The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Opus 4.5 is disgustingly good
| odious henna travel guidebook volcanic crater | 11/29/25 |
| Cerise bateful state famous landscape painting | 11/29/25 |
| odious henna travel guidebook volcanic crater | 11/29/25 |
| stirring canary quadroon | 11/29/25 |
| rambunctious concupiscible roommate range | 11/29/25 |
| odious henna travel guidebook volcanic crater | 11/29/25 |
| excitant corner wagecucks | 11/29/25 |
| tan crusty meetinghouse | 12/07/25 |
| nubile ruby elastic band mad cow disease | 12/07/25 |
| excitant corner wagecucks | 11/30/25 |
| tan crusty meetinghouse | 12/07/25 |
| sick casino | 12/07/25 |
| diverse indirect expression set | 12/07/25 |
| abusive bonkers station | 12/07/25 |
| Cerise bateful state famous landscape painting | 12/21/25 |
| Milky Scourge Upon The Earth Boistinker | 12/21/25 |
| stirring canary quadroon | 12/21/25 |
Poast new message in this thread
Date: November 29th, 2025 12:55 PM Author: odious henna travel guidebook volcanic crater Pretty sure humans are effectively useless now other than to pilot AI systems (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470203) |
Date: November 29th, 2025 1:37 PM Author: Cerise bateful state famous landscape painting The level of improvement from Sonnet 4.5 is insane (a model that is a couple months old). LLM progress isn’t really slowing down in a meaningful way. (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470302) |
 |
Date: November 29th, 2025 2:10 PM Author: odious henna travel guidebook volcanic crater yeah and whats also interesting is that sonnet 4.5 was legit good..like it was better than opus 4.1 for most things and competitive with gpt5. I still like gpt 5.1 and the 5 pro api best as a generalist but opus 4.5 is insane for coding and also its much better at critiquing something you give it. the other LLMs are still too nice, but it has no problem giving harsh criticism and arguing against you. GPT 5.1 is better than 5 for this but still a bit weak compared to claude (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470392) |
|
Date: November 29th, 2025 2:12 PM Author: stirring canary quadroon (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470405) |
|
Date: November 29th, 2025 2:13 PM Author: rambunctious concupiscible roommate range My retarded fucking company refuses to upgrade our GHCP models from gpt4o and I want to kill myself (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470410) |
|
Date: November 29th, 2025 2:49 PM Author: odious henna travel guidebook volcanic crater lol jfc (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470540) |
|
Date: November 29th, 2025 2:50 PM Author: excitant corner wagecucks (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49470543) |
|
Date: December 7th, 2025 10:17 AM Author: tan crusty meetinghouse wow (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491040) |
|
Date: December 7th, 2025 10:32 AM Author: nubile ruby elastic band mad cow disease lmao (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491074) |
|
Date: November 30th, 2025 1:14 AM Author: excitant corner wagecucks (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49471468) |
|
Date: December 7th, 2025 10:19 AM Author: tan crusty meetinghouse it truly is insane - what a gift (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491048) |
|
Date: December 7th, 2025 10:23 AM Author: sick casino explain what cause you to reach this conclusion (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491063) |
|
Date: December 7th, 2025 10:50 AM Author: diverse indirect expression set Mental illness (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491106) |
|
Date: December 7th, 2025 10:44 AM Author: abusive bonkers station I need an AI agent to work with (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49491097) |
|
Date: December 21st, 2025 12:59 PM Author: Cerise bateful state famous landscape painting Opus 4.5 is up to 4 hours and 49 minutes on the METR time horizon task. this benchmark measures the task length (in terms of human work time) that models can do with SWE/AI research type projects. big increase over 5.1 max, which was 2 hours 53 minutes and faster than the overall trend of doubling every 7 months. with any luck, models will be capable of substantially automating AI research before 2030 and set off an intelligence explosion.
https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/ |
|
Date: December 21st, 2025 1:47 PM Author: Milky Scourge Upon The Earth Boistinker People complaining that 4.5 was shadow throttled starting a few days ago (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49527733) |
|
Date: December 21st, 2025 1:53 PM Author: stirring canary quadroon They are always claiming this for new model releases and no objective evidence ever materializes for it. It’s almost certainly a psychological bias rather than reality. There is substantial variation in how models respond to a particular problem just based on how they are prompted. It’s hard for a user to reliably measure model capabilities over time based on intuition alone. (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2в#49527743) |