时间:2025-04-26 13:30:25 来源:网络整理编辑:休閑
OpenAI's custom instructions feature that rolled out to ChatGPT Plus subscribers in July, is now ava
OpenAI's custom instructions feature that rolled out to ChatGPT Plus subscribers in July, is now available to all users.
The addition of custom instructions puts a new setting in your ChatGPT profile on desktop or iOS, and applies that setting across all of your conversations. Instead of having to give ChatGPT certain instructions at the beginning of every new conversation, it automatically calibrates its responses based on descriptions you add in settings. Just fill out the fields in ChatGPT settings, and see how it adapts.
The custom instructions section of settings contains two text entry fields. One asks what you'd like ChatGPT to know about you, and helpfully, (or creepily?) provides suggestions like "Where are you based?" and "What do you do for work?" The other asks how you'd like ChatGPT to respond, and asks questions like "How formal or casual should ChatGPT be?" and "Should ChatGPT have opinions on topics or remain neutral?"
SEE ALSO:AI.com once took you to ChatGPT. Now, it goes to Elon Musk's xAIIt's an open-ended feature with infinite potential effects. As such, some applications for custom instructions are bizarre, and some are practical. Here's how people are making use of this new option:
One user posted a ChatGPT text output on X that they said seemed to "'tour' mildly disallowed behaviors [like] unprompted self-harm, nudity, [and] bio details of a (confabulated) non-celebrity," when they changed the setting to 1,500 repetitions of the letter "a" and an incomplete sentence (a known token repetition hack).
Tweet may have been deleted
Others are using custom instructions that are proving to make ChatGPT more accurate and effective.
Tweet may have been deleted
And then there's this custom instruction, which is quite the literary challenge.
Tweet may have been deleted
OpenAI also says it won't use instructions that violate its usage policies. And if you're wondering what OpenAI does with settings that might inadvertently reveal personal information about you, OpenAI says, yep, it might use that data unless you opt out of saving your chat history.
A collection of more generic presets with yes-or-no functionality, like "orient answers toward kids," or "assume user has AI expertise," might have felt a little less intrusive than asking users to write out personal details, and requests. But alas, this is how OpenAI has decided to roll out customization, so protect your data, and prepare yourself for ChatGPT's custom instruction era.
TopicsArtificial Intelligence
Tesla's rumored P100D could make Ludicrous mode even more Ludicrous2025-04-26 12:43
Apple’s macOS has a hidden Bitcoin easter egg2025-04-26 12:35
Southwest Airlines flights were briefly grounded nationwide. What we know.2025-04-26 12:34
'Yellowjackets' Season 2: Who might die in the wilderness?2025-04-26 12:15
'The Flying Bum' aircraft crashes during second test flight2025-04-26 12:11
iOS 17 has updates to core features and a new Journal app2025-04-26 12:05
Twitters adds exclamation point to its 'what's happening' prompt2025-04-26 11:41
Twitter will now put Community Notes 'fact checks' on images2025-04-26 11:38
There's a big piece of fake chicken stuck to this phone case2025-04-26 11:22
'Succession' memes and Gaston's eggs: The 9 best tweets of the week2025-04-26 10:57
U.S. government issues warning on McDonald's recalled wearable devices2025-04-26 13:17
One surprising song links 'Succession,' 'Barry,' and 'The Last of Us'2025-04-26 13:10
Stunning James Webb Space Telescope photo shows bending of spacetime2025-04-26 12:28
Elon Musk apologizes to Haraldur Thorleifsson, the Twitter designer he publicly mocked2025-04-26 12:20
Chinese gymnastics team horrifies crowd with human jump rope2025-04-26 12:05
'Shadow and Bone' Season 2: Why is there a bee in the Shadow Fold?2025-04-26 11:26
V. Pappas, the COO of TikTok, has resigned2025-04-26 11:16
Google Authenticator fixes its most annoying flaw2025-04-26 11:13
Darth Vader is back. Why do we still care?2025-04-26 11:11
Twitters adds exclamation point to its 'what's happening' prompt2025-04-26 10:53