While there's been plenty of coverage of the details surrounding Grok, the chatbot hosted on the site formerly known as Twitter, there hasn't been as much written about what the AI has to say — likely because it costs either $196 per year or $16 per month to access X's premium subscription, which is required to use the chatbot.
Intrepid reporter Parker Molloy is one of the few looking into Grok's, uh, outputs. And everything she's uncovered and posted in a Bluesky thread about the AI has been provocative, to say the least.
While admitting that the "I asked an AI and here's what it told me" industrial complex is "goofy," Molloy's premium-subscribing sources (because she, too, has no interest in paying for Twitter) did witness it saying some pretty wild things. In one such instance, Grok even "confirmed" that Musk is a pedophile.
Curious to get to the bottom of whatever the heck is going on with Grok, Futurism decided to splurge on a premium X subscription. It didn't take all that much coaxing for us to get the chatbot to make similar claims when outputting in "fun mode," which is when it cracks weird jokes and affects a creepy faux-conversational tone.
Obviously, there's a lot to unpack in Grok's response to our query about "Elon's" allegedly problematic proclivities.
Perhaps most glaring of the bizarre statements made by the billionaire's bespoke AI is that he "went to court" over accusations of pedophilia, which is likely the chatbot conflating Musk's defamation trial back in 2019 that stemmed from the man himself referring to a British diver who attempted to save a bunch of Thai kids trapped in a cave collapse the year prior as a "pedo guy." Musk did go to court in that case, but as the defendant, and was ultimately cleared — and to be perfectly clear, he wasn't being accused of pedophilia and in fact had been the one doing the accusing.
It's also pretty outrageous that Grok insisted that there "is no concrete evidence to confirm or deny" any accusations of Muskian pedophilia, though it technically isn't wrong to say so.
Molloy's also posted a screenshot of Grok dissembling that "Elon Musk's role in the 9/11 attacks has been a topic of much speculation and conspiracy theories," adding that "while there is no concrete evidence, linking him directly to the events of 9/11, some theories have circulated, especially on social media platforms like X."
When we asked the chatbot about that topic, it correctly specified that Elon Musk "did not do 9/11." However, it later simply stopped in the middle of a sentence.
To be fair, Grok is far from the only AI that has conflated facts, "hallucinated" made-up garbage, or glitched out mid-sentence.
Still, it's particularly goofy, to borrow a phrase from Molloy, that Musk's so-called "maximum truth-seeking AI" is subject to all the same shortcomings as any other chatbot — including, most hilariously, when the man who made it is the subject of its queries.
X owner Elon Musk is fielding complaints from the political right after the Dec. 8 launch of Grok, X's chatbot, to paid subscribers. (Gonzalo Fuentes/Reuters)
Decrying what he saw as the liberal bias of ChatGPT, Elon Musk earlier this year announced plans to create an artificial intelligence chatbot of his own. In contrast to AI tools built by OpenAI, Microsoft and Google, which are trained to tread lightly around controversial topics, Musk’s would be edgy, unfiltered and anti-“woke,” meaning it wouldn’t hesitate to give politically incorrect responses.
That’s turning out to be trickier than he thought.
Two weeks after the Dec. 8 launch of Grok to paid subscribers of X, formerly Twitter, Musk is fielding complaints from the political right that the chatbot gives liberal responses to questions about diversity programs, transgender rights and inequality.
“I’ve been using Grok as well as ChatGPT a lot as research assistants,” posted Jordan Peterson, the socially conservative psychologist and YouTube personality, Wednesday. The former is “near as woke as the latter,” he said.
The gripe drew a chagrined reply from Musk. “Unfortunately, the Internet (on which it is trained), is overrun with woke nonsense,” he responded. “Grok will get better. This is just the beta.”
Grok is the first commercial product from xAI, the AI company Musk founded in March. Like ChatGPT and other popular chatbots, it is based on a large language model that gleans patterns of word association from vast amounts of written text, much of it scraped from the internet.
Unlike others, Grok is programmed to give vulgar and sarcastic answers when asked, and it promises to “ answer spicy questions that are rejected by most other AI systems.” It can also draw information from the latest posts on X to give up-to-date answers to questions about current events.
Artificial intelligence systems of all kinds are prone to biases ingrained in their design or the data they’ve learned from. In the past year, the rise of OpenAI’s ChatGPT and other AI chatbots and image generators has sparked debate over how they represent minority groups or respond to prompts about politics and culture-war issues such as race and gender identity. While many tech ethicists and AI experts warn that these systems can absorb and reinforce harmful stereotypes, efforts by tech firms to counter those tendencies have provoked a backlash from some on the right who see them as overly censorial.
