The most prestigious law school admissions discussion board in the world.
|
 |
 
|
LJL at how easy 1L must be these days with ChatGPT
Poast new message in this thread
Date: September 28th, 2024 7:15 PM Author: Let\'s dispel with this fiction 1. Get outlines from 3 previous students for each class from last year.
2. Tell chatgpt to create a master outline.
3. Read each outline once per week. Ask chatgpt to help make analogies for legal issues with shit you like (e.g. South Park, Star Wars, etc.) and mnemonic devices to help you memorize every outline. As it gets closer to exams, tell chatgpt to create a "leansheets" style outline for each class.
4. Quiz yourself on it with chatgpt voice.
All this can be done for the bar exam too lmao. Throw in a bunch of old exam questions and ask chatgpt to create new questions in the same style.
|
Date: September 28th, 2024 7:21 PM Author: ..,.,,,...,..,,.,...,.,,.,.. I was testing out o1 preview edition with LSAT type questions and it got every one right. I understand there is a difference between the LSAT and being a lawyer, but people starting out now should not feel comfortable with the idea they will have a long career. Language models were babbling like idiots a few years ago. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48141371) |
 |
Date: September 28th, 2024 7:27 PM Author: Let\'s dispel with this fiction Exactly. Will be interesting to track law school admission numbers over the next few years. I have a feeling it will plummet significantly.
o1 preview is just today. What will Chatgpt 6 or whatever look like 3 years from now. The law student starting today is royally fucked. |
|
Date: September 28th, 2024 8:10 PM Author: ..,.,,,...,..,,.,...,.,,.,.. They are using o1 to create data for training the next generation of models. So now they can generate as much high quality of reasoning data as they want and then use it to train GPT-5 or 6, which can then be used for more synthetic data creation. Billions and billions of reasoning traces to learn from. The models by 2030 will be completely nuts. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48141492) |
|
Date: October 4th, 2024 9:24 AM Author: Mahchine'ing the $ecret truth of the univer$e (My 'Mahchine' lately running on dial-up circa 1999) (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162186) |
|
Date: September 28th, 2024 7:33 PM Author: DISGUST (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48141387) |
|
Date: October 4th, 2024 6:58 AM Author: Fresh Mango Not flame you can pretty much chatgpt any law question (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161948) |
|
Date: October 4th, 2024 7:10 AM Author: .- .-. . .-. . .--. - .. .-.. . You will get absurdly wrong but very convincing answers. Most of the time the real answer is "there is no case law exactly on point but...." The Charbots can't handle that and will literally invent law in an attempt to give you a definitive answer which makes them dangerous. They misread cases for the sake of definitivnous. |
|
Date: October 4th, 2024 7:18 AM Author: Fresh Mango Lmao keep telling yourself that. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161963) |
|
Date: October 4th, 2024 7:21 AM Author: .- .-. . .-. . .--. - .. .-.. . I use them daily because even the shit answers are a good starting point. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161967) |
|
Date: October 4th, 2024 9:06 AM Author: .,..,..,.,,..,..,,,,,,,,..,...,.,.,., it's good for discovery requests as well. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162145) |
|
Date: October 4th, 2024 7:21 AM Author: LLM Vance CR. Lexis AI works to fetch cases but lol @ trusting it to actually do anything. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161970) |
|
Date: October 4th, 2024 8:12 AM Author: Fresh Mango Right but it 100% points you in the right direction. I’m a shitty researcher and it helps give me cases as a starting point. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162050) |
|
Date: October 4th, 2024 8:10 AM Author: Smoker It’s terrible if you ask it anything that requires judgment. Even simple questions like “is this provision market?” when it’s obviously off market come back terribly wrong. Then if you question it it might say the opposite eventually. It seems to just tell you what it thinks you want to hear. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162046) |
|
Date: October 4th, 2024 8:46 AM Author: ,..,,,,,,....,,,..., Wow that sounds really different from what a human lawyer does. (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162099) |
|
Date: October 4th, 2024 9:18 AM Author: wait till biggus dickus hears of this (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48162173) |
|
Date: October 4th, 2024 7:00 AM Author: Fresh Mango How do we take advantage of this for our deli stocks? (Delicious stocks)? (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161949) |
|
Date: October 4th, 2024 7:29 AM Author: Taylor Swift is not a hobby she is a lifestyle I do this for my fiancee using her pharmacy school letters to generate multiple choice questions to prep for exams (http://www.autoadmit.com/thread.php?thread_id=5602898&forum_id=2\u0026mark_id=5310684",#48161980) |