That’s how I use Chat GPT. Not for coding, but for help on how to get Excel to do things. I guess some of what I want to do are fairly esoteric, so just searching for help doesn’t really turn up anything useful. If I explain to GPT what I’ll trying to do, it’ll give me avenues to explore.
I have a spreadsheet with items with their price and quantity bought. I want to include a discount with multiple tiers, based on how much items have been bought, and have a small table where I can define quantity and a discount that applies to that quantity. Which Excel functions should I use?
Response:
You can achieve this in Excel using the VLOOKUP or INDEX-MATCH functions along with the IF function.
Create a table with quantity and corresponding discounts.
Use VLOOKUP or INDEX-MATCH to find the discount based on the quantity in your main table.
Use IF to apply different discounts based on quantity tiers.
Using AI in this way is what finally pushed me to learn databases instead of trying to make excel do tricks it’s not optimal for anyways.
I tried a bunch of iterations of various AI resources and even stuff like the Google Sheets integration and most of them just annoyed me into finding better ways to search for what I was trying to do. Eventually I had to stop ignoring the real problem and pivot to software better optimized for the work I was trying to do with it.
Yeah, that’s about it. I’ve trown buggy code at it, tell it to check it, says it’ll work just fine… scripts as well. You really can’t trust anything that that thing outputs and it’s more than 1 or 2 lines long (hello world examples excluded, they work just fine in most cases).
Have you looked at the project that spins up multiple LLM “identities” where they are “told” the issue to solve, one is asked to generate code for it, the others “critique” it, it generates new code based on the feedback, then it can automatically run it, if it fails it gets the error message so it can fix the issues, and only once it has generated code that works and is “accepted” by the other identities, it is given back to you
It sounds a bit silly, but it turns out to work quite well apparently, critiquing code is apparently easier than generating it, and iterating on code based on critiques and runtime feedback is much easier than producing correct code in one go
The software that implements multi agents called ChatDev, it’s significant more capable than one agent working alone. The ability to critique and fix bugs in the code in an iterative process gives a massive step up to the ability of the AI to program.
Granted it might still get in a loop between the programing and testing departments, but it’s a solid step in the right direction.
There is a (non-meme) reason why Prompt Engineer is a real title these days. It takes a measure of skill to get the model to focus on and attempt to solve the right question. This becomes even more apparent if you try to generate a product description where a newb will get something filled with superlative lies and a pro will get something better than most human writers in the field can muster for a much lower cost per text (compared to professional writers, often on par or more expensive than content farms). AI is a great tool, but it’s neither the only tool (don’t hammer in screws) nor is it perfect. The best approach is to let the AI do the easy boiler plate 80% then add that human touch to the hard 20% and at most have the AI prepare the structure / stubs.
I’m totally willing to accept “the world is changing and new skills are necessary” but at the same time, are a prompt engineer’s skills transferrable across subject domains?
It feels to me like “prompt engineering” skills are just skills to compliment the expertise you already have. Like the skill of Google searching. Or learning to use a word processor. These are skills necessary in the world today, but almost nobody’s job is exclusively to Google, or use a word processor. In reality, you need to get something done with your tool, and you need to know shit about the domain you’re applying that tool to. You can be an excellent prompt engineer, and I guess an LLM will allow you to BS really well, but subject matter experts will see through the BS.
I know I’m not really strongly disagreeing, but I’m just pushing back on the idea of prompt engineer as a job (without any other expertise).
We’re not talking small organizations here, nor small projects. In those cases it’s true that you can’t “only” do prompt engineering but where I see it is in larger orgs where you bring into the team the know how about how to prompt efficiently, how to do refinement, where to do variable substitution and how, etc etc. The closest analogy is specific tech skills, like say DBs, for a small firm its just something one backend dude knows decently, at a large firm there are several DBAs and they help teams tackle complex DB questions. Same with say Search, first Solr and nowadays Elastic. Or for that matter Networks, in many cases there might be absolutely no one at the whole firm that knows anything more than the basics because you have another company doing it for you.
The closest analogy is specific tech skills, like say DBs, for a small firm its just something one backend dude knows decently, at a large firm there are several DBAs and they help teams tackle complex DB questions. Same with say Search, first Solr and nowadays Elastic.
Yeah I mean I guess we’re saying the same thing then :)
I don’t think prompt engineering could be somebody’s only job, just a skill they bring to the job, like the examples you give. In those cases, they’d still need to be a good DBA, or whatever the specific role is. They’re a DBA who knows prompt engineering, etc.
I’ve found it’s best use to me as a glorified auto-complete. It knows pretty well what I want to type before I get a chance to type it. Yes, I don’t trust stuff it comes up with on its own though, then I need to Google it
Yeah, I find it works really well for brainstorming and “rubber-ducking” when I’m thinking about approaches to something. Things I’d normally do in a conversation with a coworker when I really am looking more for a listener than for actual feedback.
I can also usually get useful code out of it that would otherwise be tedious or fiddly to write myself. Things like “take this big enum and write a function that converts the members to human-friendly strings.”
Tell ChatGPT you want to do the project as an exercise and that it should not write any pseudocode. It will then give you a high-level breakdown which is usually a decent guide line.
Honestly, the best use for AI in coding thus far is to point you in the right direction as to what to look up, not how to actually do it.
That’s how I use Chat GPT. Not for coding, but for help on how to get Excel to do things. I guess some of what I want to do are fairly esoteric, so just searching for help doesn’t really turn up anything useful. If I explain to GPT what I’ll trying to do, it’ll give me avenues to explore.
Can you give an example? This sounds like exactly what I’ve always wanted.
