zlacker

[parent] [thread] 4 comments
1. lukesc+(OP)[view] [source] 2025-05-06 16:14:16
I take preview to mean the model may be retired on an accelerated timescale and replaced with a "real" model so it's dangerous to put into prod unless you are paying attention.
replies(2): >>lolind+4b >>danena+Me
2. lolind+4b[view] [source] 2025-05-06 17:19:31
>>lukesc+(OP)
They could still use version numbers for that. 2.5.1-preview becomes 2.5.1 when stable.
3. danena+Me[view] [source] 2025-05-06 17:42:03
>>lukesc+(OP)
Scheduled tasks in ChatGPT are useful for keeping track of these kinds of things. You can have it check daily whether there's a change in status, price, etc. for a particular model (or set of models).
replies(1): >>cdolan+rp
◧◩
4. cdolan+rp[view] [source] [discussion] 2025-05-06 18:48:34
>>danena+Me
I appriciate that you are trying to help

But I do not want to have to build a network of bots with non-deterministic outputs to simply stay on top of versions

replies(1): >>danena+zq
◧◩◪
5. danena+zq[view] [source] [discussion] 2025-05-06 18:54:25
>>cdolan+rp
Neither do I, but it's the best solution I've found so far. It beats checking models/prices manually every day to see if anything has changed, and it works well enough in practice.

But yeah, some kind of deterministic way to get alerts would be better.

[go to top]