The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Opus 4.5 is disgustingly good
| jet address tank | 11/29/25 |
| Motley bistre sneaky criminal school | 11/29/25 |
| jet address tank | 11/29/25 |
| Topaz razzle meetinghouse | 11/29/25 |
| pearl titillating stag film private investor | 11/29/25 |
| jet address tank | 11/29/25 |
| misanthropic underhanded hairy legs shitlib | 11/29/25 |
| tantric beady-eyed roommate | 12/07/25 |
| pearly home | 12/07/25 |
| misanthropic underhanded hairy legs shitlib | 11/30/25 |
| tantric beady-eyed roommate | 12/07/25 |
| vibrant indirect expression | 12/07/25 |
| Pink concupiscible coldplay fan resort | 12/07/25 |
| Aphrodisiac cerise piazza | 12/07/25 |
| Motley bistre sneaky criminal school | 12/21/25 |
| coiffed gas station trump supporter | 12/21/25 |
| Topaz razzle meetinghouse | 12/21/25 |
Poast new message in this thread
Date: November 29th, 2025 12:55 PM Author: jet address tank Pretty sure humans are effectively useless now other than to pilot AI systems (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49470203) |
Date: November 29th, 2025 1:37 PM Author: Motley bistre sneaky criminal school 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=2\u0026show=week",#49470302) |
 |
Date: November 29th, 2025 2:10 PM Author: jet address tank 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=2\u0026show=week",#49470392) |
|
Date: November 29th, 2025 2:12 PM Author: Topaz razzle meetinghouse (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49470405) |
|
Date: November 29th, 2025 2:13 PM Author: pearl titillating stag film private investor 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=2\u0026show=week",#49470410) |
|
Date: November 29th, 2025 2:49 PM Author: jet address tank lol jfc (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49470540) |
|
Date: November 29th, 2025 2:50 PM Author: misanthropic underhanded hairy legs shitlib (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49470543) |
|
Date: December 7th, 2025 10:17 AM Author: tantric beady-eyed roommate wow (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491040) |
|
Date: December 7th, 2025 10:32 AM Author: pearly home lmao (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491074) |
|
Date: November 30th, 2025 1:14 AM Author: misanthropic underhanded hairy legs shitlib (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49471468) |
|
Date: December 7th, 2025 10:19 AM Author: tantric beady-eyed roommate it truly is insane - what a gift (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491048) |
|
Date: December 7th, 2025 10:23 AM Author: vibrant indirect expression explain what cause you to reach this conclusion (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491063) |
|
Date: December 7th, 2025 10:50 AM Author: Pink concupiscible coldplay fan resort Mental illness (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491106) |
|
Date: December 7th, 2025 10:44 AM Author: Aphrodisiac cerise piazza I need an AI agent to work with (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49491097) |
|
Date: December 21st, 2025 12:59 PM Author: Motley bistre sneaky criminal school 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: coiffed gas station trump supporter People complaining that 4.5 was shadow throttled starting a few days ago (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2\u0026show=week",#49527733) |
|
Date: December 21st, 2025 1:53 PM Author: Topaz razzle meetinghouse 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=2\u0026show=week",#49527743) |