GPT-6.2 Astra review: frustrating to use, the model has no concept of knowledge gaps, its outputs are very hard to parse, and it runs in circles on long tasks (@theo)
@theo : GPT-6.2 Astra review: frustrating to use, the model has no concept of knowledge gaps, its outputs are very hard to parse, and it runs in circles on long tasks — Why I hate GPT-6.2 Astra
We haven't written up this one. Techmeme has the full story — the link below goes straight to it.
