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

51–60 of 84 posts

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

#51

Post by elicksaur »

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…

>If you listen carefully it's almost always based on a lack of imagination.

I actually find things to be the opposite. My skepticism comes from understanding that what LLMs do is token prediction. If the output that I want can be solved by the most likely next token, then sure, that’s a good use case. I’m perfectly capable of imagining those cases. People who are all in on AI seem to not get this and go wild.

There’s a difference between imagination and magical thinking.

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

#52

Post by godelski »

Yhippa wrote: post #46
godelski wrote: post #10

Earlier quoted context omitted.

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?

  > I think this does have a real shot of becoming something.
I wouldn't be doing a PhD if I didn't. PhDs are terrible. I'm amazed people do them for "the money" and not the passion.

  > Because of that I think they’re going to keep throwing money at this until someone figures it out.
My concern is who they throw money at, and even more specifically who they don't throw money at.

  Some people known to do carpet pulls, no prior experience in ML, and throw together a shitty demo that any ML researcher should be skeptical of?
  $_$ 
  PhD researchers turning their theses into a product?
  ._.
Something's off.... But I guess when Eric Schmidt is saying you should steal and ask for forgiveness later, I don't think anyone should be surprised when unethical behavior becomes prevalent.

  > Because what else is there left to grift on in tech right now?
l̶i̶f̶e̶Hype finds a way. There's always something to grift.

The key thing to always recognize: grifters are people who have solutions and are looking for problems (e.g. hamstring AI into everything) while honest people have problems and are looking for solutions (i.e. people understand the limits of what we can do, the nuances of these things, and are looking to fill in that gap). I can tell you right now, anyone saying anything should be end-to-end AI is a grifter (including Google search). We just aren't there yet. I hope we get there, but we are quite a ways. Pareto is a bitch when it comes to these things.

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

#53

Post by ynniv »

elicksaur wrote: post #51
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…

>If you listen carefully it's almost always based on a lack of imagination. I actually find things to be the opposite. My skepticism comes from understanding that what LLMs do is token prediction. If the output that I want can be solved by the most likely next token, then sure, that’s a good use case. I’m perfectly capable of imagining those cases. People who are all in on AI seem to not get this and go wild. There’s…

My disappointment comes from understanding that what humans do is keystroke prediction. If the output that I want can be solved by the most likely next keystroke, then sure, that’s a good use case. I’m perfectly capable of imagining those cases. People who are all in on humanity seem to not get this and go wild.

Don't mistake the "what" for the "how". What we ask LLMs to do is predict tokens. How they're any good at doing that is a more difficult question to answer, and how they are getting better at it, even with the same training data and model size, is even less clear. We don't program them, we have them train themselves. And there are a huge number of hidden variables that could be encoding things in weird ways.

These aren't n-gram models, and you're not going to make good predictions treating them as such.

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

#55

Post by SwiftyBug »

Yhippa wrote: post #45
blobbers wrote: post #27

Earlier quoted context omitted.

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…

One thing I noticed about this behavior of LLMs "seeing" their error when you correct them is that sometimes I'm not even correcting them, just asking follow up questions that they interpret as me pointing out some mistake. Example:

Me: - Write a Go function that will iterate over the characters of a string and print them individually.

~Claude spits out code that works as intended.~

Me: - Do you think we should iterate over runes instead?

Claude: – You are absolutely right! Sorry for my oversight, here's the fixed version of the code:

I just wanted to reason about possibilities, but it always takes my question as if I'm pointing out mistakes. This makes me feel not very confident in their answers.

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

#56

Post by ruszki »

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…

Where did you get that it can figure out things which was not feed into it (e.g. not on Stackoverflow)? In the past year, none could answer any of my questions, for which I couldn’t find anything on Google, in any reasonable ways. They failed very badly when there was no answer to my question, and the question should have been changed.

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

#57

Post by fenesiistvan »

kwindla wrote: post #2

"Generative" AI/ML is moving so fast in so many directions that keeping up is a challenge even if you're trying really hard to stay current! I'm part of a team building developer tools for real-time AI use cases (voice and video). I feel like I have three overlapping perspectives and goals re this new stuff: 1. To figure out what we should build I need to have a good understanding of what's possible and useful right…

I have a VoIP software (https://www.mizu-voip.com/Software/SIPSDK/JavaSIPSDK.aspx) and I am trying to market it as the interface between AI and real time audio/video. It already has real-time in/out streaming capabilities, i just want to add some more helper methods to make it more obvious for AI input/output. Can you help me with a little feedback? I am trying to think with the mind of an AI developer and I am interested on your thoughts on how to implement the real-time interactivity for your software/service? Is our JVoIP library close to your requirements or are you going to use something completly different to interact with the endusers and/or backend services? (To what kind of software/service are you thinking more exactly to cover this part?)

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

#59

Post by makeitrain »

BobbyJo wrote: post #31
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? 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.

We’re going to have AI building Drupal sites soon. The platform is well architected for this. Most of the work is generating configuration files that scaffold the site. There are already AI integrations for content. The surface area is relatively small, and the options are well defined in code and documentation. I would not be surprised if we pull this off first. It’s one of the current project initiatives.

The coding part is still a hard problem. AI for front end and module code is still pretty primitive. LLMs are getting more helpful with that over time.

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

#60

Post by elicksaur »

ynniv wrote: post #53
elicksaur wrote: post #51

Earlier quoted context omitted.

>If you listen carefully it's almost always based on a lack of imagination. I actually find things to be the opposite. My skepticism comes from understanding that what LLMs do is token prediction. If the output that I want can be solved by the most likely next token, then sure, that’s a good use case. I’m perfectly capable of imagining those cases. People who are all in on AI seem to not get this and go wild. There’s…

My disappointment comes from understanding that what humans do is keystroke prediction. If the output that I want can be solved by the most likely next keystroke, then sure, that’s a good use case. I’m perfectly capable of imagining those cases. People who are all in on humanity seem to not get this and go wild. Don't mistake the "what" for the "how". What we ask LLMs to do is predict tokens. How they're any good at…

> 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 that quote, but the actual technical descriptions of the models are what should be considered.

Also, skepticism =/= disappointment and swapping those out greatly changes what the sentence says about my feelings on the matter. Tech from OpenAI and friends can’t really disappoint me. I have no expectation that it won’t just be a money grab ;)

Post reply on HN