top | item 46876851 (no title) uberman | 26 days ago Why do you feel an older cut off degrades the model? Perhaps it improves it as the model has limited training on AI garbage. discuss order hn newest unsupp0rted|26 days ago That's a possible hypothesis, but qualitatively the model seems to be so much less capable than it was even 4 hours ago.And I'm talking about GPT 5.2 High (non-codex), which is the best trade-off model for capability vs. speed.It's like talking to a senior programmer who all of a sudden experienced a traumatic injury. Noticeable. uberman|26 days ago Interesting. For what it is worth, I use Claude Opus at the moment and I am generally impressed.
unsupp0rted|26 days ago That's a possible hypothesis, but qualitatively the model seems to be so much less capable than it was even 4 hours ago.And I'm talking about GPT 5.2 High (non-codex), which is the best trade-off model for capability vs. speed.It's like talking to a senior programmer who all of a sudden experienced a traumatic injury. Noticeable. uberman|26 days ago Interesting. For what it is worth, I use Claude Opus at the moment and I am generally impressed.
uberman|26 days ago Interesting. For what it is worth, I use Claude Opus at the moment and I am generally impressed.
unsupp0rted|26 days ago
And I'm talking about GPT 5.2 High (non-codex), which is the best trade-off model for capability vs. speed.
It's like talking to a senior programmer who all of a sudden experienced a traumatic injury. Noticeable.
uberman|26 days ago