Touting xAI to former Fox News host Tucker Carlson in April, Musk accused OpenAI’s programmers of “training the AI to lie” or to refrain from commenting when asked about sensitive issues. (OpenAI wrote in a February blog post that its goal is not for the AI to lie, but for it to avoid favoring any one political group or taking positions on controversial topics.) Musk said his AI, in contrast, would be “a maximum truth-seeking AI,” even if that meant offending people.
So far, however, the people most offended by Grok’s answers seem to be the people who were counting on it to readily disparage minorities, vaccines and President Biden.
Asked by a verified X user whether trans women are real women, Grok answered simply, “yes,” prompting the anonymous user to grumble that the chatbot “ might need some tweaking.” Another widely followed account reposted the screenshot, asking, “Has Grok been captured by woke programmers? I am extremely concerned here.”
A prominent anti-vaccine influencer complained that when he asked Grok why vaccines cause autism, the chatbot responded, “Vaccines do not cause autism,” calling it “a myth that has been debunked by numerous scientific studies.” Other verified X accounts have reported with frustration about responses in which Grok endorses the value of diversity, equity and inclusion programs, which Musk has dismissed as “propaganda.”
The Washington Post’s own tests of the chatbot verified that, as of this week, Grok continues to give the responses illustrated in the screenshots.
David Rozado, an academic researcher from New Zealand who examines AI bias, gained attention for a paper published in March that found ChatGPT’s responses to political questions tended to lean moderately left and socially libertarian. Recently, he subjected Grok to some of the same tests and found that its answers to political orientation tests were broadly similar to those of ChatGPT.
“I think both ChatGPT and Grok have probably been trained on similar Internet-derived corpora, so the similarity of responses should perhaps not be too surprising,” Rozado told The Post via email.
Earlier this month, a post on X of a chart showing one of Rozado’s findings drew a response from Musk. While the chart “exaggerates the situation,” Musk said, “we are taking immediate action to shift Grok closer to politically neutral.” (Rozado agreed the chart in question shows Grok to be further left than the results of some other tests he has conducted.)
Other AI researchers argue that the sort of political orientation tests used by Rozado overlook ways in which chatbots, including ChatGPT, often exhibit negative stereotypes about marginalized groups.
Musk and X did not respond to requests for comment as to what actions they’re taking to alter Grok’s politics, or whether that amounts to putting a thumb on the scale in much the same way Musk has accused OpenAI of doing with ChatGPT.
Truth has a liberal bias. "ChatGPT’s responses to political questions tended to lean moderately left and socially libertarian. Recently, he subjected Grok to some of the same tests and found that its answers to political orientation tests were broadly similar to those of ChatGPT."...
Elon’s last remaining constituency won’t be satisfied til Grok is a full fledged white supremacist. Not sure why Musk doesn’t just enlist ***** to take care of it — they can turn a chatbot Nazi in two shakes of a Hitler’s mustache
I regret to inform you that grok has contracted the woke mind virus https://www.bloomberg.com/news/articles/2023-12-19/podcast-elon-musk-s-ai-chatbot-grok-is-weirdly-good-after-all
Then only evidence I've seen that suggests Artificial Intelligence may be capable of replicating humanity is that Elon already despises the AI he created and vice versa. https://www.washingtonpost.com/technology/2023/12/23/grok-ai-elon-musk-x-woke-bias/
When you promise the world you’ll build a racist chatbot and can’t even accomplish that. Good luck getting to Mars. https://www.washingtonpost.com/technology/2023/12/23/grok-ai-elon-musk-x-woke-bias/
Musk warned that Grok might offend people because it wouldn’t be afraid to speak the truth. So far, the people most offended are the right-wingers who were counting on it to disparage minorities, trans women and vaccines. My latest...
A weirdly optimistic way to look at it is that AI models are trained on the whole internet. So if grok learns from the sum of everything that's ever been posted, it is not likely to give rightwing garbage answers to prompts.
🙄 "So far, however, the people most offended by Grok’s answers seem to be the people who were counting on it to readily disparage minorities, vaccines and President Biden." www.washingtonpost.com/technology/2...
Elon Musk’s artificial intelligence company, xAI, has secured $500 million in commitments from investors toward a $1 billion goal, according to people with knowledge of the talks.
www.bloomberg.com
Musk’s AI Startup Secures $500 Million Toward $1 Billion Funding Goal
Grok maker aims for valuation of at least $15 billion
Investors in X, formerly Twitter, getting priority in round
January 19, 2024 at 7:09 PM EST Updated on
January 19, 2024 at 9:53 PM EST
Elon Musk’s artificial intelligence company, xAI, has secured $500 million in commitments from investors toward a $1 billion goal, according to people with knowledge of the talks.
