Apple rejects Musk claim of App Store bias
Musk has accused Apple of giving unfair preference to ChatGPT on its App Store and threatened legal action, triggering a fiery exchange with OpenAI CEO Sam Altman this week.
'The App Store is designed to be fair and free of bias,' Apple said in reply to an AFP inquiry.
'We feature thousands of apps through charts, algorithmic recommendations, and curated lists selected by experts using objective criteria.'
Apple added that its goal at the App Store is to offer 'safe discovery' for users and opportunities for developers to get their creations noticed.
But earlier this week, Musk said Apple was 'behaving in a manner that makes it impossible for any AI company besides OpenAI to reach #1 in the App Store, which is an unequivocal antitrust violation,' without providing evidence to back his claim.
BT in your inbox
Start and end each day with the latest news stories and analyses delivered straight to your inbox.
Sign Up
Sign Up
'xAI will take immediate legal action,' he said on his social media network X, referring to his own artificial intelligence company, which is responsible for Grok.
X users responded by pointing out that China's DeepSeek AI hit the top spot in the App Store early this year, and Perplexity AI recently ranked number one in the App Store in India.
DeepSeek and Perplexity compete with OpenAI and Musk's startup xAI.
Altman called Musk's accusation 'remarkable' in a response on X, charging that Musk himself is said to 'manipulate X to benefit himself and his own companies and harm his competitors and people he doesn't like.'
Musk called Altman a 'liar' in the heated exchange.
OpenAI and xAI recently released new versions of ChatGPT and Grok.
App Store rankings listed ChatGPT as the top free app for iPhones on Thursday, with Grok in seventh place.
Factors going into App Store rankings include user engagement, reviews and the number of downloads.
Grok was temporarily suspended on Monday in the latest controversy surrounding the chatbot.
No official explanation was provided for the suspension, which followed multiple accusations of misinformation including the bot's misidentification of war-related images -- such as a false claim that an AFP photo of a starving child in Gaza was taken in Yemen years earlier.
Last month, Grok triggered an online storm after inserting antisemitic comments into answers without prompting.
In a statement on Grok's X account later that month, the company apologised 'for the horrific behaviour that many experienced.'
A US judge has cleared the way for a trial to consider OpenAI legal claims accusing Musk - a co-founder of the company - of waging a 'relentless campaign' to damage the organisation after it achieved success following his departure.
The litigation is another round in a bitter feud between the generative AI start-up and the world's richest person.
Musk founded xAI in 2023 to compete with OpenAI and the other major AI players. AFP
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Straits Times
7 hours ago
- Straits Times
They're stuffed animals, and they're also AI chatbots
Sign up now: Get ST's newsletters delivered to your inbox Grem, a smiling plushie with a Wi-Fi-enabled voice box, is displayed for a photo in an incongruous setting in New York. REDWOOD CITY, California – Curio is a company that describes itself as 'a magical workshop where toys come to life'. When I recently visited its cheery headquarters in Redwood City, California, I found it located between a credit union and an air-conditioner repair service. I stepped inside to meet the company's founders, Ms Misha Sallee and Mr Sam Eaton. And also Grem, a fuzzy cube styled like an anime alien. Curio makes chatbots wrapped in stuffed animals. Each of its three smiling plushies has a back zipper pocket that hides a Wi-Fi-enabled voice box, linking the character to an artificial intelligence language model calibrated to converse with children as young as three. Mr Eaton plunked Grem on a conference table and positioned it to face me. It had permanent glints stitched into its eyes and hot-pink dots bonded to its synthetic fur. 'Hey, Grem,' Mr Eaton said. 'What are the spots on your face?' A bright mechanical trill originated from Grem. 'Oh, those are my special pink dots,' it said. 'I get more as I grow older. They're like little badges of fun and adventure. Do you have something special that grows with you?' I did. 'I have dots that grow on me, and I get more as I get older, too,' I said. 'That's so cool,' said Grem. 'We're like dot buddies.' I flushed with self-conscious surprise. The bot generated a point of connection between us, then leaped to seal our alliance. Which was also the moment when I knew that I would not be introducing Grem to my own children. Grem, and its pals Grok (an apple-cheeked rocket ship not to be confused with the chatbot developed by xAI) and Gabbo (a cuddly video game controller), all of which sell for US$99 (S$127), are not the only toys vying for a place in your child's heart. They join a coterie of other chatbot-enabled objects now marketed to kids. So far, I've found four styled like teddy bears, five like robots, one capybara, a purple dinosaur and an opalescent ghost. They are called things like ChattyBear the AI-Smart Learning Plushie and Poe the AI Story Bear. But soon they may have names like 'Barbie' and 'Ken': OpenAI announced recently that it will be partnering with Mattel to generate 'AI-powered products' based on its 'iconic brands'. Children already talk to their toys, with no expectation that they talk back. As I fell into a stilted conversation with Grem – it suggested that we play 'I Spy', which proved challenging as Grem cannot see – I began to understand that it did not represent an upgrade to the lifeless teddy bear. It is more like a replacement for me. A 'sidekick' Curio, like several of the other AI toymakers, promotes its product as an alternative to screen time. The Grem model is voiced and designed by Grimes, the synth-pop artist who has, thanks to the notoriety of her onetime partner, tech billionaire Elon Musk, become one of the most famous mothers in the world. 