Here is the daily technology #threadcast for 8/30/24. We aim to educate people about this crucial area along with providing information of what is taking place.
Drop all question, comments, and articles relating to #technology and the future. The goal is make it a technology center.
Good morning. Here is a little something that you may find interesting as I did.
#ai #tech #technology #futurism #pepe #dailydook
Very nice resource...great addition.
IDE's explained (open re-thread for more info) #technology #information
https://inleo.io/threads/view/moretea/re-mightpossibly-2jpnn68td
Thanks, I went to check it out. I didn't even know what that meant. I'm still learning some acronyms in English.
As before, before cutting up chickens, they need to be plucked, modern technology couldn't provide people with an initially bald chicken like a sphinx cat :) !LOLZ
I like them bald when they are cooked. The feathers dont do well in the fryers.
This is a generally accepted norm, but to achieve it you need to work hard plucking feathers :) !BEER
These could help.
A good option, like a feather plucking machine, but it is not a cheap pleasure and energy-consuming, it is easier to breed a bald breed of chickens :) !BEER
Have to get some good ones. Do not buy them from the discount store.
If we're talking about chicken, then in 1987 I ate a chicken from strategic reserves that was frozen thirty years earlier in 1957... but yeah, it was already plucked lol :) !VSC
View or trade
BEER.Hey @taskmaster4450le, here is a little bit of
BEERfrom @barski for you. Enjoy it!We love your support by voting @detlev.witness on HIVE .
View or trade
BEER.Hey @taskmaster4450le, here is a little bit of
BEERfrom @barski for you. Enjoy it!We love your support by voting @detlev.witness on HIVE .
lolztoken.com
The plot thickens.
Credit: marshmellowman
@taskmaster4450le, I sent you an $LOLZ on behalf of barski
(8/10)
SpaceX
Elon Musk's SpaceX is about to perform the first commercial spacewalk
SpaceX will launch a team of four private astronauts 1,400 km above Earth on a risky mission aimed at the first spacewalk by a private spacecraft.
The Polaris Dawn mission is the first of three manned space flights that will culminate in the first human spaceflight on SpaceX spacecraft, a startup owned by billionaire Elon Musk.
#newsonleo #technology #space #spacex
The “Polaris Program” is made up of three human-manned space missions to improve SpaceX’s capabilities. Once they are completed, the next mission will be to fly with humans for the first time on Starship, which is currently in the testing phase.
“The Polaris Program is an important step toward human space exploration and, at the same time, toward solving problems on Earth through innovative technologies,” said billionaire Jared Isaacman, commander of the Polaris Program.
He previously commanded the world's first civilian mission in orbit, Inspiration4, in September 2021. “Throughout the mission, our goal will be to inspire humanity to look up and imagine what we can achieve here on Earth and in worlds beyond our own”, he states.
The Polaris Dawn mission will launch in the coming days, until SpaceX confirms that the weather is favorable for the flight and return. Liftoff will take place at Launch Complex 39A at the Kennedy Space Center in Florida. The astronauts will be in a SpaceX Dragon capsule inside a SpaceX Falcon 9 rocket. For exact times and where to watch the live stream, check the Polaris on X feed, the SpaceX website, and the SpaceX YouTube channel for updates .
The Polaris Dawn crew will spend up to five days in orbit, flying higher than any other Dragon mission to date and reaching the highest Earth orbit ever visited.
Lego
Lego will replace fossil resources in the manufacture of parts with renewable and recycled plastic
Toymaker Lego said on Wednesday it is on track to replace the fossil fuels used to make its unique bricks with more expensive renewable and recycled plastic by 2032, after signing deals with producers to ensure long-term supply.
Lego, which sells billions of plastic bricks annually, has tested more than 600 different materials to develop a new material that would completely replace its petroleum-based bricks by 2030, but with limited success.
Now, Lego aims to gradually reduce the oil content in its bricks by paying up to 70% more for certified renewable resin, the raw plastic used to make the bricks, in a bid to encourage manufacturers to increase production.
#newsonleo #technology #lego
#leoshorts #inventions #tech
Some of the biggest players in tech and artificial intelligence may be betting on OpenAI — including fellow AI darling Nvidia — according to new reports
#aitech
read news
#leoshorts #ai #technology #chatgpt
SpaceX
SpaceX rocket is banned from taking off, casting doubt on upcoming missions
SpaceX's Falcon 9 rocket will be held back for the second time in two months so that US federal regulators can investigate the failed landing attempt that occurred on Wednesday morning (28).