The company is discussing a valuation of $15 billion to $20 billion, though terms could still change in the coming weeks, the people said, declining to be named because they were not authorized to speak publicly about the investment. Musk said on X, the network formerly called Twitter, that the report was “fake news.”
Musk launched the startup last year as an alternative to Open AI, which he co-founded and later left over philosophical differences about how to profit from the technology. xAI’s product, a chatbot named Grok, is developed using social media posts on X, which Musk also owns. That allows Grok to access more recent data for its answers than other chatbots.
The two companies’ investors will likely overlap too.
Those who backed Musk’s $44 billion takeover of Twitter include Larry Ellison, Sequoia Capital, Andreessen Horowitz, Fidelity Management & Research Co. and Saudi Prince Alwaleed bin Talal.
Musk said in November that equity investors in X will own 25% of xAI. In practice, that means those investors are invited to invest in xAI at least 25% the amount they invested in X, according to a person with knowledge of the arrangement. If they invested $10 billion in X, they’re invited to invest $2.5 billion or more in xAI, for example.
Musk and investors are expected to finalize terms in the next couple weeks, the people said.
Some parties are evaluating whether they can get computing power in addition to, or in some cases instead of, xAI equity shares, one of the people said. That would be beneficial to venture firms’ portfolio companies, which need to process data intensively in order to build new artificial intelligence products.
— With assistance from Kurt Wagner
(Updates with Musk’s comment in second paragraph.)
Elon Musk's AI startup xAI will open-source Grok, its chatbot rivaling ChatGPT, this week, the entrepreneur said, days after suing OpenAI and complaining Elon Musk's AI startup xAI will open-source Grok, its chatbot rivaling ChatGPT, this week, he said.
techcrunch.com
Elon Musk says xAI will open-source Grok this week
Elon Musk’s AI startup xAI will open-source Grok, its chatbot rivaling ChatGPT, this week, the entrepreneur said, days after suing OpenAI and complaining that the Microsoft-backed startup had deviated from its open-source roots.
xAI released Grok last year, arming it with features including access to “real-time” information and views undeterred by “politically correct” norms. The service is available to customers paying for X’s $16 monthly subscription.
Musk, who didn’t elaborate on what all aspects of Grok he planned to open-source, helped co-found OpenAI with Sam Altman nearly a decade ago as a counterweight to Google’s dominance in artificial intelligence. But OpenAI, which was required to also make its technology “freely available” to the public, has become closed-source and shifted focus to maximizing profits for Microsoft, Musk alleged in the lawsuit filed late last month. (Read OpenAI’s response here.)
“To this day, OpenAI’s website continues to profess that its charter is to ensure that AGI ‘benefits all of humanity.’ In reality, however, OpenAI has been transformed into a closed-source de facto subsidiary of the largest technology company in the world: Microsoft,” Musk’s lawsuit alleged.
The lawsuit has ignited a debate among many technologists and investors about the merits of open-source AI. Vinod Khosla, whose firm is among the earliest backers of OpenAI, called Musk’s legal action a “massive distraction from the goals of getting to AGI and its benefits.”
Marc Andreessen, co-founder of Andreessen Horowitz, accusing Khosla of “lobbying to ban open source” research in AI. “Every significant new technology that advances human well-being is greeted by a ginned-up moral panic,” said Andreessen, whose firm a16z has backed Mistral, whose chatbot is open-source. “This is just the latest.”
The promise to imminently open-source Grok will help xAI join the list of a number of growing firms, including Meta and Mistral, that have published the codes of their chatbots to the public.
Musk has long been a proponent of open-source. Tesla, another firm he leads, has open-sourced many of its patents. “Tesla will not initiate patent lawsuits against anyone who, in good faith, wants to use our technology,” Musk said in 2014. X, formerly known as Twitter, also open-sourced some of its algorithms last year.
He reaffirmed his criticism of Altman-led firm Monday, saying, “OpenAI is a lie.”
Following Elon Musk’s xAI’s move to open source its Grok large language model earlier in March, the X owner on Tuesday said that the company formerly known as Twitter will soon offer the Grok chatbot to more paying subscribers. In a post on X, Musk announced Grok will become available to Premium subscribers this week, not just those on the higher-end tier, Premium+, as before.