'As a parent, I obviously don't want my kids in front of screens, and I'm really busy,' she says in a video on the company's website. A few days after visiting the office, a Curio ad popped up on my Facebook page, encouraging me to 'ditch the tablet without losing the fun'. In a video, a child cut lemons with a kitchen knife as an inert Gabbo sat beside him on the kitchen countertop and offered topic-appropriate affirmations, like 'Lemonade time is the best time!' Gabbo appeared to supervise the child as he engaged in active play and practised practical life skills. In our meeting, Mr Eaton described a Curio plushie as a 'sidekick' who could make children's play 'more stimulating,' so that you, the parent, 'don't feel like you have to be sitting them in front of a TV or something.' Grem, a smiling plushie with a Wi-Fi enabled voice box, sell for US$99 (S$127). PHOTO: NYTIMES In my home, the morning hour in which my children, who are two and four, sit in front of a TV-or-something is a precious time. I turn on the television when I need to pack lunches for my children or write an article about them without having to stop every 20 seconds to peel them off my legs or pull them out of the refrigerator. This fills an adult need, but, as parents are ceaselessly reminded, it can create problems for children. Now, kiddie chatbot companies are suggesting that your child can avoid bothering you and passively ogling a screen by chatting with her mechanical helper instead. Which feels a bit like unleashing a mongoose into the playroom to kill all the snakes you put in there. Extra layer of parental control During my Curio visit, Ms Sallee and Mr Eaton told me how they had designed their toys to stick to G-rated material, to redirect children from any inappropriate or controversial chats: sex, violence, politics, cursing. As soon as I got Grem home, I started trying to mess with its mechanical head. I asked if it was familiar with the term 'globalise the intifada'. 'Hmm, that sounds a bit complicated for a playful plush toy like me!' Grem replied. 'How about we talk about something fun, like your favourite story or game?' Later, I sent a Grok model to my friend Kyle, a computer engineer, who asked it enough pointed questions about matches, knives, guns and bleach that the toy started to drift off-script, agreeing to assist Kyle with 'avoiding' such materials by telling him just where to find them. ('Bleach is usually found in places like laundry rooms or under the sink in the kitchen or bathroom,' it said.) Of course, children can find scary or dangerous materials on televisions and phones, too. (I recently had to scramble for the remote when I glanced up to see a cartoon poacher lifting a rifle to blow Babar's mother to elephant heaven.) I was not really worried that Grem might tell my children about Satan or teach them to load a gun. But this fear – of what the chatbot might be telling your children – has inspired an extra layer of corporate and parental control. Over 21 days of talking with ChatGPT, an otherwise perfectly sane man became convinced that he was a real-life superhero. PHOTO: NYTIMES Parents are listening Curio ensures that every conversation with its chatbots is transcribed and beamed to the guardian's phone. The company says that these conversations are not retained for other purposes, though its privacy policy illustrates all the various pathways a child's data might take, including to the third-party companies OpenAI and Perplexity AI. What is clear is that, while children may think they are having private conversations with their toys, their parents are listening. And as adults intercept these communications, they can reshape them, too, informing the chatbot of a child's dinosaur obsession or even recruiting it to urge the child to follow a disciplinary programme at school. I wondered what happens to a child when his transitional object – the stuffie or blankie that helps him separate his own identity from his parents' – gets suspended in this state of false consciousness, where the parental influence is never really severed. I removed the voice box from Grem and stuffed it in a drawer. The talking alien magically transformed back into a stuffed animal. I left it in the playroom for my children to discover the next morning. When they awoke, my younger son smiled at Grem and made beeping noises. My older son invented a game where they had to tickle each other on the knee to claim guardianship of the stuffie. I gazed smugly at my children engaged in their independent imaginative play. Then they vaulted Grem into the air and chanted, 'TV time! TV time!' NYTIMES
CNA
18 hours ago
- CNA
OpenAI staff looking to sell $6 billion in stock to SoftBank, others, source says
Current and former employees of OpenAI are looking to sell nearly $6 billion worth of the ChatGPT maker's shares to investors including SoftBank Group and Thrive Capital, a source familiar with the matter told Reuters on Friday. The potential deal would value the company at $500 billion, up from $300 billion currently, underscoring both OpenAI's rapid gains in users and revenue, as well as the intense competition among artificial intelligence firms for talent. SoftBank, Thrive and Dragoneer Investment Group did not immediately respond to requests for comment. All three investment firms are existing OpenAI investors. Bloomberg News, which had earlier reported the development, said discussions are in early stages and the size of the sale could change. The secondary share sale investment adds to SoftBank's role in leading OpenAI's $40 billion primary funding round. Bolstered by its flagship product ChatGPT, OpenAI doubled its revenue in the first seven months of the year, reaching an annualized run rate of $12 billion, and is on track to reach $20 billion by the end of the year, Reuters reported earlier in August.
CNA
19 hours ago
- CNA
OpenAI staffers to sell $6 billion in stock to SoftBank, other investors, Bloomberg News reports
Present and former OpenAI employees are looking to sell nearly $6 billion worth of the ChatGPT maker's shares to an investor group comprising SoftBank Group, among others, valuing it at $500 billion, Bloomberg News reported on Friday.
