The most prestigious law school admissions discussion board in the world.
|
 |
 
|
6/2/25 AI thread
Poast new message in this thread
Date: June 2nd, 2025 10:59 AM Author: Vermilion Vigorous Rigpig https://x.com/NicoleSHsing/status/1929217404619673873
"I am proud to present MIRROR: a cognitive AI architecture that implements inner monologue & self narrative in LLMs."
LLMs are female I can't say it enough |
 |
Date: June 2nd, 2025 3:30 PM Author: Amethyst Talented Library why is she not using thinking models in her comparisons? i would like to see the benefit for models that use thinking tokens. (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981339) |
Date: June 2nd, 2025 3:22 PM Author: Vermilion Vigorous Rigpig https://x.com/dionysianagent/status/1929337613292327231?s=46
Lmao |
|
Date: June 2nd, 2025 3:24 PM Author: cowardly geriatric stead (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981332) |
|
Date: June 2nd, 2025 3:36 PM Author: hilarious curious locale pistol It’s only just beginning. (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981350) |
|
Date: June 2nd, 2025 3:58 PM Author: chestnut place of business theater (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981397) |
|
Date: June 2nd, 2025 3:56 PM Author: pea-brained henna temple striped hyena (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981389) |
|
Date: June 2nd, 2025 3:59 PM Author: Vermilion Vigorous Rigpig Nah that guy probably has zero usable code after all that (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981401) |
|
Date: June 2nd, 2025 6:52 PM Author: Amethyst Talented Library it only has a 200K token context window. models doing this sort of thing would saturate it quickly. i'm imagining it making the same mistakes and quickly forgetting them. meanwhile anthropic drains your bank account with API costs. (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981734) |
|
Date: June 2nd, 2025 6:55 PM Author: Vermilion Vigorous Rigpig Yup half their current business model is pretty much scamming retards like this and large institutions with superfluous useless api costs
These guys just need to improve the open source models a little more and we can leave them behind forever |
|
Date: June 2nd, 2025 7:02 PM Author: chestnut place of business theater unfortunately the only open "source" (which is really only weights) models worth a damn are out of china and lmao at trusting that shit. meta is the only major US company open sourcing all of its models and zuckerfuck has really dropped the ball (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981753) |
|
Date: June 2nd, 2025 7:09 PM Author: Vermilion Vigorous Rigpig Yeah the Chinese ones are way better and will probably always be the best ones because I assume “meta” has figured out that there’s not actually a way to make money with their current business model for AI (http://www.autoadmit.com/thread.php?thread_id=5732488&forum_id=2...id.#48981769) |
|
Date: June 2nd, 2025 7:16 PM Author: Amethyst Talented Library Gemma 3 from Google is good.
The llama models are fraud bullshit anymore though. |