[3cats-in-a-coat]

They're deprecating all the completion/edit models.

The chat models constantly argue with you on certain tasks and are highly opinionated. A completion API was a lot more flexible and "vanilla" about a wide variety of tasks, you could start a thought, or a task, and truly have it complete it.

The chat API doesn't complete, it responds (I mean of course internally it completes, but completes a response, rather than a continuation).

I find this a big step back, I hope the competition steps in to fill the gaps OpenAI keeps opening.

[saliagato]

Unfortunately their decisions are driven by model usage: gpt-3.5-turbo is the most used one (probably due to the low price and similar result)

[fredoliveira]

"similar" is a very bold claim ;-)

Comparable, perhaps.