[localghost3000]

> 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 anything useful. Short of them coming up with a truly miraculous breakthrough in the next 12 to 24 months (very unlikely but theres always a chance) investors are gonna get fed up and turn off the money fountain.

It's always a good idea to learn and grow your skillset. I am just not sure this is an investment that will pay off.

[godelski]

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 before it pops. The more hype you make, the more money you get, but the quicker that bubble pops. My concern here is that too much hype makes it difficult to distinguish charlatans form honest people. Charlatans will jump from cool topic to the next (don't trust someone who was a VR founder, then a crypto founder, and now a ML founder. Trust people who have experience and can stick with a topic for longer than a hype cycle).

The big danger, is if charlatans dominate the space, the hype disappears, and then there is no money for everyone. So if you do believe in the possibility of AGI and that AI/ML can make the world better (I truly do), make sure that we don't over hype. There's already growing discontent for products pushed too early with too big promises. If you really believe (like I do), you have to get rid of the bad apples before they spoil the whole barrel.

[mnky9800n]

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.

[Yhippa]

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?

[godelski]

  > 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.

[ryandvm]

I do not understand the AI naysayers.

The other day I had an idea for a Chrome plugin. I'm a senior dev, but I've never made a Chrome plugin. I asked ChatGPT 4o if my idea was possible (it was) and then I asked it to create an MVP of the plugin. In 10 seconds I had a full skeleton of my plugin. I then had it iterate and incrementally add capability until it was fully developed.

I had to do some stylesheet tweaking and it asked for a permission that we didn't need, but otherwise it completely nailed it. Easily provided 95% of the work for my extension.

I was able to do in 60 minutes what would have probably taken several days of reading specs and deciphering APIs.

Is my Chrome plugin derivative? Yes. Is most of what we all do every single day derivative? Also yes.

How are people still skeptical of the value that LLMs are already delivering?

[jryan49]

It's probably because it's providing different amounts of value to different people. For some people, it's not giving any benefits, and in fact making their work harder (me). They are skeptical because people naturally don't believe each other when their personal experience does not match up with another.

[BigParm]

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.

[daemonologist]

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 version/library I'm using and the existing code being written for said version.)

Anyways, they can definitely be very useful, but they also have a golden path/winning team/wheel rut effect as well which is not always desirable.

[meiraleal]

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