Rising rate of incomplete responses on o3 and o4-mini

I don’t know if anyone else is experiencing this, but I’ve noticed a substantial increase in occurrences where the reasoning models only refactor a small part of the code instead of giving a fully updated code when used for programming. Both in the API and ChatGPT.

In o3-mini that wasn’t nearly as frequent as now.

When using canvas, it is much more insistent on doing the performed changes, having to confirm that I do want to apply them, having to spend unnecessary extra interactions or instructions in the API, and in case of chatgpt in having to explicitly re-instruct that I do want the full code every time.

It doesn’t make sense in the canvas, to erase the previous code and put […rest of the code is unchanged] there. Then I ask again for the full code and it answers me ending with “# (rest of pipeline unchanged…)”

While I appreciate the new models, I think this is something to look over, as struggling to put the pieces together kind of defeats the purpose of making it practical.

11 Likes

I completly agree it s short output

1 Like

o4-mini-high is apparently better on paper, but in reality pales in comparison compared to its predecessor, first of all it hallucinates, which o3-mini-high never did for me even once
Overall its very lazy too, too prideful too lol, can show it screenshots and it tell me something is there when its clearly not, gaslighting just like the OG original chat gpt’s…