ofseed
Specifically, 3.8 Flash suffers from far more hallucinations than 3.1 Pro and frequently ignores the context between consecutive messages. These two issues are fatal to the chat experience.
Because of this experience, I believe that benchmarks are quite limited to evaluate a model's real-world performance, and most current benchmarks focus on coding performance rather than chatting. At the moment, I have almost no reason to use 3.8 Flash.
I've been using GPT since its 3.5 release, but starting from 5, its output always contains some meaningless nonsense or provides answers that are difficult to read just to avoid hallucinations. I find Gemini to be excellent for chatting. For example, when I'm pondering a mathematical theorem, it could provides answers that inspire me, even guiding me to think about the next question.
For me, this is the only reason to maintain multiple AI subscriptions. Gemini is irreplaceable in the realm of answering questions or chatting for learning purposes; I can leave the rest to GPT.
For example, a common scenario is rolling back a file via git, which triggers this reset. However, considering they treated it as a reliable version control system without actually reading the documentation, they probably aren't using git anyway.
The good news for them, however, is that they actually can bypass this limitation and treat their undo history like version control—by using nvim-fundo [1]. The catch is that they'll have to switch to nvim, as there isn't a direct equivalent for vim.
1. [nvim-fundo](https://github.com/kevinhwang91/nvim-fundo)
A few weeks later, Bun began the Rust rewrite. Although not explicitly stated, I suspect these two events may be related.