- 55comments
- 157comments
- 5comments
- 81comments
- 83comments
- 39comments
- 28comments
- 444comments
- 8comments
- 217comments
- —discuss
- 1comments
- 248comments
- 33comments
- 3comments
- 24comments
- 334comments
- 90comments
- 65comments
- 158comments
- 304comments
- 21comments
- 408comments
- 7comments
- 95comments
- 17comments
- 46comments
- 234comments
- —discuss
- 26comments
Do people prefer the new flat style LLMs are producing? I don’t mind it as much as the gradient theme they were pumping out previously.
It still matters, but in the age of good reasoning, tool use, and web search, this is much less of a problem than it used to be.
all the reasoning still comes from pretraining data
After Trump's last inauguration, ChatGPT would still tell me that Biden was President of the US. I understand that the training cutoff was before Biden dropped out. But it knew, or should have known, the current date and that there had been an election since its last update, but it didn't qualify the answer. When I asked it to search the web, it got it right. The moral I took away was to always ask for the search whenever I ask about current events. I do that so routinely that I wouldn't know if this problem has been fixed. I suppose that failing to update my priors per individual model release is a form of bigotry against a widely hated class.
ChatGPT recently started web searching for for basically every general knowledge question, which I found quite odd. Maybe an overcorrection to the issue you were having?
I remember when the US captured Venezuelan president Maduro, and when I posed a prompt related to this, the model said that’s pure fiction. I told it to double check. Still didn’t want to entertain the idea. It only acquiesced when I specifically directed it to check Reuters. I haven’t noticed this problem in months. Model cutoff seems to be less of a problem these days.