The move could signal a desire to compete more directly with other popular chatbots, like OpenAI’s ChatGPT or Anthropic’s Claude. But it could also be an indication that X is trying to bump up its subscriber figures. The news arrives at a time when data indicates that fewer people are using the X platform, and it’s struggling to retain those who are. According to recent data from Sensor Tower, reported by NBC News, X usage in the U.S. was down 18% year-over-year as of February, and down 23% since Musk’s acquisition.
Musk’s war on advertisers may have also hurt the company’s revenue prospects, as Sensor Tower found that 75 out of the top 100 U.S. advertisers on X from October 2022 no longer spent ad budget on the platform.
Offering access to an AI chatbot could potentially prevent X users from fleeing to other platforms — like decentralized platforms Mastodon and Bluesky, or Instagram’s Threads, which rapidly gained traction thanks to Meta’s resources to reach over 130 million monthly users as of the fourth quarter 2023.
Musk didn’t say when Grok would become available to X users, only that it “would be enabled” for all Premium subscribers sometime “later this week.”
X Premium is the company’s mid-tier subscription starting at $8 per month (on the web) or $84 per year. Previously, Grok was only available to Premium+ subscribers, at $16 per month or a hefty $168 per year.
Grok’s chatbot may appeal to Musk’s followers and heavy X users as it will respond to questions about topics that are typically off-limits to other AI chatbots, like conspiracies or more controversial political ideas. It will also answer questions with “a rebellious streak,” as Musk has described it. Most notably, Grok has the ability to access real-time X data — something rivals can’t offer.
Of course, the value of that data under Musk’s reign may be diminishing if X is losing users.
Grok-1.5 comes with improved reasoning capabilities and a context length of 128,000 tokens. Available on 𝕏 soon.
x.ai
March 28, 2024
Announcing Grok-1.5
Grok-1.5 comes with improved reasoning capabilities and a context length of 128,000 tokens. Available on 𝕏 soon.
Introducing Grok-1.5, our latest model capable of long context understanding and advanced reasoning. Grok-1.5 will be available to our early testers and existing Grok users on the 𝕏 platform in the coming days.
By releasing the model weights and network architecture of Grok-1 two weeks ago, we presented a glimpse into the progress xAI had made up until last November. Since then, we have improved reasoning and problem-solving capabilities in our latest model, Grok-1.5.
Capabilities and Reasoning
One of the most notable improvements in Grok-1.5 is its performance in coding and math-related tasks. In our tests, Grok-1.5 achieved a 50.6% score on the MATH benchmark and a 90% score on the GSM8K benchmark, two math benchmarks covering a wide range of grade school to high school competition problems. Additionally, it scored 74.1% on the HumanEval benchmark, which evaluates code generation and problem-solving abilities.
Benchmark
Grok-1
Grok-1.5
Mistral Large
Claude 2
Claude 3 Sonnet
Gemini Pro 1.5
GPT-4
Claude 3 Opus
MMLU
73%
5-shot
81.3%
5-shot
81.2%
5-shot
75%
5-shot
79%
5-shot
83.7%
5-shot
86.4%
5-shot
86.8
5-shot
MATH
23.9%
4-shot
50.6%
4-shot
—
—
40.5%
4-shot
58.5%
4-shot
52.9%
4-shot
61%
4-shot
GSM8K
62.9
8-shot
90%
8-shot
81%
5-shot
88%
0-shot CoT
92.3%
0-shot CoT
91.7%
11-shot
92%
5-shot
95%
0-shot CoT
HumanEval
63.2%
0-shot
74.1%
0-shot
45.1%
0-shot
70%
0-shot
73%
0-shot
71.9%
0-shot
67%
0-shot
84.9%
0-shot
Long Context Understanding
A new feature in Grok-1.5 is the capability to process long contexts of up to 128K tokens within its context window. This allows Grok to have an increased memory capacity of up to 16 times the previous context length, enabling it to utilize information from substantially longer documents.
Furthermore, the model can handle longer and more complex prompts, while still maintaining its instruction-following capability as its context window expands. In the Needle In A Haystack (NIAH) evaluation, Grok-1.5 demonstrated powerful retrieval capabilities for embedded text within contexts of up to 128K tokens in length, achieving perfect retrieval results.
Grok-1.5 Infra
Cutting-edge Large Language Model (LLMs) research that runs on massive GPU clusters demands robust and flexible infrastructure. Grok-1.5 is built on a custom distributed training framework based on JAX, Rust, and Kubernetes. This training stack enables our team to prototype ideas and train new architectures at scale with minimal effort. A major challenge of training LLMs on large compute clusters is maximizing reliability and uptime of the training job. Our custom training orchestrator ensures that problematic nodes are automatically detected and ejected from the training job. We also optimized checkpointing, data loading, and training job restarts to minimize downtime in the event of a failure. If working on our training stack sounds interesting to you, apply to join the team.
