The most prestigious law school admissions discussion board in the world.
|
 |
 
|
Opus 4.5 is disgustingly good
| vengeful cocky twinkling uncleanness indirect expression | 11/29/25 |
| Swollen Fluffy Generalized Bond | 11/29/25 |
| vengeful cocky twinkling uncleanness indirect expression | 11/29/25 |
| mewling supple orchestra pit turdskin | 11/29/25 |
| talented awkward trailer park sex offender | 11/29/25 |
| vengeful cocky twinkling uncleanness indirect expression | 11/29/25 |
| flirting university | 11/29/25 |
| zombie-like orange field toilet seat | 12/07/25 |
| Vibrant mentally impaired reading party | 12/07/25 |
| flirting university | 11/30/25 |
| zombie-like orange field toilet seat | 12/07/25 |
| Razzle-dazzle iridescent liquid oxygen coldplay fan | 12/07/25 |
| multi-colored sooty business firm antidepressant drug | 12/07/25 |
| chestnut diverse address travel guidebook | 12/07/25 |
| Swollen Fluffy Generalized Bond | 12/21/25 |
| sinister hominid house | 12/21/25 |
| mewling supple orchestra pit turdskin | 12/21/25 |
Poast new message in this thread
Date: November 29th, 2025 12:55 PM Author: vengeful cocky twinkling uncleanness indirect expression 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: Swollen Fluffy Generalized Bond 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: vengeful cocky twinkling uncleanness indirect expression 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: mewling supple orchestra pit turdskin (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49470405) |
|
Date: November 29th, 2025 2:13 PM Author: talented awkward trailer park sex offender 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: vengeful cocky twinkling uncleanness indirect expression lol jfc (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49470540) |
|
Date: November 29th, 2025 2:50 PM Author: flirting university (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49470543) |
|
Date: December 7th, 2025 10:17 AM Author: zombie-like orange field toilet seat wow (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49491040) |
|
Date: December 7th, 2025 10:32 AM Author: Vibrant mentally impaired reading party lmao (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49491074) |
|
Date: November 30th, 2025 1:14 AM Author: flirting university (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49471468) |
|
Date: December 7th, 2025 10:19 AM Author: zombie-like orange field toilet seat 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: Razzle-dazzle iridescent liquid oxygen coldplay fan 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: multi-colored sooty business firm antidepressant drug Mental illness (http://www.autoadmit.com/thread.php?thread_id=5804093&forum_id=2,#49491106) |
|
Date: December 7th, 2025 10:44 AM Author: chestnut diverse address travel guidebook 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: Swollen Fluffy Generalized Bond 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: sinister hominid house 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: mewling supple orchestra pit turdskin 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) |