Programming thread

  • 🇵🇦 Nuestro primer dominio localizado está en español en kiwifarms.pa. Our first localized domain is on Spanish on kiwifarms.pa.
  • Want to keep track of this thread?
    Accounts can bookmark posts, watch threads for updates, and jump back to where you stopped reading.
    Create account
the person writing this article is retarded
at first gpt3 at first was only given
Código:
write me a 4chan greentext

> be me
> bottomless pit supervisor
then it generated everything up until "what" and ONLY THEN he added "to do" and then it made up the rest

iirc thats how the old gpt3 playground worked
why would it stop generating at ‘what’? Regardless I’m skeptical it was written by gpt at all, the model has improved significantly since then yet somehow this is the one time in history an LLM has been funny
 
why would it stop generating at ‘what’?
tokens output probably stopped idk
Regardless I’m skeptical it was written by gpt at all, the model has improved significantly since then yet somehow this is the one time in history an LLM has been funny
because current LLMs are prompted to hell and back ("You are ChatGPT 5.0. You act as an assistant chatbot....") GPT3 in playground mode was not prompted so it could be funny and racist
 
the person writing this article is retarded
at first gpt3 at first was only given
Código:
write me a 4chan greentext

> be me
> bottomless pit supervisor
then it generated everything up until "what" and ONLY THEN he added "to do" and then it made up the rest

iirc thats how the old gpt3 playground worked
While true, that doesn't change that the meat of the joke (the guy becoming a regular pit supervisor, which leads pretty directly into the punchline) was provided by the prompter, not the model.
 
While true, that doesn't change that the meat of the joke (the guy becoming a regular pit supervisor, which leads pretty directly into the punchline) was provided by the prompter, not the model.
yeah but ">become a" pretty naturally leads to "regular pit supervisor"
and even then gpt3 was still relatively bad so it couldve said anything but just "bottomless"
 
AI kids these days never touched a model that didn't have crazy internal prompts to make it look like it's a person.
If you don't get some schizophrenic autocomplete after typing a single letter, it's not the real deal.
 
Gen Alphas don't know what they missed out on. In 2019 you could trivially get a model to write a story about Osama Bin Laden repenting and becoming a Catholic.

I'm working on getting emacs set up on my personal box again after 13 years. Going whole hog on Guile and using emacs as my environment for it. Why Guile? Why not I guess. Something to do, alongside all my other personal projects sitting at 75% completion for years. 🧩
 
Gen Alphas don't know what they missed out on. In 2019 you could trivially get a model to write a story about Osama Bin Laden repenting and becoming a Catholic.
I remember AlphaGo beating top players back in 2015, and then finding about MarI/O.
Back then I though neural nets were the coolest shit ever. Even though about going into data science. Probably biggest blunder form financial standpoint, that I have not done it.
Then there was this Harry Potter AI stories which were the funniest shit ever.

Nowadays though, I have severe case of AI fatigue.
 
I remember AlphaGo beating top players back in 2015, and then finding about MarI/O.
Back then I though neural nets were the coolest shit ever. Even though about going into data science. Probably biggest blunder form financial standpoint, that I have not done it.
Then there was this Harry Potter AI stories which were the funniest shit ever.

Nowadays though, I have severe case of AI fatigue.
Don't blame AI or MLP for the sins of LLMs :mad:
 
Don't blame AI or MLP for the sins of LLMs :mad:
Don't forget ML that enables mass surveillance thanks to face, and other characteristics, recognition.
MLs that enable psychological profiling for targeted propaganda ads.

But yeah AlphaFold is pretty cool.
 
I have found myself in a small dilemma. A student saw me on campus and made conversation with me. She was a very interesting individual, though that would be too long to type out the bizarre conversation we had. If it helps, she told me her Chinese mother is a lawyer who studied philosophy, and the student herself is into Marxism. Her father is from Germany. I said cool, so is mine! She then asked if I had family members who were Nazis, and seemed unusually excited to ask this question. Usually people ask as a joke or some brief curiosity. Not sure how to feel about that.

She became very excited after finding out I'm a CS student! She wanted my help in developing something similar to "Bloomberg Terminals." I do not know what that is. After brief research, due to strict licensing and such, I told her this is impossible. She kept asking me things like what kind of people will she need? What about the API? The VPN? I said, I have no idea (not good at vague and open-ended questions that can go any way). All I do is write little scripts and study hardware. I am not an app developer, I am not a SWE. She will probably need a backend developer, and a frontend developer. She stares at me and says nothing. I send her resources and who to contact, I felt bad. Clearly she is driven and I wanted to support her. She asks for my schedule, asks how to contact me. I get an email last night requesting to meet on a Teams call so she can show the prototype "her people" made. Is this how it feels to work in the industry? Someone with little to no knowledge in a subject throws buzzwords at you, you have no idea what they're saying, you try to figure it out, they hit you with the fluoride stare, the conversation ends and you're not sure if they left satisfied or not, and suddenly you're being asked to join a random Teams call.

I think I am ok with being unemployed if so. Anyways. I finished my little perl script to automate the math questions we're asked in assignments related to run-length compression. Will probably do something with calculating the # of bits required to transmit via Huffman's compression depending on some other factors next.

Stupid nitpick question: Is it better to use <STDIN> or <>? <> looks cleaner, but being explicit is better if I want to design secure code. I do love my nice formatting and clean code though.
 
Stupid nitpick question: Is it better to use <STDIN> or <>? <> looks cleaner, but being explicit is better if I want to design secure code. I do love my nice formatting and clean code though.
Do you always want STDIN? If you want the user to be able to use a filename or stdin, then <> if you may want to use other options on the command line later, then <STDIN>
 
Atrás
Top Abajo