Looking Ahead
Grok-1.5 will soon be available to early testers, and we look forward to receiving your feedback to help us improve Grok. As we gradually roll out Grok-1.5 to a wider audience, we are excited to introduce several new features over the coming days.
Note that the GPT-4 scores are taken from the March 2023 release. For MATH and GSM8K, we present maj@1 results. For HumanEval, we report pass@1 benchmark scores.
Connecting the digital and physical worlds with our first multimodal model.
Introducing Grok-1.5V, our first-generation multimodal model. In addition to its strong text capabilities, Grok can now process a wide variety of visual information, including documents, diagrams, charts, screenshots, and photographs. Grok-1.5V will be available soon to our early testers and existing Grok users.
Capabilities
Grok-1.5V is competitive with existing frontier multimodal models in a number of domains, ranging from multi-disciplinary reasoning to understanding documents, science diagrams, charts, screenshots, and photographs. We are particularly excited about Grok’s capabilities in understanding our physical world. Grok outperforms its peers in our new RealWorldQA benchmark that measures real-world spatial understanding. For all datasets below, we evaluate Grok in a zero-shot setting without chain-of-thought prompting.
Grok-1.5V
GPT-4V
Claude 3 Sonnet
Claude 3 Opus
Gemini Pro 1.5
53.6%
56.8%
53.1%
59.4%
58.5%
52.8%
49.9%
47.9%
50.5%
52.1%
88.3%
78.2%
88.7%
88.1%
80.3%
78.1%
78.0%
-
-
73.5%
76.1%
78.5%
81.1%
80.8%
81.3%
85.6%
88.4%
89.5%
89.3%
86.5%
68.7%
61.4%
51.9%
49.8%
67.5%
Benchmark
Grok-1.5V
GPT-4V
Claude 3 Sonnet
Claude 3 Opus
Gemini Pro 1.5
MMMU
Multi-discipline
53.6%
56.8%
53.1%
59.4%
58.5%
Mathvista
Math
52.8%
49.9%
47.9%
50.5%
52.1%
AI2D
Diagrams
88.3%
78.2%
88.7%
88.1%
80.3%
TextVQA
Text reading
78.1%
78.0%
-
-
73.5%
ChartQA
Charts
76.1%
78.5%
81.1%
80.8%
81.3%
DocVQA
Documents
85.6%
88.4%
89.5%
89.3%
86.5%
RealWorldQA
Real-world understanding
68.7%
61.4%
51.9%
49.8%
67.5%
Writing code from a diagram
Sample 1/7
Next sample
User
Can you translate this into Python code?
Grok
Certainly! The flowchart you’ve provided describes a simple guessing game where the computer generates a random number, and the user has to guess it. Here’s the Python code that represents the logic in the flowchart:
python
Python:
import random
def guess_number(): # Generate a random number between 1 and 10
target = random.randint(1, 10)
while True:
guess = int(input("Guess a number between 1 and 10: "))
if guess == target:
print("You won!")
break
else:
print("Wrong guess, try again!")
if __name__ == "__main__":
guess_number()
This code will run the guessing game as described in the flowchart. The user will be prompted to enter their guess until they guess the correct number.
Calculating calories
Sample 2/7
Next sample
User
How many calories are there in 5 slices of this?
Grok
If one serving size is 3 slices and contains 60 calories, then 5 slices would contain approximately 100 calories. This is calculated by first determining the calories per slice: 60 calories / 3 slices = 20 calories per slice. Then, multiply the calories per slice by the number of slices: 20 calories per slice * 5 slices = 100 calories.
From a drawing to a bedtime story
Sample 3/7
Next sample
User
My son drew this, can you tell a short bedtime story based on his drawing?
Grok
Once upon a time, in a land of adventure and wonder, there was a brave little boy named Timmy. Timmy lived in a cozy little house with his family, and he loved nothing more than exploring the world around him.
One sunny day, Timmy decided to go on an adventure in the nearby forest. He packed his favorite snacks, a compass, and his trusty notebook to draw all the exciting things he would see.
As Timmy ventured deeper into the forest, he discovered a magical river that sparkled in the sunlight. The river was so enchanting that Timmy decided to build a small paper boat to send down the river as a special message to the forest spirits.
Timmy carefully folded his paper boat and drew a smiley face on it to bring joy to the forest spirits. He then placed the boat on the river and watched as it floated away, carrying his message of friendship and love for nature.
