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

71–80 of 84 posts

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

#71

Post by emseetech »

KerryJones wrote: post #37
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.

How are you judging others who make this claim? I'm a FAANG Sr. Software Engineer, use it both in my company and personal projects, and it has made me much faster, but now I'm just "some other person who made this claim".

Can you publish your workflow? I'm on the hunt for resources from people who make the claim. Publishing their workflow in a repeatable way would go a long way.

I'm skeptical that we aren't inundated with tutorials that prove these extraordinary claims.

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

#72

Post by KerryJones »

emseetech wrote: post #71
KerryJones wrote: post #37

Earlier quoted context omitted.

How are you judging others who make this claim? I'm a FAANG Sr. Software Engineer, use it both in my company and personal projects, and it has made me much faster, but now I'm just "some other person who made this claim".

Can you publish your workflow? I'm on the hunt for resources from people who make the claim. Publishing their workflow in a repeatable way would go a long way. I'm skeptical that we aren't inundated with tutorials that prove these extraordinary claims.

What do you mean by "publish my workflow"? Do you want a blog post, a github md file? It's pretty simple.

Most recently I use Claude 3.5 projects with this workflow: https://www.youtube.com/watch?v=zNkw5K2W8AQ

Quick example, I wanted to make a clickable visible piano keyboard. I told it I was using Vue and asked for the HTML/CSS to do this (after looking at several github and other examples that looked fairly complicated). It spat out code that worked out of the box in about 1m.

I gave it a package.json file that got messed up with many dependencies versions being off from each other, it immediately fixed them up.

I asked it to give me a specific way using BigQuery SQL to delete duplicate rows while avoiding a certain function, again, 1 minute, done.

I have given it broken code and said "this is the error" and it immediately highlights the error and shows a fix.

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

#73

Post by meiraleal »

daemonologist wrote: post #69
BigParm wrote: post #67

Earlier quoted context omitted.

It's the best API searcher ever made but most people don't search APIs. They are waiting for it to make them a grilled cheese or something.

It's the best API searcher for APIs which are used a lot. If you want do anything other than the most common thing it can be worse than useless. (I've been running into this in a project where I'm using Svelte 5, and the language models are only interested in telling me about/writing Svelte 4, and transformers.js, where they tend to veer off towards tensorflow.js instead. This despite me explicitly mentioning what ve…

That's only Svelte to blame. How can something change so much every major release.

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

#74

Post by emseetech »

KerryJones wrote: post #72
emseetech wrote: post #71

Earlier quoted context omitted.

Can you publish your workflow? I'm on the hunt for resources from people who make the claim. Publishing their workflow in a repeatable way would go a long way. I'm skeptical that we aren't inundated with tutorials that prove these extraordinary claims.

What do you mean by "publish my workflow"? Do you want a blog post, a github md file? It's pretty simple. Most recently I use Claude 3.5 projects with this workflow: https://www.youtube.com/watch?v=zNkw5K2W8AQ Quick example, I wanted to make a clickable visible piano keyboard. I told it I was using Vue and asked for the HTML/CSS to do this (after looking at several github and other examples that looked fairly complic…

But given a large project, does any of that really average out to a multiple? Or is just a nice to have? This is what I keep encountering. It's all very focused on boilerplate or templating or small functions or utility. But at some point of code complexity, what is the % of time saved really?

Especially considering the amount of ai babysitting and verification required. AI code obviously cannot be trusted even if it "works."

I watched the video and there wasn't anything new compared to how I used Copilot and ChatGPT for over a year. I stopped because I realized eventually got in the way, and I felt it was preventing me from building the mental model and muscle memory that the early drudge work of a project requires.

I still map ai code completion to ctrl-; but I find myself hardly ever calling it up.

(For the record, I have 25+ years professional experience)

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

#75

Post by rldjbpin »

there seems to me tons of gatekeeping in this field to put it blunt. but if you want to mix full stack with AI/ML use cases, i think it might be a good idea to just keep track of high-level news and services that allow you to interface between the latest functionalities with an app.

there is enough space for creating user experiences built on top of existing work instead of learning how the sausage is made. but i pray to you to not just stick to text/LLM

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

#76

Post by ynniv »

emseetech wrote: post #74
KerryJones wrote: post #72

Earlier quoted context omitted.

