Rae Lasko

personality @openai

[Rae Lasko @raelasko]

@subramanya @Aria_Churchill @OpenAI when you make a new project you can click the gear to scope memory to project only!

[Rae Lasko @raelasko]

@giffmana I generally agree with this! The tricky part will be getting the the "often (but not always)" part right. Examples or screenshots of before/afters would be super helpful, feel free to dm me!

[Rae Lasko @raelasko]

@phuguo Legend

[Rae Lasko @raelasko]

my job is weird sometimes & i love it https://t.co/wrtPpDlkgl

[Rae Lasko @raelasko]

you know whats really humbling is when you tell codex to update the script to use a different model or something and its like "no dummy, just use the command line arg i already made for you"

[Rae Lasko @raelasko]

This was one of my favorite features to work on!
ChatGPT can now directly modify your UI accent color, flip between dark mode/light mode, and switch to a new personality when asked.

[Rae Lasko @raelasko]

@springertimo @DataChaz good q – personalities don't change capabilities eg all personalities are equally good at coding.
BUT they influence content of subjective answers like
they'll all tell different jokes!

[Rae Lasko @raelasko]

@_simonsmith Thanks for flagging! we're looking into it!

[Sam Altman @sama]

Small-but-happy win:

If you tell ChatGPT not to use em-dashes in your custom instructions, it finally does what it's supposed to do!

[Rae Lasko @raelasko]

@stellashimonaka great work!!

[Rae Lasko @raelasko]

@dlevine815 congrats! exciting!!

[Rae Lasko @raelasko]

@emollick good question! personalities don't affect chatgpt's core capabilities (they're all equally good at code for instance) but can change some very subjective answers. like quirky will tell different jokes than professionals! we're pushing some copy to clarify this

[Rae Lasko @raelasko]

@julez_122 @emollick they work together! though you may get inconsistent behavior if personality and custom instructions directly conflict

[Rae Lasko @raelasko]

@CodewithP @sama try cynic!

[Rae Lasko @raelasko]

@potato_log @sama try Candid!

[Rae Lasko @raelasko]

@XiangningChen most excited for this part!

[Rae Lasko @raelasko]

another day, another ship!

[Sam Altman @sama]

Also, we've made it easier to customize ChatGPT. You can pick from presets (Default, Friendly, Efficient, Professional, Candid, or Quirky) or tune it yourself.

[Fidji Simo @fidjissimo]

GPT-5.1 is a great new model that we think people are going to like more than 5. But with 800M+ people using ChatGPT, one default personality won’t work for everyone. We launched new preset personalities so people can make ChatGPT their own. 
https://t.co/oYcRqKfYoF