【Lee Do】

OpenAI's custom instructions feature that rolled out to ChatGPT Plus subscribers in July,Lee Do 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.

ChatGPT really wants to know more about you. Credit: OpenAI

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?"

---

You May Also Like

---

---

SEE ALSO: AI.com once took you to ChatGPT. Now, it goes to Elon Musk's xAI

It'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:

Mashable Light Speed Want more out-of-this world tech, space and science stories? Sign up for Mashable's weekly Light Speed newsletter. By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy. Thanks for signing up!

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).

This Tweet is currently unavailable. It might be loading or has been removed.

Others are using custom instructions that are proving to make ChatGPT more accurate and effective.

This Tweet is currently unavailable. It might be loading or has been removed.

And then there's this custom instruction, which is quite the literary challenge.

---

Related Stories

---

• Researchers jailbreak AI chatbots, including ChatGPT
• ChatGPT has an Android app now
• OpenAI updates GPT-4 with new features
• OpenAI launches webcrawler GPTBot, and instructions on how to block it
• OpenAI announces $5 million partnership to support local news

This Tweet is currently unavailable. It might be loading or has been removed.

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.

Topics Artificial Intelligence

• Science
• Life
• Digital Culture
• Social Good
• Games
• Deals
• Tech
• Entertainment

• NYT Strands hints, answers for May 24
• 'You' Season 2 is still the depraved thriller you fell in love with
• 'You' Season 2 is still the depraved thriller you fell in love with
• Star Wars: Where to go for your fix now that Skywalker Saga is over
• Witch Kids of Instagram
• Cool blue phone cases inspired by Pantone's color of the year
• The feud between Britain and Sean Spicer is getting ridiculous
• End of an era: 2020 brings Tesla's federal tax credit to zero
• The Coronation of Macron
• SNL Christmas and Hanukkah songs that'll get you through the holidays

• Data scientist amid Facebook scandal didn't know of voter targeting
• Nimbus Data announces world's largest 3.5
• 5 businesses that are actively fighting Donald Trump
• VW will race its all
• Mark Zuckerberg still hasn't commented on Cambridge Analytica scandal
• Hot cross bun cones are the Frankenfectionery we're about this Easter
• Child pornography links found in Bitcoin's blockchain
• 'Avengers: Infinity War' is the longest MCU movie, obviously
• The tech talent gap is real. Increased diversity is the solution.
• Microsoft's forcing its Edge browser onto users through Mail app

• In Praise of Negative Reviews
• Donald Trump is killing Meals on Wheels and it's a serious problem
• Happy birthday to this dog who had the best possible reaction to her treat
• Everything to remember from 'YOU' Season 1
• I Dream of Content-Trash
• The very worst denim trends of 2019 (no, you cannot unsee this)
• Incredible sights from space as astronauts celebrate Christmas and Hanukkah
• Incredible sights from space as astronauts celebrate Christmas and Hanukkah
• In the House of a Thousand Likes
• Rapper tears into NME on Twitter after they put him on cover without permission

• Cardinal Cons
• Why the holidays warp our perception of time
• George Orwell's '1984' became too real this decade
• Boeing fires CEO in wake of 737 Max crisis
• The Vital Possibility of Abdul El-Sayed
• Volkswagen built a robot that can find your electric car in a parking lot and charge it
• 'Star Wars: The Rise of Skywalker' has a 'Harry Potter Cursed Child' problem
• The best reactions to that rogue McDonald's Trump tweet
• Swords into Marketshare
• How do you pronounce the weirdest emoticon on the internet? The debate continues to rage