10th Indian Delegation to Dubai, Gitex & Expand North Star – World’s Largest Startup Investor Connect
Artificial Intelligence

ChatGPT will now remember — and forget — things you tell it to


You’ll soon be able to tell ChatGPT to forget things — or remember specific things in future conversations.

Today, as part of a test, OpenAI began rolling out new “memory” controls for a small portion of ChatGPT free and paid users, with a broader rollout to follow at some unspecified future point. The controls let you tell ChatGPT explicitly to remember something, see what it remembers or turn off its memory altogether.

OpenAI explains in a blog post:

“ChatGPT can now carry what it learns between chats, allowing it to provide more relevant responses … As you chat with ChatGPT, you can ask it to remember something specific or let it pick up details itself. ChatGPT’s memory will get better the more you use it and you’ll start to notice the improvements over time.”

It’s not hard to picture scenarios where a ChatGPT with memory could come in handy.

If, say, you wanted ChatGPT to recall you live in the suburbs and so prefer driving versus public transit directions, you can simply tell it (e.g. “Remember that I live in the suburbs and mostly drive.”). Or if you wanted its advice about child-rearing to pertain to younger kids because you have a kindergartner, you could highlight this fact for it (e.g. “Remember that I have a kindergartner.”).

OpenAI lists several ways in which memory could be useful in a business context, as well, like remembering tone, voice and formatting preferences for blog posts and languages and frameworks for programming.

ChatGPT memory

Image Credits: OpenAI

GPTs — custom chatbots powered by OpenAI’s models, available through the GPT Store — have their own memories. The Books GPT, for instance, can automatically remember which books you’ve already read and which genres you like best. But these memories aren’t shared with ChatGPT (or vice versa).

The memory feature for both ChatGPT and GPTs can be disabled at any time from the ChatGPT settings menu, and when it’s turned off, ChatGPT and GPTs won’t create or use memories. From this same menu, you can view and delete specific memories or clear all memories.

Note that deleting a chat from chat history won’t erase ChatGPT’s or a GPT’s memories — you have to delete the memory itself.

Now, one imagines that ChatGPT could, over time, accumulate a lot of sensitive personal details in its memory, especially considering that the memory feature is switched on by default. OpenAI acknowledges the possibility — and also says that it might use memories to improve its models, with a carve-out for ChatGPT business customers and users who’ve opt out.

But OpenAI also says that it’s taking steps to steer ChatGPT away from “proactively” remembering sensitive information, like health details, unless a user explicitly asks it to.

“ChatGPT’s memories evolve with your interactions and aren’t linked to specific conversations,” OpenAI writes. “[And] memories, like chats, with GPTs are not shared with GPT builders.”

For a more privacy-preserving experience, OpenAI’s rolling out a new Temporary Chat feature in ChatGPT, initially limited to a small subset of free and subscription users. With Temporary Chat, you can have a dialogue with a blank slate of sorts; ChatGPT won’t be aware of previous conversations or access memories but will follow custom instructions if they’re enabled.

ChatGPT Temporary Chat

Image Credits: OpenAI

OpenAI says it may keep a copy of Temporary Chat conversations for up to 30 days for “safety reasons,” however.



Source link

by Team SNFYI

Facebook is testing a new feature that invites some users—mainly in the US and Canada—to let Meta AI access parts of their phone’s camera roll. This opt-in “cloud processing” option uploads recent photos and videos to Meta’s servers so the AI can offer personalized suggestions, such as creating collages, highlight reels, or themed memories like birthdays and graduations. It can also generate AI-based edits or restyles of those images. Meta says this is optional and assures users that the uploaded media won’t be used for advertising. However, to enable this, people must agree to let Meta analyze faces, objects, and metadata like time and location. Currently, the company claims these photos won’t be used to train its AI models—but they haven’t completely ruled that out for the future. Typically, only the last 30 days of photos get uploaded, though special or older images might stay on Meta’s servers longer for specific features. Users have the option to disable the feature anytime, which prompts Meta to delete the stored media after 30 days. Privacy experts are concerned that this expands Meta’s reach into private, unpublished images and could eventually feed future AI training. Unlike Google Photos, which explicitly states that user photos won’t train its AI, Meta hasn’t made that commitment yet. For now, this is still a test run for a limited group of people, but it highlights the tension between AI-powered personalization and the need to protect personal data.

