Comment by Bombthecat 2 months ago Yap, not famous enough to train AI on it 2 comments Bombthecat Reply F7F7F7 2 months ago It’s getting better on Claude specifically now that training cutoffs are starting to move beyond the end of 2023.OpenAI models are a little less likely to trip up as long as you keep reminding it that it needs to account for v0.23+ throwaway77385 2 months ago I've found Gemini 2.5 pro to handle it ok. It forgets small things like using the deprecated model instead of baseModel and things like that, but nothing dramatic.
F7F7F7 2 months ago It’s getting better on Claude specifically now that training cutoffs are starting to move beyond the end of 2023.OpenAI models are a little less likely to trip up as long as you keep reminding it that it needs to account for v0.23+ throwaway77385 2 months ago I've found Gemini 2.5 pro to handle it ok. It forgets small things like using the deprecated model instead of baseModel and things like that, but nothing dramatic.
throwaway77385 2 months ago I've found Gemini 2.5 pro to handle it ok. It forgets small things like using the deprecated model instead of baseModel and things like that, but nothing dramatic.
It’s getting better on Claude specifically now that training cutoffs are starting to move beyond the end of 2023.
OpenAI models are a little less likely to trip up as long as you keep reminding it that it needs to account for v0.23+
I've found Gemini 2.5 pro to handle it ok. It forgets small things like using the deprecated model instead of baseModel and things like that, but nothing dramatic.