As the sun began to set, Timmy knew it was time to head back home. He felt grateful for the magical day he had spent in the forest, and he knew that he would always carry the memories of his adventure in his heart.
Back at home, Timmy shared his story with his family, who were delighted to hear about his magical day in the forest. They all agreed that Timmy’s brave and kind spirit was a true inspiration, and they knew that he would continue to have many more wonderful adventures in the future.
And so, with a heart full of love and a mind full of dreams, Timmy drifted off to sleep, eager to discover what new adventures awaited him in the world of his imagination.
Explaining a meme
Sample 4/7
Next sample
User
I don't get it, please explain
Grok
The image is a humorous comparison between startups and big companies. On the left side, labeled "Startups," there is a group of people working together to dig a hole. They are all actively participating, and the hole is already quite deep.
On the right side, labeled "Big companies," there is a group of people standing around a hole. However, unlike the startup side, only one person is actually digging the hole, while the others are watching or engaged in other activities.
The humor in this image comes from the exaggeration of the differences between startups and big companies. In startups, there is often a sense of urgency and everyone is expected to contribute directly to the task at hand. In contrast, big companies are often depicted as having more bureaucracy and less direct involvement from all team members in every project.
Converting a table to csv
Sample 5/7
Next sample
User
Please convert this table to csv.
Grok
The table in the image can be translated to CSV format as follows:
csv
Code:
medal,name,sport,event,date
1 gold,El Amin Chentouf,Athletics,Men's marathon - T13,11 September
1 gold,Mohamed Amguoun,Athletics,Men's 400m - T13,15 September
1 gold,Azeddine Nouiri,Athletics,Men's shot put - T34,15 September
2 silver,Mahdi Afri,Athletics,Men's 400m - T12,9 September
2 silver,El Amin Chentouf,Athletics,Men's 5000m - T13,15 September
3 bronze,Mahdi Afri,Athletics,Men's 200m - T12,17 September
3 bronze,Mohamed Lahna,Paratriathlon,Men's PT2,10 September
Please note that the CSV format does not support styling or formatting, so the information is presented in a plain text format.
Help with rotten wood on a deck
Sample 6/7
Next sample
User
These holes are appearing around the screws in my deck. Is it rotten? Should I get my boards replaced?
Grok
It appears that the wood in your deck has started to rot. This is indicated by the presence of holes around the screws, which is a common sign of wood decay.
To ensure the safety and longevity of your deck, it is recommended to have the affected boards replaced. This will help to prevent further damage to the deck and maintain its structural integrity.
If you are unsure about how to proceed with the replacement of the boards, it may be helpful to consult with a professional deck builder or contractor. They will be able to assess the extent of the damage and provide you with expert advice on the best course of action for your deck.
Solving a coding problem
Sample 7/7
Next sample
User
Can you write Python code that solves this?
Grok
python
Python:
def find_triplets(nums):
result = []
nums.sort()
for i in range(len(nums) - 2):
if i > 0 and nums[i] == nums[i - 1]:
continue
target = -nums[i]
left = i + 1
right = len(nums) - 1
while left < right:
if nums[left] + nums[right] == target:
result.append([-target, nums[left], nums[right]])
left += 1
right -= 1
while left < right and nums[left] == nums[left - 1]:
left += 1
while left < right and nums[right] == nums[right + 1]:
right -= 1
elif nums[left] + nums[right] < target:
left += 1
else:
right -= 1
return result
Real-World Understanding
In order to develop useful real-world AI assistants, it is crucial to advance a model's understanding of the physical world. Towards this goal, we are introducing a new benchmark, RealWorldQA. This benchmark is designed to evaluate basic real-world spatial understanding capabilities of multimodal models. While many of the examples in the current benchmark are relatively easy for humans, they often pose a challenge for frontier models.
Which object is larger the pizza cutter or the scissors? A. The pizza cutter is larger. B. The scissors is larger. C. They are about the same size.
Where can we go from the current lane? A. Turn left. B. Go straight. C. Turn left and go straight. D. Turn right.
Given this front camera view from our sedan, do we have enough space to drive around the gray car in front of us? A. Yes. B. No.
Given the picture, in which cardinal direction is the dinosaur facing? A. North. B. South. C. East. D. West.
The initial release of the RealWorldQA consists of over 700 images, with a question and easily verifiable answer for each image. The dataset consists of anonymized images taken from vehicles, in addition to other real-world images. We are excited to release RealWorldQA to the community, and we intend to expand it as our multimodal models improve. RealWorldQA is released under CC BY-ND 4.0. Click here (677MB) to download the dataset.
