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

How to keep up with AI/ML as a full stack dev?

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 84 posts

Re: How to keep up with AI/ML as a full stack dev?

#41

Post by kukkeliskuu »

al_borland wrote: post #19

It sounds like you are aware of a technology and in search of a problem. Don’t force it. Most things don’t need AI. Personally, I find it to be a turnoff when a product tries to force AI into a product that doesn’t need it. It makes me write off the entire thing. I am in a similar position to you… I have a job they the application of AI to that job isn’t readily apparent. My posture during all this is to use AI produ…

In general it is good idea to avoid searching for a problem.

But in my experience the problem this in turn has a problem that you do not see the real problems you could solve with a piece of technology if you don't understand the technology.

So, sometimes, it makes sense to just start doing something with it. You will soon see potential uses, apply it, learn more, and overcome this hurdle.

Just do it without expecting any returns besides learning something new.

Re: How to keep up with AI/ML as a full stack dev?

#42

Post by bigtunacan »

conwy wrote: post #26
whynotkeithberg wrote: post #17

Earlier quoted context omitted.

Do you really think a useful bash script using ChatGPT prompts is worth blogging about? I'm genuinely asking. I've been wanting to start my blog back up I was always primarily a sysadmin, although I've had to move more into DevOps to keep with the times and instead of being more an SRE/sysadmin like I used to be I'm now DevOps meets sysadmin where I'm not helping write our companies application but I do everything el…

I think this skill could save time in a very rushed business environment. A while back I wrote a prompt to build a script that runs git-reflog to get a the list of distinct authors. After a few small tweaks I got it roughly working. This took about 1 hour. Writing it myself would have definitely taken multiple hours, especially having to learn the details of git-reflog. But that said I think it's mainly resume-buildi…

Did you get something done in an hour that would have taken multiple hours or not?

If you did then it transformed your productivity.

Re: How to keep up with AI/ML as a full stack dev?

#43

Post by yoyohello13 »

emseetech wrote: post #34
BobbyJo wrote: post #31

Earlier quoted context omitted.

> The question is what does programming with an LLM get you over batteries-included frameworks with scaffolding like Rails or Django? You can use them on top of those frameworks. The point is, you + LLM is generally a way faster you no matter what tech you're using.

I have not seen evidence of LLM use making programming way faster. Both in my own work, or from the work of others who make this claim.

I’ve noticed that LLM speed me up working with languages I’m bad at, but slow me down when working in languages I’m good at.

When I hear people saying they use them for 80-90% of their code it kind of blows my mind. Like how? Making crazy intricate specs in English seems way more of a pain in the ass to me than just writing code.

Re: How to keep up with AI/ML as a full stack dev?

#44

Post by kukkeliskuu »

bityard wrote: post #28

Are you looking to _use_ AI/LM or take up an interest in developing or deploying AI/LM? Because those are very different questions. Offtopic, but today I encountered my first AI-might-be-running-the-business moment. I had a helpdesk ticket open with IT for an issue with my laptop. It got assigned to a real person. After a few days of back-and-forth, the issue was resolved. I updated the ticket to the effect of, "Yup,…

I am running a fairly popular website, which has many unsophisticated users. There is a FAQ and instructional videos, but in general people do not read or understand the instructions. Then they send me email or call me. I spend lots of times repeating the same answers. I have been developing a support system that answers these basic questions based on the FAQs, and if it does not know how to respond, it tries to summarize the issue, and sends the issue to me. I am surprised how well it functions. I don't get endorphin hits from repeating same stuff for people.

Re: How to keep up with AI/ML as a full stack dev?

#45

Post by Yhippa »

blobbers wrote: post #27
ynniv wrote: post #24

My take requires a lot of salt, but… this time it’s different. Try writing single page web app or command line python app using the Claude 3.5 chat. Interact with it like you might in a pair programming session where you don’t have the keyboard. When you’ve got something interesting, have it rewrite it in another language. Complain about the bugs. Ask it what new features might are it better. Ask it to write tests. A…

I spent some time trying to get chatgpt to write a front end in js. It would plot using a library and then when I complained about a bug it would say "Oh you're right, this library does not implement that commonly implemented method, instead use this code." and then would get in a circle of spitting out buggy code, fixing a bug, and then reintroducing an old bug. It was okay, but kind of annoying. I understand js wel…

What you described was the exact same experience I had. I got so far off track in one of my conversations with corrections that I started all over again. It is neat that this technology can do it, but I probably would have been better off doing it manually to save time.

The other thing I’ve noticed is something you alluded to: the LLM being “confidently incorrect”. It speaks so authoritatively about things and when I call it out it agrees and corrects.