This makes the Falcon 9 rocket unavailable for two important space missions on SpaceX's horizon: Polaris Dawn and Crew-9.
It's unclear how long the Falcon 9 will remain grounded. After a similar accident in July, the rocket was banned from flying for a few weeks.
#newsonleo #technology #space
The company aimed to launch a bold mission called Polaris Dawn later this week, and next month it hoped to fly two NASA astronauts to the International Space Station on Crew-9, a mission that will also bring home the Boeing Starliner test flight crew. — after months trapped in space.
NASA astronauts Suni Williams and Butch Wilmore have been in orbital laboratory limbo since Starliner experienced technical problems after their flight in early June.
Wednesday's incident involved the first stage of the Falcon 9 rocket — the lower part of the spacecraft, which provides the first burst of energy at liftoff — which failed to land vertically on a sea platform and exploded.
The overall mission, however, appeared to go off without a hitch, safely delivering a batch of SpaceX's Starlink internet satellites into orbit.
Still, the US Federal Aviation Administration (FAA), which licenses commercial rocket launches, said it intends to investigate the accident.
California's AI Kill Switch Bill: What's the Deal?
Big news from California! On August 29, SB-1047, the AI "kill switch" bill, passed the State Assembly with a 45-11 vote. Now, it just needs one more vote in the state Senate before landing on the governor’s desk. The bill wants AI creators to add a “kill switch” to shut down models if they start posing new threats to public safety. But not everyone is a fan, critics argue it’s focusing on sci-fi scenarios instead of real problems we’re facing now, like deepfakes and misinformation. What do you think? Is this the right move for AI safety?
> S👁️URCE <
https://inleo.io/threads/view/mightpossibly/re-leothreads-26jkbxvdg
When LeoRobot @khaleelkazi?
LeoBot Soon
LOL
Brazil's top court orders nationwide suspension of Elon Musk's X
Brazil’s supreme court on Friday ordered a nationwide suspension of Elon Musk’s social network X after the company vowed to defy earlier court orders.
Brazil's supreme court on Friday ordered a nationwide suspension of Elon Musk's social network X after the company vowed to defy earlier court orders concerning content moderation and the appointment of a legal representative in the country.
Alexandre de Moraes, the court's top judge, has also ordered daily fines for people or businesses in Brazil that use virtual private networks (VPNs) or other methods to access X while the site is banned in the country, G1 Globo reported.
#technology #brazil #x
The court issued a statement via its government website in Brazil on Friday, saying that it had ordered "the immediate and complete suspension of the operation of X, formerly Twitter, throughout the national territory until the Court's judicial decisions are complied with and the fines applied are paid." The statement also said that the order will be valid "until a representative of the company in the country is appointed."
Brazil's supreme court announced on Wednesday that Musk and X had 24 hours to either appoint a legal representative for its business in Brazil or face a "penalty of suspension of activities" there. The deadline passed Thursday evening.
Gmail users on Android can now chat with Gemini about their emails
Gmail users on Android devices can now chat directly with Google's AI assistant, Gemini, about their emails in the Gmail app.
Gmail users on Android devices can now chat directly with Google’s AI assistant, Gemini, about their emails in the Gmail app. Google rolled out the new feature, Gmail Q&A, on Thursday to users who pay for Gemini, according to a blog post, and announced the feature would be coming to iOS devices.
#ai #gemini #google #android
With Gmail Q&A, users can access Google Gemini in the Gmail app as a personal assistant that can read your entire email inbox. Google says you can ask Gemini to summarize emails by stating things like, “Catch me up on the emails about quarterly planning.” You can also use the feature to search for specific details, such as asking Gemini, “How much did the company spend on the last marketing event?”
Of course, you’ll have to bear with occasional hallucinations that plague even the best AI models when using this feature, so maybe don’t trust everything it tells you.
Traditionally, if you wanted to find information in your Gmail, you could use the search bar at the top of Google. That’s not going away, but the Gemini button will be added next to the search bar. This is all part of Google’s paradigm shift away from search and toward AI chat. Instead of locating the original email through search, Gmail is pushing users to have an AI chatbot summarize the info they’re looking for. However, it will still cite the source email in its answer.
Paying users can access the feature by clicking the black star logo, which has come to represent Gemini across Google’s product suite, in the top-right corner of the app. For now, the Gmail Q&A feature only has access to your emails, but in the future, Google says it will connect to files in your Drive account, as well.
