Technologies

Gen AI Chatbots Are Starting to Remember You. Should You Let Them?

An AI model’s long memory can offer a better experience — or a worse one. Good thing you can turn it off.

Until recently, generative AI chatbots didn’t have the best memories: You tell it something and, when you come back later, you start again with a blank slate. Not anymore.

OpenAI started testing a stronger memory in ChatGPT last year and rolled out improvements this month. Grok, the flagship tool of Elon Musk’s xAI, also just got a better memory.

It took significant improvements in math and technology to get here but the real-world benefits seem pretty simple: You can get more consistent and personalized results without having to repeat yourself.

«If it’s able to incorporate every chat I’ve had before, it does not need me to provide all that information the next time,» said Shashank Srivastava, assistant professor of computer science at the University of North Carolina at Chapel Hill.

Those longer memories can help with solving some frustrations with chatbots but they also pose some new challenges. As with when you talk to a person, what you said yesterday might influence your interactions today.

Here’s a look at how the bots came to have better memories and what it means for you.

Improving an AI model’s memory

For starters, it isn’t quite a «memory.» Mostly, these tools work by incorporating past conversations alongside your latest query. «In effect, it’s as simple as if you just took all your past conversations and combined them into one large prompt,» said Aditya Grover, assistant professor of computer science at UCLA.

Those large prompts are now possible because the latest AI models have significantly larger «context windows» than their predecessors. The context window is, essentially, how much text a model can consider at once, measured in tokens. A token might be a word or part of a word (OpenAI offers one token as three-quarters of a word as a rule of thumb).

Early large language models had context windows of 4,000 or 8,000 tokens — a few thousand words. A few years ago, if you asked ChatGPT something, it could consider roughly as much text as is in this recent CNET cover story on smart thermostats. Google’s Gemini 2.0 Flash now has a context window of a million tokens. That’s a bit longer than Leo Tolstoy’s epic novel War and Peace. Those improvements are driven by some technical advances in how LLMs work, creating faster ways to generate connections between words, Srivastava said.

Other techniques can also boost a model’s memory and ability to answer a question. One is retrieval-augmented generation, in which the model can run a search or otherwise pull up documents as needed to answer a question, without always keeping all of that information in the context window. Instead of having a massive amount of information available at all times, it just needs to know how to find the right resource, like a researcher perusing a library’s card catalog.

Read more: AI Essentials: 27 Ways to Make Gen AI Work for You, According to Our Experts

Why context matters for a chatbot

The more an LLM knows about you from its past interactions with you, the better suited to your needs its answers will be. That’s the goal of having a chatbot that can remember your old conversations.

For example, if you ask an LLM with no memory of you what the weather is, it’ll probably follow up first by asking where you are. One that can remember past conversations, however, might know that you often ask it for advice about restaurants or other things in San Francisco, for example, and assume that’s your location. «It’s more user-friendly if the system knows more about you,» Grover said.

A chatbot with a longer memory can provide you with more specific answers. If you ask it to suggest a gift for a family member’s birthday and tell it some details about that family member, it won’t need as much context when you ask again next year. «That would mean smoother conversations because you don’t need to repeat yourself,» Srivatsava said.

A long memory, however, can have its downsides.

You can (and maybe should) tell AI to forget

Having a chatbot recommend a gift poses a conundrum that’s all too common in human memories: You told your aunt you liked airplanes when you were 12 years old, and decades later you still get airplane-themed gifts from her. An LLM that remembers things about you could bias itself too much toward something you told it before.

«There’s definitely that possibility that you can lose your control and that this personalization could haunt you,» Srivastava said. «Instead of getting an unbiased, fresh perspective, its judgment might always be colored by previous interactions.»

LLMs typically allow you to tell them to forget certain things or to exclude some conversations from their memory.

You may also deal with things you don’t want an AI model to remember. If you have private or sensitive information you’re communicating with an LLM (and you should think twice about doing so at all), you probably want to turn off the memory function for those interactions.

Read the guidance on the tool you’re using to be sure you know what it’s remembering, how to turn it on and off and how to delete items from its memory.

Grover said this is an area where gen AI developers should be transparent and offer clear commands in the user interface. «I think they need to be providing more controls that are visible to the user, when to turn it on, when to turn it off,» he said. «Give a sense of urgency for the user base so they don’t get locked into defaults that are hard to find.»

How to turn off gen AI memory features

Here’s how to manage memory features in some common gen AI tools.

