Users flag OpenAI reconnects and fast-draining limits mid 28-day challenge
A user tallies tibo's 28-day improvement challenge at day 15 with ~9 real fixes and 6 rollbacks, says reconnects persist and limits drain too fast, and questions whether the upcoming GPT-6.1 Terra beats Astra or Opus.
it's not looking good for openai tibo started a 28-day challenge to ship one improvement a day and we're on day 15 now so far we got 6 resets and about 9 good improvements only team said they fixed model capacity and reconnecting issues, but i'm still getting reconnecting and now users are reporting that limits are draining way too fast on top of that, team is planning to release gpt 6.1 terra which sits below 6.1 sol do we really need another model that isn't better than astra or opus? i don't know what's going on but it feels like something changed after sam agreed with dario to pace down dario went ahead and released his beasts while same really decided to pace down