The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Opus 4.5 is disgustingly good
| Excitant claret space ladyboy | 11/29/25 |
| light tripping stock car kitty | 11/29/25 |
| Excitant claret space ladyboy | 11/29/25 |
| angry den giraffe | 11/29/25 |
| chest-beating pit | 11/29/25 |
| Excitant claret space ladyboy | 11/29/25 |
| Disgusting Magenta House | 11/29/25 |
| Glittery Insanely Creepy Home | 12/07/25 |
| Aqua Exhilarant Kitchen | 12/07/25 |
| Disgusting Magenta House | 11/30/25 |
| Glittery Insanely Creepy Home | 12/07/25 |
| Maize histrionic ratface | 12/07/25 |
| Appetizing forum reading party | 12/07/25 |
| Federal mahogany affirmative action | 12/07/25 |
| light tripping stock car kitty | 12/21/25 |
| Big impertinent stead son of senegal | 12/21/25 |
| angry den giraffe | 12/21/25 |
Poast new message in this thread
Date: November 29th, 2025 12:55 PM Author: Excitant claret space ladyboy Pretty sure humans are effectively useless now other than to pilot AI systems (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49470203) |
Date: November 29th, 2025 1:37 PM Author: light tripping stock car kitty 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=2Ã#49470302) |
 |
Date: November 29th, 2025 2:10 PM Author: Excitant claret space ladyboy 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=2Ã#49470392) |
|
Date: November 29th, 2025 2:12 PM Author: angry den giraffe (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49470405) |
|
Date: November 29th, 2025 2:13 PM Author: chest-beating pit 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=2Ã#49470410) |
|
Date: November 29th, 2025 2:49 PM Author: Excitant claret space ladyboy lol jfc (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49470540) |
|
Date: November 29th, 2025 2:50 PM Author: Disgusting Magenta House (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49470543) |
|
Date: December 7th, 2025 10:17 AM Author: Glittery Insanely Creepy Home wow (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491040) |
|
Date: December 7th, 2025 10:32 AM Author: Aqua Exhilarant Kitchen lmao (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491074) |
|
Date: November 30th, 2025 1:14 AM Author: Disgusting Magenta House (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49471468) |
|
Date: December 7th, 2025 10:19 AM Author: Glittery Insanely Creepy Home it truly is insane - what a gift (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491048) |
|
Date: December 7th, 2025 10:23 AM Author: Maize histrionic ratface explain what cause you to reach this conclusion (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491063) |
|
Date: December 7th, 2025 10:50 AM Author: Appetizing forum reading party Mental illness (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491106) |
|
Date: December 7th, 2025 10:44 AM Author: Federal mahogany affirmative action I need an AI agent to work with (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49491097) |
|
Date: December 21st, 2025 12:59 PM Author: light tripping stock car kitty 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: Big impertinent stead son of senegal People complaining that 4.5 was shadow throttled starting a few days ago (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2Ã#49527733) |
|
Date: December 21st, 2025 1:53 PM Author: angry den giraffe 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=2Ã#49527743) |