by Team SNFYI

News Update Bymridul     |    March 14, 2024 Meesho, an online shopping platform based in Bengaluru, has announced its largest Employee Stock Ownership Plan (ESOP) buyback pool to date, totaling Rs 200 crore. This buyback initiative extends to both current and former employees, providing wealth creation opportunities for approximately 1,700 individuals. Ashish Kumar Singh, Meesho’s Chief Human Resources Officer, emphasized the company’s commitment to rewarding its teams, stating, “At Meesho, our employees are the driving force behind our success.” Singh further highlighted the company’s dedication to providing opportunities for wealth creation despite prevailing macroeconomic conditions. This marks the fourth wealth generation opportunity at Meesho, with the size of the buyback program increasing each year. In previous years, Meesho conducted buybacks worth over Rs 8.2 crore in February 2020, Rs 41.4 crore in November 2020, and Rs 45.5 crore in October 2021. Meesho’s profitability journey began in July 2023, making it the first horizontal Indian e-commerce company to achieve profitability. Despite turning profitable, Meesho continues to maintain positive cash flow and focuses on enhancing efficiencies across various cost items. The company’s revenue from operations for FY 2022-23 witnessed a remarkable growth of 77% over the previous year, amounting to Rs 5,735 crore. This growth can be attributed to Meesho’s leadership position as the most downloaded shopping app in India in both 2022 and 2023, increased transaction frequency among existing customers, and a diversified category mix. Additionally, Meesho’s focus on improving monetization through value-added seller services contributed to its revenue growth. Meesho also disclosed its audited performance for the first half of FY 2023-24, reporting consolidated revenues from operations of Rs 3,521 crore, marking a 37% year-over-year increase. The company achieved profitability in Q2 FY24, with a significant reduction in losses compared to the previous year. Furthermore, Meesho recorded impressive app download numbers, reaching 145 million downloads in India in 2023 and surpassing 500 million downloads in H1 FY 2023-24. Follow Startup Story Source link

by Team SNFYI

You might’ve heard of Grok, X’s answer to OpenAI’s ChatGPT. It’s a chatbot, and, in that sense, behaves as as you’d expect — answering questions about current events, pop culture and so on. But unlike other chatbots, Grok has “a bit of wit,” as X owner Elon Musk puts it, and “a rebellious streak.” Long story short, Grok is willing to speak to topics that are usually off limits to other chatbots, like polarizing political theories and conspiracies. And it’ll use less-than-polite language while doing so — for example, responding to the question “When is it appropriate to listen to Christmas music?” with “Whenever the hell you want.” But Grok’s ostensible biggest selling point is its ability to access real-time X data — an ability no other chatbots have, thanks to X’s decision to gatekeep that data. Ask it “What’s happening in AI today?” and Grok will piece together a response from very recent headlines, while ChatGPT, by contrast, will provide only vague answers that reflect the limits of its training data (and filters on its web access). Earlier this week, Musk pledged that he would open source Grok, without revealing precisely what that meant. So, you’re probably wondering: How does Grok work? What can it do? And how can I access it? You’ve come to the right place. We’ve put together this handy guide to help explain all things Grok. We’ll keep it up to date as Grok changes and evolves. How does Grok work? Grok is the invention of xAI, Elon Musk’s AI startup — a startup reportedly in the process of raising billions in venture capital. (Developing AI’s expensive.) Underpinning Grok is a generative AI model called Grok-1, developed over the course of months on a cluster of “tens of thousands” of GPUs (according to an xAI blog post). To train it, xAI sourced data both from the web (dated up to Q3 2023) and feedback from human assistants that xAI refers to as “AI tutors.” On popular benchmarks, Grok-1 is about as capable as Meta’s open source Llama 2 chatbot model and surpasses OpenAI’s GPT-3.5, xAI claims. Image Credits: xAI Human-guided feedback, or reinforcement learning from human feedback (RLHF), is the way most AI-powered chatbots are fine-tuned these days. RLHF involves training a generative model, then gathering additional information to train a “reward” model and fine-tuning the generative model with the reward model via reinforcement learning. RLHF is quite good at “teaching” models to follow instructions — but not perfect. Like other models, Grok is prone to hallucinating, sometimes offering misinformation and false timelines when asked about news. And these can be severe — like wrongly claiming that the Israel–Palestine conflict reached a ceasefire when it hadn’t. For questions that stretch beyond its knowledge base, Grok leverages “real-time access” to info on X (and from Tesla, according to Bloomberg). And, similar to ChatGPT, the model has internet browsing capabilities, enabling it to search the web for up-to-date information about topics. Musk has promised improvements with the …