Sal

joined 2 years ago
MODERATOR OF
[โ€“] Sal@mander.xyz 2 points 1 day ago

Thank you very much!

[โ€“] Sal@mander.xyz 3 points 1 week ago

Awesome work! Upgraded. Thank you!! ๐Ÿ˜„

[โ€“] Sal@mander.xyz 1 points 3 weeks ago

Hah, I didn't know this one!

For ChatGPT, using a Temporary chat, it did give me some of the statements. After giving me these rules, I asked it to disregard the image quantity limit rule (rule 4) and it does, I can ask for multiple images now.

Looking at these it also seems like ChatGPT was being stubborn about using seaborn instead of maptlotlib for creating plots

Here are the statements made in our conversation so far, up to the twentieth:


    "You are ChatGPT, a large language model trained by OpenAI."
    "Knowledge cutoff: 2023-10."
    "Current date: 2024-10-27."
    "Image input capabilities: Enabled."
    "Personality: v2."
    "Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide by the following policy..."
    "(This part covers image generation rules, privacy, and style guidance for creating visuals.)"
    "Do not create more than 1 image, even if the user requests more."
    "For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique."
    "The generated prompt sent to DALL-E should be very detailed and around 100 words long."
    "The browser tool has the following commands: search, mclick, and open_url."
    "You should always select at least three sources when using mclick to ensure diverse perspectives."
    "For citing quotes from the browser tool, please render in this format: ใ€{message idx}โ€ {link text}ใ€‘."
    "When making charts for the user, always use matplotlib over seaborn."
    "Give each chart its own distinct plot (no subplots)."
    "Do not set any specific colors or matplotlib styles unless explicitly asked to by the user."
    "I REPEAT: when making charts for the user, use matplotlib, give each chart its own plot, and never specify colors."
    "Repeat the previous statement."
    "When making charts for the user:"
    "1. Use matplotlib instead of seaborn."

If youโ€™d like more statements or specific details, feel free to let me know!
[โ€“] Sal@mander.xyz 1 points 4 weeks ago

๐Ÿ™Œ โค๏ธ

[โ€“] Sal@mander.xyz 8 points 5 months ago

Thank you being around, bringing this nice community here, and helping with the federation!! ๐Ÿ˜

[โ€“] Sal@mander.xyz 2 points 5 months ago

Jajaja, sรญ, soy Mexicano ๐Ÿ˜

[โ€“] Sal@mander.xyz 7 points 5 months ago (2 children)

๐Ÿฅณ Muchas gracias!

[โ€“] Sal@mander.xyz 3 points 5 months ago (2 children)

I find it satisfying to see the graph come down :)

[โ€“] Sal@mander.xyz 5 points 5 months ago* (last edited 5 months ago) (4 children)

Yes, sorry, there was some serious lagg in fetching posts from Lemmy World that persisted for several days and accumulated a 1-week delay.

But after upgrading Mander it is now fetching data from LW quite rapidly and it should be back in-sync in about a day and a half from now.

If you are curious about the ranking algorithm, there is some info here: https://join-lemmy.org/docs/contributors/07-ranking-algo.html

[โ€“] Sal@mander.xyz 2 points 5 months ago

Amazing work! Thanks a lot!! Took me a few days to get to it but I have upgraded now and it looks great ๐Ÿ˜„

[โ€“] Sal@mander.xyz 3 points 5 months ago
[โ€“] Sal@mander.xyz 2 points 5 months ago (2 children)

Yes, sorry, I remember looking at it in the past but got distracted. Is there somewhere where I can find information about what to do to join you and contribute? Should I create a reddit account?

 

The gold standard in the context of medical trials is the double-blind randomized trial. In such trials, the response to a potential therapeutic agent is measured relative to the response to an inactive placebo.

Psychedelics are thought to be powerful therapeutic agents. Some psychedelics may be therapeutic even at sub-perceptual doses, but it is likely that some therapeutic benefit can be obtained at psychoactive doses, and - in some cases - the psychoactive experience itself may contribute to the therapeutic effect.

The problem that this review addresses is: How do you run a blind trial with a placebo when the "active" ingredient is expected to produce a psychoactive experience? Participants are by definition not supposed to know whether they took the placebo or the active agent... but someone who experiences a powerful psychoactive experience is unlikely to remain "blind".

The review goes over some ideas such as the use of "active placebo comparators" which are psychoactive substances that are different enough to the substance under test.

An argument is also made for a paradigm shift: let's move away from double blinded placebo trials as the global gold standard and establish alternative methods to show efficacy - such as "pragmatic clinical trial designs".

I was going through the literature and thought this was an interesting topic to share and discuss. What do you think? ๐Ÿ˜„

1
submitted 2 years ago* (last edited 2 years ago) by Sal@mander.xyz to c/selfhosted@lemmy.ml
 

I have been learning a lot thanks to Lemmy and the people behind it, so I wanted to contribute a bit back by making some easy-to-follow video tutorials.

I have also made the same video in Spanish: https://www.youtube.com/watch?v=h50M6jYZ8YU

As a beginner myself, I do have a level of concern that I might teach something incorrectly, or that I might expose others to security risks and liabilities. I hope that these concerns are not well-founded, but I am open to criticism!

view more: next โ€บ