em_poc
Official Title of this Community: Ethnic Minorities and People of Color
Why is the title different?
We like to have fun here.
What is this place? A safe space for underrepresented peoples and peoples of color to talk, chill, and vibe.
What are the basic rules of the community?
-
Follow Lemmy TOS and Community Guidelines. Non negotiable. This is the bedrock and mods will make decisions with this always in mind.
-
This community is for ethnic minorities and people of color. This is a safe space where such people can freely discuss their struggles, insight, and thoughts without fear. If you are not, we respectfully ask you do not post or comment here. A future community will be established to allow for racial discussions with a mixed userbase. However, remember, comments here must still respect Lemmy TOS and Community Guidelines.
-
Irony Racism is still racism. Racism is bad m'kay? We will treat irony racism and bad faith racist satire as racism. Will wield the ban hammer accordingly.
-
No sectarianism: This is an identity channel not a channel for you all to complain about why XYZ isn't the "one true leftism". Take that to another place.
-
Stupidpol is not allowed. Stupidpol is class reductionist. We are an identity community. Thinking like stupidpol ignores the struggles of the oppressed, their voices, and their need for unique support. Nothing says oppression more than someone saying that the identity you have is "not real" and that if you only thought like them you'd see what your "real" identity is. Mods reserve the right to ban users and content who promote stupidpol, stupidpol memes, and other class reductionist thinking.
FAQ
I don't look XYZ and/or sometimes I can pass as white so I don't know if I can post here. Can I?
-
This place is for ethnic minorities and people of color. This includes those of mixed heritage and those who may be "white" but are of an ethnicity that is a minority in their area (i.e. Kurds, etc) If you've experienced oppression due to your identity that is not based on sexual / gender identification, you are welcome here.
-
Moreover, for our American audience, we have people from around the world who are "white" but are oppressed due to being a minority in their country. They are and should be welcomed here.
What can I post?
- Anything you think is relevant to the mission of this community. Things will evolve over time.
- Topics and things relevant to EM and POC.
Suggested Posts
- [People of Spice]: Food recipes so others can taste your culture
- [Theory]: Vid/podcasts/websites discussing issues relevant to identity, anti-imperialism, etc
- [News]: Vids/podcasts/websites that talk about current events relevant to EM and POC
view the rest of the comments
Is ChatGPT (or any other AI) a good tool for summarizing articles?
I'm taking a psychology class and it's just a list of articles with no lecture, no slides and no teacher notes or even highlights. Just a pile of articles with dozens of pages each.
I really want to use ChatGPT to help summarize these articles and make the reading load potentially easier but I'm worried about the AI hallucinating and potentially leaving me worse off for studying.
Usually im against the use of LLMs, but that class sounds horrible. An LLM would be helpful as a primer before you read.
depends on how much u care about learning the course material tbh. there's less chance of hallucinations if you ask for a high level summary but at that point you may as well have just skim read everything.
one thing i would consider is prompting several different models, the main alternatives you can try are gemini-pro from Google and claude-2.1. if they all tell you different things then u probably want to pay attention and just read. anecdotally: gemini kind of sucks but has multi-modal stuff. claude-2.1 seems better than gpt3.5 across the board.
you could try looking into the CoT prompting all the LLM nerds do, but that stuff tends to work better for asking language models to do a task, and not summaries.
actually, an extra thing to add is that language models tend to 'pay less attention' to the middle of the context you send them, and this behaviour gets worse the more tokens they process. if you send them a 4000 word reading ur assigned the language model is not going to recall details in the middle 2000 words as accurately, and possibly just ignore them. this means that for accuracy you may be better off summarising each page one by one, which seems like a pretty simple ctrl+a ctrl+c crtl+v operation but regardless. if this all sounds very stupid its because they are.
(i didn't go through the education system with language models but i abuse them heavily for corporate stuff at work. i also am not a cs/ml expert.)