people can even get to that point with only a 3-6 month intensive bootcamp despite no prior experience.
Re: Brex’s Prompt Engineering Guide
#18Are 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 that outputs a matrix view for quickly comparing outputs across multiple prompts, variables, and models. Good luck to everyone else out there tuning prompts :)
Re: Brex’s Prompt Engineering Guide
#19This is a question borne of ignorance: why does Brex, a bank, care about AI like this?
Lets say that you invest in 100 promising technologies. If one of them becomes a black swan, even if all the other 99 failed you still would be winning big.
Re: Brex’s Prompt Engineering Guide
#20YAML is just as effective at communicating data structure to the model while using ~50% less tokens. I now convert all my JSON to YAML before feeding it to GPT API's
I've heard this a lot but don't understand where this idea comes from. With JSON you can strip whitespace whereas with YAML you're stuck with all these pointless whitespace tokens you can't do anything about.
I would recommend the exact opposite, JSON is just as effective while using less tokens.
This example JSON:
{"glossary":{"title":"example glossary","GlossDiv":{"title":"S","GlossList":{"GlossEntry":{"ID":"SGML","SortAs":"SGML","GlossTerm":"Standard Generalized Markup Language","Acronym":"SGML","Abbrev":"ISO 8879:1986","GlossDef":{"para":"A meta-markup language, used to create markup languages such as DocBook.","GlossSeeAlso":["GML","XML"]},"GlossSee":"markup"}}}}}
Is 112 tokens, and the corresponding YAML (which I won't paste) is 206.
What am I missing?