I have a spreadsheet with items with their price and quantity bought. I want to include a discount with multiple tiers, based on how much items have been bought, and have a small table where I can define quantity and a discount that applies to that quantity. Which Excel functions should I use?
Response:
You can achieve this in Excel using the VLOOKUP or INDEX-MATCH functions along with the IF function.
Create a table with quantity and corresponding discounts.
Use VLOOKUP or INDEX-MATCH to find the discount based on the quantity in your main table.
Use IF to apply different discounts based on quantity tiers.
That’s really cool, I gotta try that in the future. Thanks!
Index / Match gang represent. Much more flexible than Vlookup.
It’s shunned upon in the Excel pro scene (shout-out to my boi Makro), but xlookup can be used instead
That’s exactly how I use it (but for more things than excel), it works pretty well as a documentation ‘searcher’ + template/example maker
Using AI in this way is what finally pushed me to learn databases instead of trying to make excel do tricks it’s not optimal for anyways.
I tried a bunch of iterations of various AI resources and even stuff like the Google Sheets integration and most of them just annoyed me into finding better ways to search for what I was trying to do. Eventually I had to stop ignoring the real problem and pivot to software better optimized for the work I was trying to do with it.
Yeah, that’s about it. I’ve trown buggy code at it, tell it to check it, says it’ll work just fine… scripts as well. You really can’t trust anything that that thing outputs and it’s more than 1 or 2 lines long (hello world examples excluded, they work just fine in most cases).
Have you looked at the project that spins up multiple LLM “identities” where they are “told” the issue to solve, one is asked to generate code for it, the others “critique” it, it generates new code based on the feedback, then it can automatically run it, if it fails it gets the error message so it can fix the issues, and only once it has generated code that works and is “accepted” by the other identities, it is given back to you
It sounds a bit silly, but it turns out to work quite well apparently, critiquing code is apparently easier than generating it, and iterating on code based on critiques and runtime feedback is much easier than producing correct code in one go
The software that implements multi agents called ChatDev, it’s significant more capable than one agent working alone. The ability to critique and fix bugs in the code in an iterative process gives a massive step up to the ability of the AI to program.
Granted it might still get in a loop between the programing and testing departments, but it’s a solid step in the right direction.
I was thinking of AutoGPT, but nice to see there are multiple projects taking a crack at this approach
Hm… that sounds interesting… a link to this AI?
Here ya go: https://github.com/Significant-Gravitas/AutoGPT
Thanks 👍, on my watch list.
There is a (non-meme) reason why Prompt Engineer is a real title these days. It takes a measure of skill to get the model to focus on and attempt to solve the right question. This becomes even more apparent if you try to generate a product description where a newb will get something filled with superlative lies and a pro will get something better than most human writers in the field can muster for a much lower cost per text (compared to professional writers, often on par or more expensive than content farms). AI is a great tool, but it’s neither the only tool (don’t hammer in screws) nor is it perfect. The best approach is to let the AI do the easy boiler plate 80% then add that human touch to the hard 20% and at most have the AI prepare the structure / stubs.
I’m totally willing to accept “the world is changing and new skills are necessary” but at the same time, are a prompt engineer’s skills transferrable across subject domains?
It feels to me like “prompt engineering” skills are just skills to compliment the expertise you already have. Like the skill of Google searching. Or learning to use a word processor. These are skills necessary in the world today, but almost nobody’s job is exclusively to Google, or use a word processor. In reality, you need to get something done with your tool, and you need to know shit about the domain you’re applying that tool to. You can be an excellent prompt engineer, and I guess an LLM will allow you to BS really well, but subject matter experts will see through the BS.
I know I’m not really strongly disagreeing, but I’m just pushing back on the idea of prompt engineer as a job (without any other expertise).
We’re not talking small organizations here, nor small projects. In those cases it’s true that you can’t “only” do prompt engineering but where I see it is in larger orgs where you bring into the team the know how about how to prompt efficiently, how to do refinement, where to do variable substitution and how, etc etc. The closest analogy is specific tech skills, like say DBs, for a small firm its just something one backend dude knows decently, at a large firm there are several DBAs and they help teams tackle complex DB questions. Same with say Search, first Solr and nowadays Elastic. Or for that matter Networks, in many cases there might be absolutely no one at the whole firm that knows anything more than the basics because you have another company doing it for you.
Yeah I mean I guess we’re saying the same thing then :)
I don’t think prompt engineering could be somebody’s only job, just a skill they bring to the job, like the examples you give. In those cases, they’d still need to be a good DBA, or whatever the specific role is. They’re a DBA who knows prompt engineering, etc.
To be fair, in my mind most AI is kind of half baked potential terminator style nightmare fuel for the average person
To be honest, I just gave up on it regarding code. Now I use it mostly for getting info into one place when I know it’s scattered all over the web.
I’ve found it’s best use to me as a glorified auto-complete. It knows pretty well what I want to type before I get a chance to type it. Yes, I don’t trust stuff it comes up with on its own though, then I need to Google it
Yeah, I find it works really well for brainstorming and “rubber-ducking” when I’m thinking about approaches to something. Things I’d normally do in a conversation with a coworker when I really am looking more for a listener than for actual feedback.
I can also usually get useful code out of it that would otherwise be tedious or fiddly to write myself. Things like “take this big enum and write a function that converts the members to human-friendly strings.”
100% this yeah.
I think of it as a step between a Google search and bothering actual people by asking for help.
All the hype are grifters and Google trying to convince people this isn’t just a search engine assistant.
Well we need something now that google is absolute dogshit at providing useful results XD Maybe not AI though
Tell ChatGPT you want to do the project as an exercise and that it should not write any pseudocode. It will then give you a high-level breakdown which is usually a decent guide line.