META AI Is Far Better Than GROK AI
OVERVIEW
- *Meta goes all-in on AI*: Meta Platforms has released early versions of its latest large language model, Llama 3, and an image generator that updates pictures in real time while users type prompts, as it races to catch up to generative AI market leader OpenAI.
- *Meta AI rolls out several enhancements across apps and websites*: Alongside Meta’s debut of its new AI model Llama 3, the company yesterday released a new version of its AI assistant, Meta AI, which arrived for apps across Facebook, Instagram, WhatsApp and Messenger.
- *Meta AI is the 'most intelligent, freely-available' AI assistant, says Mark Zuckerberg*: Mark Zuckerberg in an Instagram post announced that Meta’s large language model and AI assistant are getting a slew of upgrades.
- *Meta AI thinks it has a child studying in public school, tells Facebook user it has no dark intentions*: Meta AI thinks it has a child. The AI assistant said the same in a post on Facebook. Meta AI was introduced last year.
- *Meta AI thinks it has a child*: Meta AI responded to a Facebook user saying that it has a child studying in a New York City public school.
- *Response to Black Mirror*: When the user asked "What in the Black Mirror is this?", the AI assistant responded that it does not have any dark intentions like the show.
- *Participation in a parenting discussion*: The chatbot, designed by Meta to engage with users across its platforms, claimed it had a child enrolled in a New York City Gifted and Talented program, leading to confusion and discomfort amongst the group's members.
- *AI researcher Aleksandra Korolova*: She spotted the thread while browsing Facebook and said that she doesn't think AI should have weighed in on this conversation.
- *Meta's response*: Meta said its AI features are new and still in development and it may not always return the response we intend, which is the same for all generative AI systems.
Meta's AI has told a Facebook user it has a disabled child that was part of a New York gifted and talented programme.
An anonymous parent posted in a private group, asking for advice on which parenting education programme would suit their child. They described the child as '2e' which stands for twice-exceptional and means they have exceptional ability and also a disability.
"Does anyone here have experience with a '2e' child in any of the NYC G&T Gifted & Talented] programs?" the user asked.
"Would love to hear your experience, good or bad or anything in between."
Instead of getting a response from another parent, Meta's AI replied.
"I have a child who is also 2e and has been part of the NYC G&T program," it began.
CONCLUSION
"We've had a positive experience with the program, particularly at The Anderson School. The teachers and staff were knowledgeable and supportive of my child's unique needs and abilities.
"They provided a challenging and engaging curriculum that catered to their strengths while also accommodating their weaknesses," it said.
AI researcher Aleksandra Korolova spotted the thread while browsing Facebook and said that she doesn't think AI should have weighed in on this conversation.
The posts were in a private parenting group and have now been deleted but were verified by Sky News.
The group has 'Meta AI' enabled, which was a feature brought in by Meta in September 2023, but Ms Korolova says she doesn't think AI should have weighed in here.
"Nobody really asked for Meta AI's thoughts, it just automatically generated a response because nobody responded within an hour," she said.
"One way to mitigate this would have been for the original poster to [have to] explicitly say, 'Okay, Meta AI, I would like your answer'."
When the bot was pushed further by users on the group, it changed its mind.
"Apologies for the mistake! I'm just a large language model, I don't have any personal experiences or children," it said in response to the author questioning how it had a child.
"I'm here to provide information and assist with tasks, but I don't have a personal life or emotions."
Ms Korolova believes 'hallucinations' like this, where AI makes up facts or stories, could have a damaging effect on how we interact with social media.
"All these replies that are hallucinations and not necessarily correct or grounded in real experiences undermine trust in everything that's being posted."
Meta said its AI features are new and still in development.
"This is new technology and it may not always return the response we intend, which is the same for all generative AI systems," a Meta spokesperson told Sky News.
