Connect with us

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.» 

Related Topics:

Technologies

Today’s NYT Connections Hints, Answers and Help for Jan. 16, #950

Here are some hints and the answers for the NYT Connections puzzle for Jan. 16 #950.

Looking for the most recent 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, Connections: Sports Edition and Strands puzzles.

Today’s NYT Connections puzzle has a very intriguing blue group. You’ll notice some band names, but can you locate what they have in common? Read on for clues and today’s Connections answers.

The Times has a Connections Bot, like the one for Wordle. Go there after you play to receive a numeric score and to have the program analyze your answers. Players who are registered with the Times Games section can now nerd out by following their progress, including the number of puzzles completed, win rate, number of times they nabbed a perfect score and their win streak.

Read more: Hints, Tips and Strategies to Help You Win at NYT Connections Every Time

Hints for today’s Connections groups

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

Yellow group hint: Worn on heads.

Green group hint: Nighty-night.

Blue group hint: Bands with something alphabet-related in common.

Purple group hint: Like great.

Answers for today’s Connections groups

Yellow group: Kinds of hats.

Green group: Components of a kid’s bedtime routine.

Blue group: Musical acts with «A» as the only vowel.

Purple group: Grand ____.

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

What are today’s Connections answers?

The yellow words in today’s Connections

The theme is kinds of hats. The four answers are derby, fedora, Panama and porkpie.

The green words in today’s Connections

The theme is components of a kid’s bedtime routine.  The four answers are bath, brushing, pajamas and story.

The blue words in today’s Connections

The theme is musical acts with «A» as the only vowel. The four answers are Alabama, Bananarama, Kansas and Santana.

The purple words in today’s Connections

The theme is grand ____.  The four answers are Bahama, Canyon, piano and slam.

Don’t miss any of our unbiased tech content and lab-based reviews. Add CNET as a preferred Google source.

Quick tips for Connections

#1: Say the clue words out loud, pausing before and after each. That helps you hear the words in the context of a phrase. The Connections editors love to group words together that are used in similar phrasing, like ____ Up.

#2: Don’t go for the obvious grouping. These editors are smart. Once, they offered SPONGE, BOB, SQUARE and PANTS in the same puzzle. None of those words were in the same category. If you like, hit the «shuffle» button to give yourself a different perspective on the words.

#3: Break down any compound words and look for similarities. «Rushmore» was once in a puzzle where the connection was that each word started with the name of a rock band.

.

Continue Reading

Technologies

Today’s NYT Connections: Sports Edition Hints and Answers for Jan. 16, #480

Here are hints and the answers for the NYT Connections: Sports Edition puzzle for Jan. 16, No. 480.

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.

Today’s Connections: Sports Edition is a tough one, with some odd words and bizarre categories. If you’re struggling with it 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: Don’t get hurt!

Green group hint: Exaggerated language.

Blue group hint: Ouch!

Purple group hint: Not northern.

Answers for today’s Connections: Sports Edition groups

Yellow group: Protective gear.

Green group: Hype.

Blue group: Sharp things.

Purple group: «Southern ____» schools.

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 protective gear. The four answers are gloves, helmet, mouth guard and shoulder pads.

The green words in today’s Connections

The theme is hype. The four answers are anticipation, ballyhoo, buildup and buzz.

The blue words in today’s Connections

The theme is sharp things. The four answers are dart, hairpin turn, ice skate and javelin.

The purple words in today’s Connections

The theme is «Southern ____» schools. The four answers are California, Illinois, Methodist and Miss.

Don’t miss any of our unbiased tech content and lab-based reviews. Add CNET as a preferred Google source.

Quick tips for Connections: Sports Edition

#1: Don’t grab for the easiest group. For each word, think about other sports categories it might fit in – is this a word that can be used in football, or to describe scoring options?

#2: Second meanings are important. The puzzle loves to use last names and even college names that mean other things, to fool you into thinking they are words, not names.

#3: And the opposite is also true. Words like HURTS might seem like a regular word, but it’s also the last name of at least one pro athlete.

Continue Reading

Technologies

Today’s NYT Mini Crossword Answers for Friday, Jan. 16

Here are the answers for The New York Times Mini Crossword for Jan. 16.

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

Need some help with today’s Mini Crossword? I thought it was exceptionally tough today, and was convinced 1-Across was «MAD» Max. (Spoiler, it’s not.) I also figured 1-Down was BOOZE, which did not work with 1-Across, and was wrong either way. Read on for all the answers. And if you could use some hints and guidance for daily solving, check out our Mini Crossword tips.

If you’re looking for today’s Wordle, Connections, Connections: Sports Edition and Strands answers, you can visit CNET’s NYT puzzle hints page.

Read more: Tips and Tricks for Solving The New York Times Mini Crossword

Let’s get to those Mini Crossword clues and answers.

Mini across clues and answers

1A clue: ___ Max
Answer: HBO

4A clue: Where Marco Polo is played
Answer: POOL

5A clue: Overwhelming amount, metaphorically
Answer: FLOOD

6A clue: Reason for success in games like Candy Land and Chutes and Ladders
Answer: LUCK

7A clue: «That’s just the worst»
Answer: UGH

Mini down clues and answers

1D clue: Liquor, informally
Answer: HOOCH

2D clue: Winner of a Booker prize, fittingly
Answer: BOOK

3D clue: Antiquated
Answer: OLD

4D clue: Give a short promotion for
Answer: PLUG

5D clue: Winter malady
Answer: FLU

Don’t miss any of our unbiased tech content and lab-based reviews. Add CNET as a preferred Google source.

Continue Reading

Trending

Copyright © Verum World Media