Anyone frustrated with GPT-6 Astra lately? The quality swings wildly from session to session. It feels like the backend is silently redirecting to Luna or other models. I wasn't aware OpenAI did this, but now it makes so much sense because some of the answers and performance read very much like a different model.
Lately it misses obvious details in the code, only to say "oh yeah, I should have mentioned that!"
I explicitly tell it to look at the code in the context, then I start to realize it's making generalizations. "oh yeah, I should have answered from the code!"
The frustrating aspect is that the items listed above are like models from 6-12 months ago. Astra is absolutely amazing and shouldn't perform this way.
Comments URL: https://news.ycombinator.com/item?id=50493498
Points: 1
# Comments: 2
