The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Opus 4.5 is disgustingly good
| peach international law enforcement agency | 11/29/25 |
| Glassy Irradiated Principal's Office Water Buffalo | 11/29/25 |
| peach international law enforcement agency | 11/29/25 |
| Yellow kitchen gaping | 11/29/25 |
| grizzly marketing idea | 11/29/25 |
| peach international law enforcement agency | 11/29/25 |
| Histrionic opaque chapel | 11/29/25 |
| cyan bbw crotch | 12/07/25 |
| Milky costumed hominid | 12/07/25 |
| Histrionic opaque chapel | 11/30/25 |
| cyan bbw crotch | 12/07/25 |
| Startling Indirect Expression | 12/07/25 |
| Walnut cerebral philosopher-king ratface | 12/07/25 |
| Infuriating Cumskin | 12/07/25 |
| Glassy Irradiated Principal's Office Water Buffalo | 12/21/25 |
| Deranged state | 12/21/25 |
| Yellow kitchen gaping | 12/21/25 |
Poast new message in this thread
Date: November 29th, 2025 12:55 PM Author: peach international law enforcement agency 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"#49470203) |
Date: November 29th, 2025 1:37 PM Author: Glassy Irradiated Principal's Office Water Buffalo 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"#49470302) |
 |
Date: November 29th, 2025 2:10 PM Author: peach international law enforcement agency 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"#49470392) |
|
Date: November 29th, 2025 2:12 PM Author: Yellow kitchen gaping (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49470405) |
|
Date: November 29th, 2025 2:13 PM Author: grizzly marketing idea 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"#49470410) |
|
Date: November 29th, 2025 2:49 PM Author: peach international law enforcement agency lol jfc (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49470540) |
|
Date: November 29th, 2025 2:50 PM Author: Histrionic opaque chapel (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49470543) |
|
Date: December 7th, 2025 10:17 AM Author: cyan bbw crotch wow (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491040) |
|
Date: December 7th, 2025 10:32 AM Author: Milky costumed hominid lmao (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491074) |
|
Date: November 30th, 2025 1:14 AM Author: Histrionic opaque chapel (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49471468) |
|
Date: December 7th, 2025 10:19 AM Author: cyan bbw crotch it truly is insane - what a gift (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491048) |
|
Date: December 7th, 2025 10:23 AM Author: Startling Indirect Expression explain what cause you to reach this conclusion (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491063) |
|
Date: December 7th, 2025 10:50 AM Author: Walnut cerebral philosopher-king ratface Mental illness (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491106) |
|
Date: December 7th, 2025 10:44 AM Author: Infuriating Cumskin I need an AI agent to work with (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2"#49491097) |
|
Date: December 21st, 2025 12:59 PM Author: Glassy Irradiated Principal's Office Water Buffalo 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: Deranged state 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"#49527733) |
|
Date: December 21st, 2025 1:53 PM Author: Yellow kitchen gaping 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"#49527743) |