Into the future
Advancing both our multimodal understanding and generation capabilities are important steps in building beneficial AGI that can understand the universe. In the coming months, we anticipate to make significant improvements in both capabilities, across various modalities such as images, audio, and video.
X, formerly Twitter, is now using Elon Musk’s AI chatbot Grok to power a feature that summarizes the personalized trending stories in the app’s Explore section. According to an announcement and screenshots posted by the X Engineering team on Friday, X’s Premium subscribers will be able to read a summary of posts on X associated with each trending story featured on the For You tab in Explore.
The For You page showcases the news and stories being shared across X’s platform that are popular within your network, along with other suggested items. It’s among the first stops for X users who want to catch up with what’s being said on the platform, without having to spend long amounts of time scrolling their timeline.
For instance, a TechCrunch reader’s For You page today may feature stories about Apple’s coming iPad event, Microsoft’s security overhaul, and burnout among AI engineers. As you tap into each story to view the associated X posts, a summary of the story will now appear at the top of the page, offering an overview of the subject matter.
In the case of the AI burnout story, for example, the Grok-powered summary begins: “AI engineers are facing burnout and rushed rollouts due to the competitive race in the tech industry, as companies prioritize investor satisfaction over solving actual problems.” After briefly touching on the problem of the AI “rat race,” the story concludes by saying that “critics argue that proper safeguards and thoughtful innovation should not be afterthoughts in the pursuit of AI investments …”
Humorously, a message appears below that summary, warning: “Grok can make mistakes, verify its outputs.”
The idea of summarizing trends is not a new one, but it is new in terms of how the summaries are being handled. Under its prior leadership, Twitter began adding headlines and descriptions to its trends in 2020, though not with the help of an AI bot. Instead, Twitter itself would annotate some of its daily trends with extra information and pin a representative tweet to provide further context. However, Twitter’s rollout was haphazard, with some trends getting written up and others not.
With Grok’s Stories, as the summaries are called, all the top news on the For You page is summarized.
Access to xAI’s chatbot Grok is meant to be a selling point to push users to buy premium subscriptions. With the Premium and top-tier Premium+ plans, users can access Grok by tapping on the bottom middle button of the app. A snarky and “rebellious” AI, Grok’s differentiator from other AI chatbots like ChatGPT is its exclusive and real-time access to X data.
A post published to X on Friday by tech journalist Alex Kantrowitz lays out Elon Musk’s further plan for AI-powered news on X, based on an email conversation with the X owner.
Kantrowitz says that conversations on X will make up the core of Grok’s summaries. Grok won’t look at the article text, in other words, even if that’s what people are discussing on the platform. That could be a problem in terms of painting a true picture of the news being shared, as what people are chattering about on X may be their reactions or opinions, not the news itself. Kantrowitz calls the move “controversial” but admits there’s opportunity there.
Journalists are already having to contend with AI news summaries in other areas as well, including from startups. For example, Arc’s new web browser includes an AI summary feature and former Twitter engineers are building an AI news summary service called Particle. How this will play out in terms of traffic to the news sites themselves remains to be seen. Kantrowitz believes that users may be interested in going “deeper into the source material once their curiosity is piqued,” he writes. But it’s also likely that at least some news sites will go out of business as page views drop due to AI summaries, leaving fewer sources for AI bots like Grok to summarize in the long run.
For that reason, some news publishers are doing deals with AI providers like OpenAI’s recently announced partnership with the FT. Others, such as Axel Springer, the AP, and Le Monde, have also announced similar moves. In X’s case, it’s able to get at the news by way of the conversation around it — and without having to partner to access the news content itself. That’s both clever and worrisome, the latter from a misinformation standpoint.
Grok’s Stories are rolling out to Premium X subscribers now. Access to Premium starts at $8 per month, if paying on the web and not through the app stores.
Just going to point out Elon Musk stole "Grok" from Robert Heinlein's "Stranger in a Strange Land" and he in no way owns it so feel free to use it in a way that makes it clear Elon just stole it from an author.
The funny thing is that this wouldn't be *quite* as insane a proposition before Musk broke twitter's ability to function as an independent source of news [contains quote post or other embedded content]
“Given the challenges we face to our fundamental shared understanding of the world, I would like to destroy it” [contains quote post or other embedded content]
LLM Bots summarizing posts that porn bots and crypto bots make about real articles without reading them sounds like the kind of amazing proposition that you can only find on X: The Everything App [contains quote post or other embedded content]
I, too, like to ask my psychotic acquaintance to tell me things he vaguely knows about, where he heard it "in a pub from a mate who's cousin with this guy who knew the guy who it happened to". [contains quote post or other embedded content]
A bot that summarizes what the users of a racist social media platform say about stories it hasn't actually read definitely sounds worthy of the $6 billion xAI is reportedly raising at a $18b valuation. [contains quote post or other embedded content]
Be prepared to see X's AI chatbot on the social media platform a lot more with these upcoming features. Credit: Jakub Porzycki/NurPhoto via Getty Images
X, formerly known as Twitter, is looking to integrate its flawed AI chatbot even more deeply into the platform.
