\
  The most prestigious law school admissions discussion board in the world.
BackRefresh Options Airdrop

Funny how open weight models can be evaluated and tested but OpenAI can't

since they swap out models on the back end or bump you down ...
vibrant at-the-ready theater
  09/13/26
Link to OpenAI cannot be tested
Poppy corner
  09/13/26
(illiterate)
vibrant at-the-ready theater
  09/13/26
So no link will be forthcoming
Poppy corner
  09/13/26
Did you hear guise? Anthropic promised not to do this no mor...
vibrant at-the-ready theater
  09/13/26
I see a link but it doesn't match what OP said
Poppy corner
  09/13/26
hi RSF
vibrant at-the-ready theater
  09/13/26
Link?
Poppy corner
  09/13/26
that's a non-denial
vibrant at-the-ready theater
  09/13/26
(no link)
Poppy corner
  09/13/26
https://i.imgur.com/hWmaZZO.jpeg
vibrant at-the-ready theater
  09/13/26
"Some of the safeguards Anthropic decided on were unsur...
vibrant at-the-ready theater
  09/13/26
GPT-6 Astra Users Say OpenAI's Newest Model Got Dumber. It H...
vibrant at-the-ready theater
  09/13/26
this thread sure triggered some folks
vibrant at-the-ready theater
  09/13/26


Poast new message in this thread



Reply

Date: September 13th, 2026 2:16 PM
Author: vibrant at-the-ready theater

since they swap out models on the back end or bump you down to lower quants without informing you

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133609)



Reply

Date: September 13th, 2026 2:20 PM
Author: Poppy corner

Link to OpenAI cannot be tested

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133616)



Reply

Date: September 13th, 2026 2:28 PM
Author: vibrant at-the-ready theater

(illiterate)

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133633)



Reply

Date: September 13th, 2026 2:30 PM
Author: Poppy corner

So no link will be forthcoming

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133636)



Reply

Date: September 13th, 2026 2:32 PM
Author: vibrant at-the-ready theater

Did you hear guise? Anthropic promised not to do this no more. Now they TELL you when you're bumped over to an older model

https://i.imgur.com/r0WpQZw.jpeg

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133640)



Reply

Date: September 13th, 2026 2:33 PM
Author: Poppy corner

I see a link but it doesn't match what OP said

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133642)



Reply

Date: September 13th, 2026 2:33 PM
Author: vibrant at-the-ready theater

hi RSF

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133646)



Reply

Date: September 13th, 2026 2:33 PM
Author: Poppy corner

Link?

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133647)



Reply

Date: September 13th, 2026 2:34 PM
Author: vibrant at-the-ready theater

that's a non-denial

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133651)



Reply

Date: September 13th, 2026 2:36 PM
Author: Poppy corner

(no link)

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133658)



Reply

Date: September 13th, 2026 2:35 PM
Author: vibrant at-the-ready theater

https://i.imgur.com/hWmaZZO.jpeg

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133655)



Reply

Date: September 13th, 2026 2:37 PM
Author: vibrant at-the-ready theater

"Some of the safeguards Anthropic decided on were unsurprising: The company said it would reroute users who asked questions about cybersecurity, biology, or chemistry to a less capable AI model"

https://www.wired.com/story/anthropic-responds-to-backlash-on-claudes-secret-sabotage-on-ai-research/

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133662)



Reply

Date: September 13th, 2026 3:23 PM
Author: vibrant at-the-ready theater

GPT-6 Astra Users Say OpenAI's Newest Model Got Dumber. It Happened Before, Too

A week after launch, complaints are rolling in from users that GPT-6 Astra has been nerfed. OpenAI's last model went through the same cycle in July.

Jose Antonio Lanz

By Jose Antonio Lanz

Edited by Guillermo Jimenez

Sep 12, 2026

https://decrypt.co/378101/gpt-6-astra-openai-model-dumber-nerfed

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133765)



Reply

Date: September 13th, 2026 4:43 PM
Author: vibrant at-the-ready theater

this thread sure triggered some folks

(https://xoxohth.com/thread.php?thread_id=5903512&forum_id=2#50133914)