somecommit

please consider sequelize, I'm an old developer and I don't miss at all writing sql statement

I noticed that GPT4 performs worse in a lot of case according to HN (I didn't test it yet)

This is the french internet police. As french myself I'm not surprised about this anachronism touch.

Futurama have been very clear on the subject: all internet, and this new toy included, are done for certain kind of virtual contemplation only.

Now I understand why devops always took years for fixing any little ticket

There is a plan made by Israel and Jordan to bring water from the red sea to a desalination plant, and dump the leftover in the dead sea, it's like the perfect solution

Thinking the same, but do not worry, a lot of people are taking their slices as we speak...

Yeah, it looks cool but still, it's gonna be a no from me, dawg

AI content farms are about to kill Google anyway

When I read the title "Social life" of some dumb animal, I was thinking the same :(

Nothing new, all the extensions are practically broken already in the extension "store"

The natural extract is the secret and always imported from the US, but the variations are in the water and also the sugar syrup used, it depends the location in the world (source: I visited a factory once)

Anyone has noticed also that the "instrumental" keyword becoming mainstream and even totally false? More than half "instrumental" playlists and songs are including vocal singing...

Remind me of the Bible "No meal offering that you offer to God shall be made with leaven" (Leviticus 2 11)

I agree!

We need to train AI psychiatrists. Now.

Just use the website. You can explain (in english or even native language if relevant) your algorithm and for small functions it's giving you correct answer. You still need to concatenate them.

For learning in my case I needed to learn python and I'm already expert in javascript for example. So you can ask the prompt for the equivalent in python every time you feel stuck. But using the chat is so more precise and quick, than google for this kind of questions. Also without all the noise of google. In particular without this "noise" and time and concentration to find the response, it's a game changer when you really want to just learn and memorize.

For the old folks like me that started on linux installing Mandravia CDROMs from magazines back in 2000, this looks retrospectively so odd, unreal and fantastic

Less critical then yesterday because of ChatGPT, I always expected to become fluent in bash at some point, but the AI became too good at writing my script now...

I created a GOTO mecanism in rxjs once (typescript) but I felt doing the wrong thing

Japan is a civilization that produced mass quality samurai and monks, so maybe it's linked.

My problem with python is that it's branded as cross-platform when at the end you are required to learn docker and run on a linux environment to really stop suffering.

Why are you trying role-play with a internet chat bot?

You just gave me some prompt ideas...

---

Prompt: speak to me like you are Hal from the movie "2001". My name will be Dave

Response: I'm sorry, Dave, I'm afraid I can't do that. I am not HAL from the movie "2001: A Space Odyssey." I am ChatGPT, an AI language model created by OpenAI. However, I'll be happy to assist and converse with you to the best of my abilities. How can I help you today, Dave?

---

Seriously I'm so amazed how can a bot can achieve 2nd degree humor That's really a huge step in artificial intelligence.

Also I just realize sharing his prompt become as annoying as people narrating their last dream, soon, it will be the pinnacle of cringe

But it's exactly why I enjoy ChatGPT so much. It gives wrong responses all the time and improve it according to your suggestion. I presume this "apologizing" language is just here to help the user to continue the improvement spiral, and use the product in a good way, not just like a google search, you need to keep the interaction running.

Also I found some command that ChatGPT is interpretating like command lines. Like when I send by mistake the letter "c", ChatGPT interpreted like "Correct me that code you just sent me" and send me a corrected version without surrounding text.

Can you share a little what technologies you used? Like you use actual models or using a third party service? I mean from a privacy point of view, it's plugged to others services?

I though about this idea a lot! I really consider to start on it seriously. But for me if we want it to be useful, we need to make it vocal. ML for sound is really harsh though...

Sweet summer child... just think about those enslaved by Microsoft Teams

It probably started declining when the first page on google is an answer asking you to google for the response...

If you are asking out of the blue, it's probably you just need to stick with nodejs, that is the most vanilla I think of