The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Gemini 3 destroyed all other LLMs
Poast new message in this thread
Date: November 24th, 2025 1:29 PM Author: Sepia Set Party Of The First Part (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49456404) |
Date: November 24th, 2025 1:34 PM Author: kink-friendly olive point masturbator (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49456421) |
 |
Date: November 24th, 2025 1:59 PM Author: Sepia Set Party Of The First Part (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49456522) |
|
Date: November 24th, 2025 2:02 PM Author: irate flushed station telephone won't Altman and co just focus on subsidies via AI data center construction and deployment all over the world to help lower the birth rate? (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49456528) |
|
Date: November 24th, 2025 4:16 PM Author: Vigorous generalized bond tattoo I was thinking about this too
Anybody here have any experience with the jewgle phone? |
|
Date: November 24th, 2025 5:57 PM Author: kink-friendly olive point masturbator I just use the gemini app on iphone. What does a google phone add? (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457429) |
|
Date: November 24th, 2025 6:54 PM Author: Vigorous generalized bond tattoo I think it just lets the Jews/Indians hoover up more of your data so you can Do The AI better (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457590) |
|
Date: November 25th, 2025 10:03 AM Author: ,.,....,..,.,.,,,,..,..,.,..,.,.,.,... (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458928) |
|
Date: November 24th, 2025 4:13 PM Author: exhilarant stain looks like Opus 4.5 might be a better coding model now. hard to know for sure, but it's close. the rate of advancement here is nuts. pretty decent improvement over Sonnet 4.5, which isn't even 2 months old.
https://www.anthropic.com/news/claude-opus-4-5
|
|
Date: November 24th, 2025 5:14 PM Author: irate flushed station telephone (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457269) |
|
Date: November 24th, 2025 5:58 PM Author: wine state wagecucks Claude is nigger af ime and the limits are fucking ass outside of enterpise subscirption (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457433) |
|
Date: November 24th, 2025 5:58 PM Author: kink-friendly olive point masturbator GPT 5.1 did a little better on Biglaw Bench than gemini 3. I haven’t done a Shitlaw Bench yet (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457434) |
|
Date: November 24th, 2025 6:00 PM Author: wine state wagecucks gemini 3 is retarded sick as fuck, im stealing 9$ mill PE funded companies workflow and sites staight from them with Gemini and Framer HTML Chrome extension, this is fucking insane I should be hunted down by these companies cant even imagine what kind of evil shit is being done with this stuff its 180 (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457439) |
|
Date: November 24th, 2025 6:03 PM Author: kink-friendly olive point masturbator (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457455) |
|
Date: November 24th, 2025 6:06 PM Author: wine state wagecucks bro i just want to be left alone ina room with access to gemini 3 and notebooklm and my last decade of google drive docs
thats it, i got it from here i dont need anyone or anythign else |
|
Date: November 24th, 2025 8:29 PM Author: kink-friendly olive point masturbator (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457921) |
|
Date: November 25th, 2025 10:09 AM Author: t.rick o'treat panama (1) translate from nerd to english please (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458946) |
|
Date: November 24th, 2025 6:35 PM Author: bateful mexican ladyboy I am skeptical about the value of comparing models on benchmarks where they cluster together at high scores. There is not much room to detect model differences when they are at 90 % (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457525) |
|
Date: November 24th, 2025 8:42 PM Author: ungodly primrose marketing idea ceo probably but they just released it today so I haven't had time to test it (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457960) |
|
Date: November 24th, 2025 6:39 PM Author: irate flushed station telephone Nano Banana Pro
Create an image at 31.7785° N, 35.2296° E, April 3, 33 CE, 15:00 hours
Thinking...
Examining the Details
I'm currently focused on the specific coordinates and date provided. My goal is to produce an image reflective of that location and timeframe. I am now working on identifying relevant historical data points.
Pinpointing the Scene
I'm now zeroing in on the specific elements needed for the historical recreation. The latitude and longitude lead me to Jerusalem, and the date focuses me on a well-documented event. I'm building a picture of the scene, considering details like Roman soldiers, a crowd, and the crosses on a hill, all against a fittingly somber backdrop.
Analyzing Visual Depiction
I'm currently reviewing the match between the visual elements and the user's input, specifically focusing on the accurate representation of the specified time, date, and location. I am ensuring that all the parameters are correctly translated into the visual depiction. The focus is on the correct elements of the crucifixion scene itself.