The more I use these things (I try to ask against multiple LLMs) the more I am wary of the output. And it seems that companies over the past user rushed to jam chatbots into any orifice of their application where they could. I’m curious to see if the incorrectness of them will start to have a real impact.

Re: How to keep up with AI/ML as a full stack dev?

#46

Post by Yhippa »

godelski wrote: post #10
localghost3000 wrote: post #9

> I most often can’t see any use case for AI/ML I'm admittedly a skeptic on all this so take what I am about to say with a grain of salt: You should trust that voice. We're in a hype cycle. It was VR before and crypto before that. Big tech is trying _very_ hard to convince you that you need this. They need you to need this tech because they are lighting billions on fire right now trying to make it smart enough to do…

ML researcher here. I will second this. Even if you think localghost is wrong about AI, it is important to always trust that voice of skepticism (to a limit). But I will say that we are in a hype cycle and as a researcher I'm specifically worried about this. I get that we have to bootstrap because you can't say "we want to spend money on research" (why?), but if you make a bubble the goal is to fill that bubble befor…

This is such a good perspective and thank you for posting. I agree with your statements and of all the hype cycles that have happened, I think this does have a real shot of becoming something. Because of that I think they’re going to keep throwing money at this until someone figures it out. Because what else is there left to grift on in tech right now?

Re: How to keep up with AI/ML as a full stack dev?

#47

Post by kukkeliskuu »

I have been very skeptical of AI, the smell of hype is strong in this one.

This said, I have started some experiments and like in all hyped technologies, there is some useful substance there as well.

My recommendation is to start with some very simple and real, repetitive need, and do it with the assistants API.

I started by turning a semi-structured word document of 150 entries into a structured database table. I would have probably done it more quickly by hand, but I would not have learned anything that way.

I think the sweet spot for generative AI right now is not in creative jobs (creating code, creating business communication , content creation etc.) but in mundane, repetivive things, where using generative AI seems like overkill at first.

Re: How to keep up with AI/ML as a full stack dev?

#48

Post by WhyOhWhyQ »

ynniv wrote: post #39
alisonatwork wrote: post #29

Earlier quoted context omitted.

The question is what does programming with an LLM get you over batteries-included frameworks with scaffolding like Rails or Django? If the problem only requires a generic infra solution put together by an LLM instead of a bespoke setup, why not look into low-code/no-code PaaS solutions to start with? Unless the LLM is going to provide you with some uniquely better results than existing tools designed to solve the sam…

The question is what does programming with an LLM get you over batteries-included frameworks with scaffolding like Rails or Django? Three years ago an LLM would conversationally describe what the code would look like. Two years ago it might crib common examples with minor typos. Last year it could do something that isn't on StackOverflow at the level of an intern. Earlier this year it could do something that isn't on…

I played with it a year ago and it really hasn't improved much since then. I even had it produce a few things similar to your battle ship demo.

And next year I don't see it improving much either if the best idea anybody has it just to give it more data, which seems to be the mantra in ML circles. There's not an infinite supply of data to give it.

Re: How to keep up with AI/ML as a full stack dev?

#49

Post by f0e4c2f7 »

I'm not sure why but it seems like most of the high quality AI content is on twitter. On average seems to be around ~4 months ahead of HN on AI dev approaches.

I would suggest following / reading people who talk about using Claude 3.5 sonnet.

Lots of people developing whole apps using 3.5 sonnet and sometimes cursor or another editor integration. The models are getting quite good now at writing code once you learn how to use them right and don't use the incorrect LLMs (a problem I often see in places other than twitter unfortunately.) They seem to get better almost weekly now too. Just yesterday Anthropic released an update where you can now store your entire codebase to call as part of the prompt at 90% token discount. Should make an already very good model much better.

Gumroad's CEO has also made some good YouTube content describing a lot of these techniques, but they're livestreams so there is a lot of dead air.

https://www.youtube.com/watch?v=1CC88QGQiEA

https://www.youtube.com/watch?v=mY6oV7tZUi0

Re: How to keep up with AI/ML as a full stack dev?

#50

Post by Retric »

sho wrote: post #40
emseetech wrote: post #34

Earlier quoted context omitted.

I have not seen evidence of LLM use making programming way faster. Both in my own work, or from the work of others who make this claim.

All I can surmise from comments like this is that you must have invented some completely unreasonable bar for "evidence" that nothing can possibly pass. Either that, or you simply haven't looked at all.

Could just be different workflows.

I didn’t get anything from messing with LLM’s but I also don’t get much use out of stack overflow even as some people spend hours a week on that site. It’s not a question of skill just the nature of the work.

Post reply on HN