YAML 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?
Yes and then format it back to JSON
Brex’s Prompt Engineering Guide
41–50 of 112 posts
Re: Brex’s Prompt Engineering Guide
#42Thanks very much for posting this! I haven't yet finished reading the whole thing, but even just the first section about the history of LLMs, explaining some of the basic concepts, etc., I found to be a very well-written and useful info, and it was really nice that it linked out to source material. So many times when you go into reading stuff about the latest AI technique or feature it can feel like you need to do a…
…was this written by an LLM? I’m starting to doubt anything on the internet that’s overly cherry and polite. Sigh.
> I’m starting to doubt anything on the internet that’s overly cherry and polite.
> …was this written by an LLM?
do you find that asking this is constructive?
Re: Brex’s Prompt Engineering Guide
#43I'm working on the idea of features instead of prompts: https://inventai.xyz
Re: Brex’s Prompt Engineering Guide
#44Thanks very much for posting this! I haven't yet finished reading the whole thing, but even just the first section about the history of LLMs, explaining some of the basic concepts, etc., I found to be a very well-written and useful info, and it was really nice that it linked out to source material. So many times when you go into reading stuff about the latest AI technique or feature it can feel like you need to do a…
…was this written by an LLM? I’m starting to doubt anything on the internet that’s overly cherry and polite. Sigh.
Pretty confident this is human-generated. Its definitely the author's usual writing style
Re: Brex’s Prompt Engineering Guide
#45Earlier 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.
The guys pressing buttons are REALLY confident going into this one.
Re: Brex’s Prompt Engineering Guide
#46The suggestion to use markdown tables was quite interesting. It makes a lot of sense, and I haven't seen it described elsewhere.
I have been getting good results by asking GPT to produce semi structured responses based on other aspects of (GitHub) markdown.
In general, I find it very helpful to find an already popular format that suits your problem. The model is probably already fluent in rendering that output format. So you spend less time trying to teach it the output syntax.
Re: Brex’s Prompt Engineering Guide
#47This reflects astonishingly poorly on Brex. What customer wants to hear that Brex is using "a non-deterministic model" for "production use cases" like "staying on top of your expenses"? I don't see them acknowledge the downsides of that non-determinism anywhere, let alone hallucination, even though they mention the latter. Hallucinating an extra expense, or missing one, could have serious consequences.
This is also potentially terrible from a privacy standpoint. That "staying on top of your expenses" example suggests that you upload "a list of the entire [receipts] inbox" to the model. It _seems_ like they're using OpenAI's API, which doesn’t use customer data for training (unlike ChatGPT), but they should be crystal clear about this. Even if OpenAI doesn't retain/reuse the data, would Brex's customers be happy with this 3rd-party sharing?
The expenses example seems like sloppy engineering too—there's no reason to share expense amounts with the model if you just want it to count the number of expenses. Merchant names could be redacted too, replaced with identifiers that Brex would map back to the real data. These suggestions would save on tokens too.
Despite Brex saying they're using this in production, I suspect it's mostly a recruiting exercise. It's still a very bad look for their engineering.
Re: Brex’s Prompt Engineering Guide
#48Worringly, I am it sure the people working on this really understand what a Transformer is
Quote from them:
“ There is still active research in non-transformer based language models though, such as Amazon’s AlexaTM 20B which outperforms GPT-3“
Quote from said paper
“ For AlexaTM 20B, we used the standard Transformer model architecture“
(Its just an encoder decoder transformer)
Re: Brex’s Prompt Engineering Guide
#49[dead]
Re: Brex’s Prompt Engineering Guide
#50Thanks very much for posting this! I haven't yet finished reading the whole thing, but even just the first section about the history of LLMs, explaining some of the basic concepts, etc., I found to be a very well-written and useful info, and it was really nice that it linked out to source material. So many times when you go into reading stuff about the latest AI technique or feature it can feel like you need to do a…
…was this written by an LLM? I’m starting to doubt anything on the internet that’s overly cherry and polite. Sigh.
I don't believe that it is generative, but I totally understand where you're coming from because it's an entire paragraphs worth of what amounts to simply thanking the author for the project, and doesn't add any salient meaningful content to the conversation.