Assessing Scene Correspondence
I've determined that the generated image aligns completely with the user's input. The specified historical setting, time, and date are all evident in the scene. The elements described in the request are correctly reflected in the visual output. The historical context, Roman soldiers, and onlookers are consistent with the prompt.
|
|
Date: November 24th, 2025 8:33 PM Author: Shaky pocket flask lettuce Why is this either impressive or useful (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457939) |
|
Date: November 24th, 2025 8:47 PM Author: irate flushed station telephone the way humans will learn, create, and consume content all look to involve Google moving forward.
|
|
Date: November 25th, 2025 1:15 AM Author: bateful mexican ladyboy It’s so much better than other generators. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458420) |
|
Date: November 25th, 2025 1:20 AM Author: bateful mexican ladyboy https://x.com/karpathy/status/1992655330002817095?s=46
They must have trained it with Gemini because it can solve complex technical problems in the image generation process. |
|
Date: November 25th, 2025 10:08 AM Author: cyberman (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458944) |
|
Date: November 24th, 2025 8:41 PM Author: ungodly primrose marketing idea ceo gpt 5.1 and grok 4.1 are both better than it. at getting answers wrong. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457957) |
|
Date: November 24th, 2025 8:45 PM Author: motley crawly milk Better at what? Destroyed it at what? I have had it on my phone for months and after some initial fun making pictures I basically stopped using it. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457969) |
|
Date: November 24th, 2025 8:46 PM Author: kink-friendly olive point masturbator Have you tried suing people with it? (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457972) |
|
Date: November 24th, 2025 8:47 PM Author: ungodly primrose marketing idea ceo it just came out like 6 days ago (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457973) |
|
Date: November 24th, 2025 8:46 PM Author: free-loading kitchen doctorate They all miss important details when they review legal docs (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49457971) |
|
Date: November 25th, 2025 1:09 AM Author: wine state wagecucks Not if you train it in notebook lm (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458417) |
|
Date: November 25th, 2025 4:01 AM Author: Smoker Not if you specifically feed it everything it needs to the extent you could have just done it all yourself tp (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458504) |
|
Date: November 25th, 2025 4:04 AM Author: Mainlining the $ecret Truth of the Univer$e (One Year Performance 1978-1979 (Cage Piece) (Awfully coy u are)) (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458509) |
|
Date: November 25th, 2025 4:05 AM Author: metaepistemology is trans yeah but feeding things into an llm is much easier than racking your brain doing all kinds of stepwise work yourself and it feels more rewarding because its like you are cheating. well to me anyway cheating feels more rewarding than actually doing something. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458511) |
|
Date: November 25th, 2025 4:06 AM Author: Mainlining the $ecret Truth of the Univer$e (One Year Performance 1978-1979 (Cage Piece) (Awfully coy u are)) (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458513) |
|
Date: November 25th, 2025 10:02 AM Author: ,.,....,..,.,.,,,,..,..,.,..,.,.,.,... cr. this is why I enjoy vibe coding even if doesn’t save time. I would rather just keep playing the code lottery and ask it to regenerate than have to think (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458925) |
|
Date: November 25th, 2025 4:00 AM Author: Smoker It’s amazing how committed you are to this schick. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49458502) |
|
Date: November 25th, 2025 3:45 PM Author: \"''''"\\'"\'\"\'"\' (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49460011) |
|
Date: November 26th, 2025 12:24 AM Author: ,.,....,..,.,.,,,,..,..,.,..,.,.,.,... TPUs can do anything anyone would want to do with neural networks. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49461564) |
|
Date: November 27th, 2025 2:57 AM Author: Mainlining the $ecret Truth of the Univer$e (One Year Performance 1978-1979 (Cage Piece) (Awfully coy u are)) Sorry ur too Poor to afford Opus 4.5 (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465135) |
|
Date: November 27th, 2025 4:20 AM Author: metaepistemology is trans Claude opus 4.5 is legit but I think Gemini 3, opus and gpt 5.1 are all good and different things. I still like GPT best overall though. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465164) |
|
Date: November 27th, 2025 3:08 AM Author: Patel Philippe This has to be a joke. Other than synthesizing massive information contexts for simplistic Google search style prompting, or analyzing a video on YouTube in detail, it is still complete trash compared to GPT and now Claude
Still no projects or OEM prompt optimization tool. Looks like they removed agentic prompting
Today it could not review a 4-page PDF in order after 4 tries (kept saying something on page 1 was on page 3).
Tempted to try Ultra but honestly why bother |
|
Date: November 27th, 2025 7:53 AM Author: metaepistemology is trans It outperforms the other leading models in certain metrics—particularly ones AI classically have a hard time with but this doesn’t mean it’s actual performance is better. Labs are starting to use internal proprietary metrics and a lot of the known public ones are now saturated or gameable (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465233) |
|
Date: November 27th, 2025 11:52 AM Author: ,.,....,..,.,.,,,,..,..,.,..,.,.,.,... There seems to be a limited amount of benchmark gaming going on. Private benchmarks or new benchmarks released after the models come out usually produce a rank ordering similar to other benchmarks. The labs have an incentive to be straight about benchmarks because people quickly figure out what models actually work and they won’t trust companies that consistently game them. (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465528) |
|
Date: November 27th, 2025 9:06 AM Author: average/ordinary/typical citizen/person Yea makes sense since deep mind has been doing all of this stuff we're seeing publicly since 2010 (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465287) |
|
Date: November 27th, 2025 9:41 AM Author: cyberman (http://www.autoadmit.com/thread.php?thread_id=5801840&forum_id=2/#49465328) |