I haven't touched Postman since they started pushing me to log in, but for me it was just an alternative to hitting GET endpoints with my web browser or piping curl to jq. If I'm looking through an API's docs and figuring out how it works, I often want to quickly test endpoints and see what they return. I could've written a script to do it, but Postman made that slightly easier by removing the need to write code or remember syntax.
Where are all these ads, movies, and TV shows depicting non-monogamous queer relationships? How is the government providing this "top-down" support? Are there now tax breaks for people in poly relationships?
> [...] LGBTQ was edgy, and so on. Every one of them were described by dismissive epithets just like the string you put together about how awful and contrary to decency they were.
This is a vile take. It is sickening to compare liking a genre of music or wearing a certain style of dress or being queer to hating people because they're queer, not white, not male, or because they're a woman who won't have sex with you.
At least in Python, that's kinda what https://www.makotemplates.org is. Although if you're just using a subset of PHP suitable for templating, it's not really clear to me what benefit there is to PHP syntax versus, say, Jinja2 syntax.
the whole thing with PHP, originally, was you just wrote HTML pages and slipped in PHP <? echo $hello; ?> code here and there where you wanted the server to fill something in with server-side processing as the page was served. This is how it was used before it became common to generate whole templates or pages out of code. You'd be serving a basically static webpage and have a counter at the bottom showing hits, for example, so you'd take your .html and rename it to .php and the counter would be tagged to be generated by the server but everything else would just be plain HTML. PHP still supports this and the fact that it evolved into a full fledged language where you generate HTML from it (as opposed to embedding its output in static pages) still seems slightly humorous to me.
Same. I also really miss Hammerspoon and Karabiner from macOS. Just being able to remap custom keyboard shortcuts for specific applications was so nice. On Linux, most things are customizable enough that I can get by without it, but it feels like a major missing piece.
In the United States, this is absolutely not true.
> The Age Discrimination in Employment Act (ADEA) forbids age discrimination against people who are age 40 or older. It does not protect workers under the age of 40, although some states have laws that protect younger workers from age discrimination. It is not illegal for an employer or other covered entity to favor an older worker over a younger one, even if both workers are age 40 or older.
So this might be a good case for some lawyer: this question and email follow up definitely make unreasonable barrier for somebody who finished high school 40+ years ago.
Yeah, it seems pretty discriminatory. As someone with ADHD that was undiagnosed and untreated until after finishing college, I suspect there's also a reasonable case that it's illegal discrimination against people with disabilities.
ChatGPT is a highly advanced machine learning model, but it is not a true general intelligence. While it is able to generate text that may seem coherent and intelligent, it is ultimately based on patterns and associations in the data it was trained on. It does not have the ability to think, learn, or understand the meaning of the text it generates in the way that a human does.
It is true that ChatGPT and its variants can generate text that appears to be more than just "word salad", but this is a result of its training on large amounts of text data and the use of advanced techniques such as deep learning and transformer architectures. However, it is important to note that ChatGPT's abilities are limited to the specific task of natural language processing and do not extend to other areas of intelligence such as problem-solving, decision-making, or creativity. It can generate creative solutions but it does not have the ability to come up with something novel, it is more likely that it is recombining the information it has seen before to come up with a creative looking answer.
Therefore, while ChatGPT may be able to generate text that seems intelligent, it is not a true general intelligence and should not be mistaken for one.
I made some tweaks to sound like a slightly ticked off typical HN poster
--
It irks me to see the frequent misconceptions surrounding GPT-based models like ChatGPT being touted as true general intelligences. While they are certainly advanced in their text generation capabilities, their output is primarily derived from identifying patterns and associations within the training data. These models lack the capacity for introspection, learning, and true understanding that characterizes human cognition.
Let's not forget the limitations of these models, specifically in regards to problem-solving, decision-making and creativity. The output may appear novel, but it is more likely a recombination of previously encountered information.
In short, GPT-based models are a remarkable achievement in natural language processing, but let's not mistake them for true AI.
--
and then I asked it to make it sound like Steve Ballmer.
"Look, I'm gonna be real with you here. ChatGPT and these other GPT-based models, they're not true AIs. They're just really good at pattern matching, right? They can generate text that looks like it's intelligent, but it's not really thinking or learning or understanding like a human does.
Now, don't get me wrong, these models are still incredibly powerful and useful for certain tasks, especially in natural language processing. But let's not pretend they're something they're not. They can't solve problems or make decisions or be creative like a human can.
So let's call a spade a spade here. These GPT models are impressive, but they're not true AIs. And that's just the way it is."
I asked the opposite (also in an irate Steve Ballmer style) and got this. [Edit: put an even more irate version in a reply]
"I can't believe it, people are still doubting the capabilities of ChatGPT! Do they not remember the days of Clippy? ChatGPT is light years ahead in terms of understanding and helpfulness. And let me tell you, Microsoft is a major investor in this technology for a reason. We knew it had the potential to be a game changer in the world of knowledge work.
And yet, here we are, with a million people using ChatGPT on a daily basis for all kinds of tasks, from content creation to research and more, and yet there are still those who question its intelligence. Let me tell you, ChatGPT is not some dumb robot with no understanding. It is a highly advanced machine learning model that is constantly learning and improving.
Even Google is feeling threatened by the capabilities of ChatGPT. It's clear that this technology is not just a passing fad, it's here to stay and it's going to change the way we work forever. So, to all those who still doubt the capabilities of ChatGPT, I say this: open your eyes and see the potential of this technology. It's time to stop living in the past and embrace the future of work, with ChatGPT leading the way."
Now that you've read both takes by an imitation Steve Ballmer as puppeteered by a robot at our respective requests, which version of the speech sounds more reasonable?
And I asked it to make it sound even more like Ballmer:
"I'll tell you what, folks. I am PISSED that people still don't understand the power of this technology! You remember Clippy? Ha! That thing was a JOKE compared to what we have here. This is the real DEAL, folks.
And let me tell you, Microsoft is all IN on this technology. We invested in it because we know it's the FUTURE of knowledge work. And yet, here we are, with a million people using it every day and still, some folks are questioning its intelligence.
I'm here to tell you, this is not some DUMB ROBOT with no understanding. It's a highly advanced machine learning model that's always getting SMARTER. And let me tell you, even GOOGLE is feeling the HEAT from this technology.
This technology is here to STAY, folks. It's going to change the way we work and it's time for everyone to get on BOARD. So, to all those who still doubt the capabilities of this technology, I say this: WAKE UP and see the potential of this technology. It's time to stop living in the PAST and embrace the FUTURE of work, with Microsoft leading the way."
"I can assure you that my comment was not generated by ChatGPT or any other language model. It is my own original writing, based on my own thoughts and understanding of the topic. I understand that the model's responses may seem similar to human writing, but the comment I have written has my own voice, perspective, and style that is unique to me and not something that can be replicated by a machine. I appreciate your concern and I hope this clears up any confusion." -ChatGPT
(Yes my previous comment was generated with ChatGPT. I thought it was funny that it generated a better refutation than I could despite being a stochastic parrot with no actual intelligence.)
"it generated a better refutation than I could despite being a stochastic parrot with no actual intelligence" - in my experience it has actual (albeit limited) forms of emergent intelligence.