ChatGPT

OpenAI has a couple types of memory in its models. One is called «reference saved memories» and it stores details that you specifically ask ChatGPT to save, like your name or dietary preferences. Another, «reference chat history,» remembers information from past conversations (but not everything).

To turn off either of these features, you can go to Settings and Personalization and toggle the items off.

You can ask ChatGPT what it remembers about you and ask it to forget something it has remembered. To completely delete this information, you can delete the saved memories in Settings and the chat where you saved that information.

Gemini

Google’s Gemini model can remember things you’ve discussed or summarize past conversations.

To modify or delete these memories, or to turn off the feature entirely, you can go into your Gemini Apps Activity menu.

Grok

Elon Musk’s xAI announced memory features in Grok this month and they’re turned on by default.

You can turn them off under Settings and Data Controls. The specific setting is different between Grok.com, where it’s «Personalize Grok with your conversation history,» and on the Android and iOS apps, where it’s «Personalize with memories.»

Technologies

Today’s NYT Connections: Sports Edition Hints and Answers for March 26, #549

Here are hints and the answers for the NYT Connections: Sports Edition puzzle No. 549 for Thursday, March 26.

Looking for the most recent regular Connections answers? Click here for today’s Connections hints, as well as our daily answers and hints for The New York Times Mini Crossword, Wordle and Strands puzzles.

How good are you at unscrambling letters to make a new word out of an old one? Today’s Connections: Sports Edition requires you to do just that — for the purple category, naturally. If you’re struggling with today’s puzzle but still want to solve it, read on for hints and the answers.

Connections: Sports Edition is published by The Athletic, the subscription-based sports journalism site owned by The Times. It doesn’t appear in the NYT Games app, but it does in The Athletic’s own app. Or you can play it for free online.

Read more: NYT Connections: Sports Edition Puzzle Comes Out of Beta

Hints for today’s Connections: Sports Edition groups

Here are four hints for the groupings in today’s Connections: Sports Edition puzzle, ranked from the easiest yellow group to the tough (and sometimes bizarre) purple group.

Yellow group hint: Touch ’em all!

Green group hint: It’s outta here!

Blue group hint: Working one’s way up to the majors.

Purple group hint: Unscramble these words.

Answers for today’s Connections: Sports Edition groups

Yellow group: Slang for home run.

Green group: MLB home run leaders in 2025.

Blue group: Minor league baseball leagues.

Purple group: Anagrams of MLB teams.

Read more: Wordle Cheat Sheet: Here Are the Most Popular Letters Used in English Words

What are today’s Connections: Sports Edition answers?

The yellow words in today’s Connections

The theme is slang for home run. The four answers are dinger, homer, jack and round-tripper.

The green words in today’s Connections

The theme is MLB home run leaders in 2025. The four answers are Judge, Ohtani, Raleigh and Schwarber.

The blue words in today’s Connections

The theme is minor league baseball leagues. The four answers are Carolina, International, Pacific Coast and Texas.

The purple words in today’s Connections

The theme is anagrams of MLB teams. The four answers are Bucs (Cubs), parties (Pirates), spread (Padres) and stem (Mets).

Toughest Connections: Sports Edition categories

The Connections: Sports Edition puzzle can be tough, but it really depends on which sports you know the most about. My husband aces anything having to do with Formula 1, my best friend is a hockey buff, and I can answer any question about Minnesota teams.

That said, it’s hard to pick the toughest Connections categories, but here are some I found exceptionally mind-blowing.

#1: Serie A Clubs. Answers: Atalanta, Juventus, Lazio, Roma.

#2: WNBA MVPs. Answers: Catchings, Delle Donne, Fowles and Stewart.

#3: Premier League team nicknames. Answers: Bees, Cherries, Foxes and Hammers.

#4: Homophones of NBA player names. Answers: Barns, Connect, Heart and Hero.

Technologies

Today’s NYT Strands Hints, Answers and Help for March 26 #753

Here are hints and answers for the NYT Strands puzzle for March 26, No. 753.

Looking for the most recent Strands answer? Click here for our daily Strands hints, as well as our daily answers and hints for The New York Times Mini Crossword, Wordle, Connections and Connections: Sports Edition puzzles.

Today’s NYT Strands puzzle should appeal to musicians of all kinds. Some of the answers are difficult to unscramble, so if you need hints and answers, read on.

I go into depth about the rules for Strands in this story.

If you’re looking for today’s Wordle, Connections and Mini Crossword answers, you can visit CNET’s NYT puzzle hints page.

