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 nore than 1 or 2 lines long (hello world examples excluded).
Comment on this AI thing
DarkMessiah@lemmy.world 11 months ago
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.
0x4E4F@infosec.pub 11 months ago
ignotum@lemmy.world 11 months ago
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
DanVctr@sh.itjust.works 11 months ago
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.
ignotum@lemmy.world 11 months ago
0x4E4F@infosec.pub 11 months ago
Hm… that sounds interesting… a link to this AI?
ignotum@lemmy.world 11 months ago
Here ya go: github.com/Significant-Gravitas/AutoGPT
ninjan@lemmy.mildgrim.com 11 months ago
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.
the_sisko@startrek.website 11 months ago
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).
ninjan@lemmy.mildgrim.com 11 months ago
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.
Cannacheques@slrpnk.net 11 months ago
To be fair, in my mind most AI is kind of half baked potential terminator style nightmare fuel for the average person
0x4E4F@infosec.pub 11 months ago
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.
guy@lemmy.world 11 months ago
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
infamousta@sh.itjust.works 11 months ago
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.”
TheBlue22@lemmy.blahaj.zone 11 months ago
100% this yeah.
explodicle@local106.com 11 months ago
I think of it as a step between a Google search and bothering actual people by asking for help.
Karyoplasma@discuss.tchncs.de 11 months ago
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.
DJDarren@thelemmy.club 11 months ago
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.
TheDoozer@lemmy.world 11 months ago
Can you give an example? This sounds like exactly what I’ve always wanted.
gornius@lemmy.world 11 months ago
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.
TheDoozer@lemmy.world 11 months ago
That’s really cool, I gotta try that in the future. Thanks!
veni_vedi_veni@lemmy.world 11 months ago
It’s shunned upon in the Excel pro scene (shout-out to my boi Makro), but xlookup can be used instead
Gork@sopuli.xyz 11 months ago
Index / Match gang represent. Much more flexible than Vlookup.
FrostyTrichs@lemmy.world 11 months ago
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.
Baizey@feddit.dk 11 months ago
That’s exactly how I use it (but for more things than excel), it works pretty well as a documentation ‘searcher’ + template/example maker