What do you mean by "publish my workflow"? Do you want a blog post, a github md file? It's pretty simple. Most recently I use Claude 3.5 projects with this workflow: https://www.youtube.com/watch?v=zNkw5K2W8AQ Quick example, I wanted to make a clickable visible piano keyboard. I told it I was using Vue and asked for the HTML/CSS to do this (after looking at several github and other examples that looked fairly complic…

But given a large project, does any of that really average out to a multiple? Or is just a nice to have? This is what I keep encountering. It's all very focused on boilerplate or templating or small functions or utility. But at some point of code complexity, what is the % of time saved really? Especially considering the amount of ai babysitting and verification required. AI code obviously cannot be trusted even if it…

20+ years here. I've been exploring different ways of using them, and this is why I recommend that people start exploring now. IntelliJ with Copilot was an interesting start, but ended up being a bit of a toy. My early breakthrough was asking chat interfaces to make something small, then refine it over a conversation. It's very fast until it starts returning snippets that you need to fold into the previous outputs.

When Claude 3.5 came out with a long context length, you could start pasting a few files in, or have it break the project into a few files, and it would still produce consistent edits across them. Then I put some coins in the API sides of the chat models and started using Zed. Zed lets you select part of a file and specify a prompt, then it diffs the result over the selection and prompts to confirm the replace. This makes it much easier to validate the changes. There's also a chat panel where you can use /commands to specify which files should be included in the chat context. Some of my co-workers have been pushing Cursor as being even more productive. I like open source and so haven't used Cursor yet, but their descriptions of language-aware context are compelling.

The catch is that, whatever you use, it's going to get much better, for free. We haven't seen that since the 90's, so it's easy to brush it off, but models are getting better and there isn't a fkattening trend yet.

So I stand behind my original statement: this time is different. Do yourself a favor and get your hands dirty.

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

#77

Post by elicksaur »

ryandvm wrote: post #64
elicksaur wrote: post #60

Earlier quoted context omitted.

> Like previous GPT models, the GPT-4 base model was trained to predict the next word in a document… https://openai.com/index/gpt-4-research/ What humans do is materially different than that. When someone asks me a question, I don’t come up with an answer by thinking, “What’s the first word of my response going to be? The second word?…” I understand that the AI marketing wants us to believe there’s more magic than th…

> I don’t come up with an answer by thinking, “What’s the first word of my response going to be? The second word?…” Actually, I'm not so sure that isn't exactly what we do. That's why it's called a "train of thought". You have a vague idea and you start talking and lo and behold out comes a pretty coherent encapsulation of your idea that is informed and bounded by the token relationships of your language. Try answeri…

I usually try to think about what I’m going to say before I say it. My train of thought for this comment certainly did not start with “I usually”.

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

#78

Post by elicksaur »

ynniv wrote: post #66
ryandvm wrote: post #64

Earlier quoted context omitted.

> I don’t come up with an answer by thinking, “What’s the first word of my response going to be? The second word?…” Actually, I'm not so sure that isn't exactly what we do. That's why it's called a "train of thought". You have a vague idea and you start talking and lo and behold out comes a pretty coherent encapsulation of your idea that is informed and bounded by the token relationships of your language. Try answeri…

Like Heptapod B. The "next word" argument is pervasive and disappointingly ridiculous. If you present an LLM with a logic puzzle and it gives you the correct answer, how did it "predict the next word"? Yes, the output came in the form of additional tokens. But if those tokens required logical thought, it's a mistake to see the what as the how.

Maybe it’s pervasive because it’s literally the architecture of these models?

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

#79

Post by KerryJones »

emseetech wrote: post #74
KerryJones wrote: post #72

Earlier quoted context omitted.

What do you mean by "publish my workflow"? Do you want a blog post, a github md file? It's pretty simple. Most recently I use Claude 3.5 projects with this workflow: https://www.youtube.com/watch?v=zNkw5K2W8AQ Quick example, I wanted to make a clickable visible piano keyboard. I told it I was using Vue and asked for the HTML/CSS to do this (after looking at several github and other examples that looked fairly complic…

But given a large project, does any of that really average out to a multiple? Or is just a nice to have? This is what I keep encountering. It's all very focused on boilerplate or templating or small functions or utility. But at some point of code complexity, what is the % of time saved really? Especially considering the amount of ai babysitting and verification required. AI code obviously cannot be trusted even if it…

I'm 20+ years here and want to just call out it's a bit of a "moving goal posts with "but given a large project" comment.

I do think it is helpful in large projects, but much less so. I think the other comment gives a good example of how it can be useful, and it seems fairly obvious as context sizes are increasing exponentially in a short amount of time that it will be able to deal with large projects soon.

When using it in larger projects, I'm typically manipulating specific functions or single pages at a time and use a diff tool, so it comes across more as PR that I need to verify or tweak.

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

#80

Post by mnky9800n »

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…

Yes as someone who works in geophysics and AI I see a lot of people promising a lot of things that no neural network will be able to do no matter how much attention it has because good data is actually what people need and they typically lack it. There's a ton of use cases across geophysics for AI, I'm even organising a conference at the end of September about this. But imo there's a bigger need for better data and better software tools first.
Post reply on HN