{"id":86666,"date":"2025-10-20T13:00:09","date_gmt":"2025-10-20T13:00:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/86666\/"},"modified":"2025-10-20T13:00:09","modified_gmt":"2025-10-20T13:00:09","slug":"chatgpt-is-smarter-now-that-its-learned-to-forget-a-huge-memory-upgrade-is-coming","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/86666\/","title":{"rendered":"ChatGPT is smarter now that it’s learned to forget – a huge memory upgrade is coming"},"content":{"rendered":"

ChatGPT\u2019s memory feature<\/a> transformed the AI chatbot<\/a> by letting it remember facts shared across conversations, allowing users to have a somewhat personalised version that knows their name, preferences, and even their coffee order if they want. Now, OpenAI is giving ChatGPT’s memory a powerful enhancement: the ability to forget.<\/p>\n

But while ChatGPT<\/a> accumulated data on users either added manually or that the model concluded was important, it had some fundamental problems. Manually managing, reviewing, and deleting memories as necessary is tedious enough, but not doing it would mean running into an annoying \u201cmemory full\u201d message.<\/p>\n

<\/p>\n

That’s why the new automatic memory prioritisation rolling out for ChatGPT is so intriguing. Giving the model the ability to decide which memories are still relevant, what can fade into the background, and how to keep your conversations useful is potentially enormous.<\/p>\n

ChatGPT decides what stays \u201ctop of mind\u201d based on how recently and frequently you\u2019ve mentioned something. It\u2019s a little like how your own brain filters what to focus on in any given moment. ChatGPT isn\u2019t erasing anything; it\u2019s just learning to weigh information in a way that feels more natural.<\/p>\n

If you\u2019ve spent the last week asking about toddler sleep schedules, that\u2019ll rise to the surface. If you haven\u2019t brought up your sourdough starter since June, it quietly moves lower on the list. All of this happens without you having to manually prune anything, which is good news for those of us who treat digital settings menus the same way we treat appliance manuals: with vague respect and active avoidance.<\/p>\n

ChatGPT can now automatically manage your saved memories\u2014no more \u201cmemory full.\u201dYou can also search and sort memories by recency, and choose which to re-prioritize in settings.Rolling out to Plus and Pro users on the web globally starting today. https:\/\/t.co\/T1vSNH5289 pic.twitter.com\/xRHLFTu2AmOctober 15, 2025<\/a><\/p>\n

This memory rework is deceptively simple in concept but radical in implication. With little fanfare, OpenAI has taught ChatGPT to self-sort. And that pushes it from a reactive tool into something better designed for the long haul. <\/p>\n

You still have full control over ChatGPT’s memory, it should be said. You can scroll through your memories, see what ChatGPT thinks is \u201ctop of mind,\u201d and adjust it like you\u2019re editing a playlist. <\/p>\n

You can bump up a memory about your dietary restrictions, downgrade your brief but intense obsession with medieval cheese trivia, or just wipe things out entirely. You can even roll back memories to previous versions.<\/p>\n

AI memory banks<\/p>\n

But the biggest change isn\u2019t in what you can do, it\u2019s in what you don\u2019t have to do anymore. Until now, the memory system has been one of ChatGPT’s most high-maintenance aspects. Power users could get a lot out of it, but it required you to keep things in order like a digital closet. The more you used it, the more you had to manage it.<\/p>\n

That\u2019s fine if you\u2019re the type to keep your desktop files colour-coded and your email inbox at zero. But for the average person who just wants their chatbot to remember they like their coffee iced and their emails polite, the old system was too much work.<\/p>\n

Now, at least theoretically, ChatGPT treats your preferences less like a static list of facts and more like a shared digital document you’re both editing. In that sense, this isn\u2019t just a technical update. It\u2019s a social one.<\/p>\n

It’s worth saying that manually checking ChatGPT memories is probably still a good idea, as the AI can mess up there just as much as in its responses to prompts, but that\u2019s where it looks like OpenAI is trying to strike a balance. <\/p>\n

The memory system is automatic, but not opaque. You can see exactly what\u2019s stored. You can reprioritise. You can delete. You can even shut it off completely. But memory isn\u2019t just a luxury add-on. For any AI assistant worth its salt, it\u2019s going to become foundational.<\/p>\n

Because without memory, and ideally a memory full of actually relevant information, most AI tools have a ceiling of usefulness. They can answer questions and brainstorm, but lack the continuity that makes for better tools long-term. It’s not flashy, but automated memory management is ultimately a pretty memorable idea for a feature.<\/p>\n

Follow TechRadar on Google News<\/a> and add us as a preferred source<\/a> to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!<\/p>\n

And of course you can also follow TechRadar on TikTok<\/a> for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp<\/a> too.<\/p>\n

You might also like<\/p>\n