Read more: NYT Connections Turns 1: These Are the 5 Toughest Puzzles So Far

Hint for today’s Strands puzzle

Today’s Strands theme is: I blew it!

If that doesn’t help you, here’s a clue: I’m in the band.

Clue words to unlock in-game hints

Your goal is to find hidden words that fit the puzzle’s theme. If you’re stuck, find any words you can. Every time you find three words of four letters or more, Strands will reveal one of the theme words. These are the words I used to get those hints but any words of four or more letters that you find will work:

NORM, CARL, MODE, MODES, LUTE, COME, COME, BEND, NITE, TINE, HARM

Answers for today’s Strands puzzle

These are the answers that tie into the theme. The goal of the puzzle is to find them all, including the spangram, a theme word that reaches from one side of the puzzle to the other. When you have all of them (I originally thought there were always eight but learned that the number can vary), every letter on the board will be used. Here are the nonspangram answers:

OBOE, FLUTE, CLARINET, RECORDER, HARMONICA

Today’s Strands spangram

Today’s Strands spangram is WINDINSTRUMENT. To find it, start with the W that is at the bottom of the far-left vertical row, and wind up and across.

Toughest Strands puzzles

Here are some of the Strands topics I’ve found to be the toughest.

#1: Dated slang. Maybe you didn’t even use this lingo when it was cool. Toughest word: PHAT.

#2: Thar she blows! I guess marine biologists might ace this one. Toughest word: BALEEN or RIGHT.

#3: Off the hook. Again, it helps to know a lot about sea creatures. Sorry, Charlie. Toughest word: BIGEYE or SKIPJACK.

Technologies

Ring Finally Goes Wire-Free for Its Latest 4K Video Doorbells

The launch of battery-powered versions of the company’s powerful AI doorbells has been highly anticipated.

Security company Ring on Wednesday announced a significant expansion of its video doorbell line, notably battery-powered versions of both its 4K and 2K models, priced from $80.

Both Amazon’s Ring and Google Nest debuted high-resolution video doorbells with new AI features in the fall of 2025. But they were wired only, and in my tests, I kept thinking, «I sure wish there were battery models available.»

Wireless video doorbells are far better for most front doors than models that require connecting to your existing doorbell wiring, which is often poorly positioned for a security camera. Mine, for example, is located on a wall beside my door that’s useless for any kind of video views, no matter how you angle a lens.

«Enhancing image quality in battery-powered doorbells means customers can enjoy reliable performance with the flexibility to install devices in a way that suits their space, whether renting or living in homes without existing wiring,» a Ring spokesperson said.

At first, I wondered whether the higher 4K resolutions and more advanced AI features would use too much power to support batteries. If so, Ring is the first to fix that issue with this suite of doorbells, including these models available for preorder right now:

Ring Battery Doorbell Pro — $250: This model offers up to 4K resolution and 10x zoom, and Ring says it features a redesigned internal architecture to support battery power.
Ring Battery Doorbell Plus (2nd-gen) — $180: This model includes a quick-release battery pack along with 2K video.
Ring Battery Doorbell (2nd-gen) — $100: This video doorbell includes 2K video, a 6x zoom and what Ring calls a «streamlined, rechargeable design,» which means you take the entire video doorbell to charge it, not just the battery — a design I greatly prefer, since Ring’s battery packs can get fiddly.

There’s also a new version of a Ring wired doorbell with 2K resolution, starting at $80. It wouldn’t be Ring without a plethora of doorbell devices to confuse newcomers, which is why I have a guide specifically for Ring video doorbells that will need some updating once I finish testing these new models.

Resolution plus an intelligence upgrade

Ring’s ordinary subscriptions of the Ring Protect plan give you cloud video storage and intelligent alerts for people, packages and vehicles, which are important but not really advanced AI. But spring for the $20-per-month Ring AI Pro cam, and this new generation of cameras opens up other capabilities.

Ring’s AI features include AI video descriptions, so if you get an alert, you can also get a summary of what the doorbell saw, including people and activities. A similar feature lets you search your video history with specific terms, such as «bike,» «truck» and so on. You also get the beta version of Ring’s Familiar Faces feature, which can ID logged faces of people who approach.

If these AI features make you uneasy and you’d rather protect your privacy, the best option is to avoid a subscription altogether or choose a lower-tier plan that gives you cloud storage without AI.

I also have a guide on how to turn off Ring’s detection and data-sharing features that might make you nervous, so you can keep what you like while ditching what you don’t.