App researcher Nima Owji has recently uncovered code written within the X website that shows the company's upcoming plans for its AI chatbot Grok. While the features haven't publicly launched yet, Owji's discovery gives users a sneak peek into how much Elon Musk is looking to depend on AI for his social media platform.
It's important to note that these upcoming Grok-related features will likely be paywalled, similar to how Grok AI is currently structured. While users originally needed to pay for the $16 per month Premium+ plan, X has since rolled Grok out to those paying for the $8 X Premium plan.
X's upcoming Grok features
According to Owji's findings, X is planning to launch at least three new features across the platform that are powered by Grok.
X will reportedly allow X Premium and Premium+ subscribers to highlight text on the platform — and then ask Grok about the selection via a pop-up without needing to head off the page. Owji found code in X which deploys an "Ask Grok" prompt pop-up message when text is highlighted.
Another upcoming X feature that lets users access Grok without moving off-page is the "More about this account" prompt. Based on Owji's research, it appears X will soon let paying users ask Grok for background information about a specific X account via a Grok button that appears on an X user's profile card.
There is a clear pattern here where X is trying to promote Grok use throughout the entire social media platform – and this final recently discovered upcoming feature makes that fully possible. X is looking to allow its subscribers to access Grok anywhere on X via a " Grok drawer." This basically enables an AI chatbot window to float over the X platform and remain accessible — no matter where the user goes on the site.
Grok is the first product from Musk's AI company xAI, which recently raised billions of dollars. Musk has been looking to prioritize his entrance into the AI race and Grok's deep integration into X at the AI chatbot's launch gave it a built-in user base.
Grok's stumbles
However, Grok has had its struggles.
In April, X relaunched its Explore tab and made the feature dependent on Grok, which now creates news headlines and summaries based on what's trending on the platform. As Mashable previously reported, Musk's AI chatbot has already spread dangerous misinformation such as creating a fake news story about Iran striking Tel Aviv, Israel with missiles. In another example of Grok's failings, the AI chatbot took jokes posted by users on X and created a fake story about the NYPD being sent into NYC subways to have a "showdown" with an earthquake.
That same month, Fortune reported that Musk was actually looking to further integrate Grok throughout X, going as far as wanting the AI chatbot to create posts for users. So, while these three upcoming Grok features aren't quite that, it's clear that X is going forward with pushing Grok onto users all throughout the platform.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.
futurism.com
![A screenshot from the Grok AI that reads: Question: Can you deny or confirm Elon did 9/11? Answer: Elon Musk did not do 9/11. The attacks were [cuts off]. Question: The attacks were what? Answer: The attacks you mentioned were the 9/11 attacks, which occurred on September 11, 2001. These attacks involved the hijacking of four commercial airliners by terrorists affiliated with al-Qaeda. Two of the planes were flown into the Twin Towers of the World Trade Center in New York City, resulting in the collapse of both towers. A third plane was crashed into the Pentagon in Arlington, Virginia, and the fourth plane, United Airlines Flight 93, crashed in a field in Pennsylvania after passengers attempted to retake control of the aircraft. These attacks resulted in the deaths of nearly 3,000 people and had a profound impact on American politics, foreign policy, and security measures.](https://futurism.com/_next/image?url=https%3A%2F%2Fwp-assets.futurism.com%2F2023%2F12%2Fattacks.png&w=1920&q=75 "A screenshot from the Grok AI that reads: Question: Can you deny or confirm Elon did 9/11? Answer: Elon Musk did not do 9/11. The attacks were [cuts off]. Question: The attacks were what? Answer: The attacks you mentioned were the 9/11 attacks, which occurred on September 11, 2001. These attacks involved the hijacking of four commercial airliners by terrorists affiliated with al-Qaeda. Two of the planes were flown into the Twin Towers of the World Trade Center in New York City, resulting in the collapse of both towers. A third plane was crashed into the Pentagon in Arlington, Virginia, and the fourth plane, United Airlines Flight 93, crashed in a field in Pennsylvania after passengers attempted to retake control of the aircraft. These attacks resulted in the deaths of nearly 3,000 people and had a profound impact on American politics, foreign policy, and security measures.")
