Many users praise Codex's task listing, renaming, and cross-thread messaging for saving time and enabling better coordination across threads, while some criticize the model's literal behavior and inconsistent tool access as disruptive.
Based on 18 visible X reactions from 29 accounts; directional sample.
Ask a question below.
Published answers will appear here.
Yes but who cares when the model is so utterly autistic and literal to each and every single character in a prompt instead of the context and meaning of what is being said, that it is only good for implementation of plans that need to first be made absolutely bullet proof so GPT cannot misinterpret anything whatsoever.
@jxnlco After 11 months of using nothing but OpenAI, this batshit insane autism of 5.6 was what broke me and made me cancel my Pro subscription and go back to Banthropic, for as much as I hate Anthropic as a company
@jxnlco Oh nice to know. Btw the "search" thing in the projects when you open a new chat is great, saves me a lot of time!
@jxnlco man this saved me hours juggling prototypes last sprint
I'v found sending messages between threads super useful. I might have a long running thread, then start some investigation in another thread. Then I tell it then when it's done with its investigation, it should write a markdown report and let the long running thread know
daily reminder, codex self control: it can list all the tasks and sessions that are available it can rename every single title it can send a message to each task from another thread.
Many users praise Codex's task listing, renaming, and cross-thread messaging for saving time and enabling better coordination across threads, while some criticize the model's literal behavior and inconsistent tool access as disruptive.
Based on 18 visible X reactions from 29 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@jxnlco are these new capabilities? they're all things I've asked codex to do in the past that it said it couldn't do