151–160 of 243 posts
I'm in two minds about it. On one hand the internet (in general) has become so hard to find information on, and I agree with the author that GPT is a breath of fresh air. On the other hand I've seen GPT fail so miserably at topics that I'm knowledge about that I have a very hard time trusting anything it tells me. I'm not sure what the answer really is, but I'm not sure it's GPT. I wish we could go back to having sea…
I'm in two minds about it. On one hand the internet (in general) has become so hard to find information on, and I agree with the author that GPT is a breath of fresh air. On the other hand I've seen GPT fail so miserably at topics that I'm knowledge about that I have a very hard time trusting anything it tells me. I'm not sure what the answer really is, but I'm not sure it's GPT. I wish we could go back to having sea…
> I wish we could go back to having search engines that actually led to useful information and not just advertisements, and I wish we had a GPT that would not tell lies. This ^. Prompting google is much more intuitive than prompting a chat bot. Also results are instantly available and you get more options to chose from. You can also filter out information much easier instead of having it summarised by a closed box th…
Earlier quoted context omitted.
> I'm honestly baffled that people lack the ability to use LLMs in a productive and optimal manner. Huge +1. I’ve got it to do a large part of my work for me by chaining some simple API calls. The fundamental conceptual gap I see - people often ask it to do some “thinking”. Then are annoyed by the inaccurate output. A simple example is doing word count and it getting the wrong answer very confidently. Of course it su…
If "chaining some simple API calls" is "a large part of your work", I can see it being incredibly useful. I already used it in this way a few times and it saved me some time indeed. However, as a software developer I feel like it's actually a tiny minority of my work; most of it is "doing some thinking" and slowly unfolding the inner parts of systems in order to understand how they work and how to fix them or make th…
As someone who is far from an expert in DevOps, this has saved me a lot of time recently, and it worked fairly well to get past duct taping infrastructure together to then leverage.
He has got a surface level understanding - GPT doesn't disambiguate crystal momentum from momentum for example.
I think this is partly why I'm still looking to be wowed by this technology, personally, in terms of what it can accomplish for me. And while it could be rightly said I've made things unnecessarily hard for myself approaching life like this, I feel it has been beneficial, and enriching, to force myself to really ask, what is this person saying here? In particular, I wouldn't want GPT to lead to a general lessening of empathy.
Puh, fun, yes. It's nice having a "conversation". But then everything that comes up I have to double check. As soon as the topic is somewhat specific, I can tell just by looking at it that the code won't work. So at the end of the day I have to go back to Google anyways.
Having a conversation allows me to figure out what I’m trying to figure out.
Once I know that, I know what to look for.
To me, the value of the conversation isn’t its perfect accuracy, but the expressiveness and ease of veering in any direction that seems interesting at the moment. The efficiency gains when jumping around within a subject are incredible.
Puh, fun, yes. It's nice having a "conversation". But then everything that comes up I have to double check. As soon as the topic is somewhat specific, I can tell just by looking at it that the code won't work. So at the end of the day I have to go back to Google anyways.
For me it’s consistently been much more helpful than google.
I always finish up by asking GPT to test my knowledge with a single-choice questionnaire. What I've observed is that the retention of the material is higher compared to "traditional" techniques. Perhaps the conversation style is more immersive, or perhaps focusing on specific knowledge gaps makes for accelerated / personalised learning.
There is of course the problem of accuracy, but I feel like it's often over-stated. Even if GPT is not correct at times, it often uncovers concepts and relations that paint a better overall picture for me, and lead me to better questions and follow up actions.
Earlier quoted context omitted.
> I wish we could go back to having search engines that actually led to useful information and not just advertisements, and I wish we had a GPT that would not tell lies. This ^. Prompting google is much more intuitive than prompting a chat bot. Also results are instantly available and you get more options to chose from. You can also filter out information much easier instead of having it summarised by a closed box th…
Except ChatGPT often gives better more accurate answers than Google without the bias of a single web page.