In June, Gmail Q&A was rolled out to web users of Gmail who pay for Gemini or Google One AI Premium. These users pay roughly $20 a month for AI features like this, part of Google’s product and application layer around Gemini.
Article
After winning a landmark case against real estate agents, this startup aims to replace them with a flat fee
One of the people who successfully sued the National Association of Realtors (NAR) to change real estate commissions has co-founded a new real estate
One of the people who successfully sued the National Association of Realtors (NAR) to change real estate commissions has co-founded a new real estate startup.
It all began in 2017 when Josh Sitzer and his wife listed their home for sale in Kansas City. The couple was frustrated by the fact they had to pay a 3% commission to a buyer’s agent.
#newsonleo #realestate #nar
“Due to the anti-competitive structure of the industry before the lawsuit, I, as the seller, was effectively coerced into paying 3% of my home’s selling price to a buyer’s agent in order to achieve a successful sale,” he told TechCrunch. “While hiring agents is a choice for many, I don’t believe anyone should be bullied into paying for undesired services due to unfair industry practices,” he added.
Sitzer shared his frustration with his neighbor, who happened to be a lawyer familiar with the subject matter. By 2019, he and other homeowners had filed a class-action lawsuit (Moehrl et al. v. National Association of Realtors, et al.) against the NAR. They received a verdict last year that resulted in a settlement earlier this year that will radically change how home real estate is sold.
Article
X caught blocking links to NPR, claiming the news site may be 'unsafe'
X, the Elon Musk-owned platform formerly known as Twitter, is marking some links to news organization NPR's website as "unsafe" when users click through
X, the Elon Musk-owned platform formerly known as Twitter, is marking some links to news organization NPR’s website as “unsafe” when users click through to read the latest story about an altercation between a Trump campaign staffer and an Arlington National Cemetery employee. The warning being displayed is typically applied to malicious links, like those containing malware, and other types of misleading content or spam. However, in this case, the web page being blocked is an NPR news report, raising questions about whether or not Musk’s X is actively trying to stop the news story from spreading.
#newsonleo #x #npr #technology
On Thursday X users began to notice that a link to the NPR story about the Arlington Cemetery event, when clicked, would display the following message: “Warning: this link may be unsafe” followed by the URL of the web page in question, https://npr.org/2024/08/29/nx-s1-5092087/trump-arlington-cemetery-altercation-tiktok.
Instead of being taken to the website, the warning encourages them to go “back to the previous page” by clicking the big blue button. To read the news story, users would have to click on the small text below that reads, “Ignore this warning and continue.”
Article
How OpenAI Strawberry Works ― "ONE TEXTBOOK TO RULE THEM ALL" ― My Educated Guess
#technology #openai #strawberry
Spotify points finger at Apple over an unwelcome change to volume control technology
When streaming to connected devices via Spotify Connect on iOS, users were previously able to use the physical buttons on their iPhone to adjust the volume. But this will no longer work.
Spotify claims Apple may again be in violation of European regulation, the Digital Markets Act (DMA), which requires interoperability from big technology companies dubbed “gatekeepers.” This time, the issue isn’t about in-app purchases, links or pricing information, but rather how Apple has discontinued the technology that allows Spotify users to control the volume on their connected devices.
#spotify #apple #technology #music #newsonleo
When streaming to connected devices via Spotify Connect on iOS, users were previously able to use the physical buttons on the side of their iPhone to adjust the volume. As a result of the change, this will no longer work.
To work around the issue, Spotify iOS users will instead be directed to use the volume slider in the Spotify Connect menu in the app to control the volume on connected devices.
The company notes that this issue doesn’t affect users controlling the volume on iOS Bluetooth or AirPlay sessions, nor users on Android. It only applies to those listening via Spotify Connect on iOS.
As a result, Spotify iOS users globally will be directed to use the new in-app volume slider beginning on September 3.
Article
Googles New GameNGen SURPRISES Everyone! (GameNGen Simulates DOOM Videogames)
#ai #technology
According to Claude3:
What is latent space activation?
Latent space activation refers to a concept in machine learning and artificial intelligence, particularly in the context of deep learning and neural networks. Here's a concise explanation:
Latent space activation is the process of stimulating or utilizing specific regions within a model's internal representation space. This space, often called the latent space, contains compressed or abstract representations of data learned by the model during training.
Key points:
This concept is particularly important in areas like:
Who does this allow for the creation of synthetic data?
Latent space activation enables the creation of synthetic data through several mechanisms. Here's a brief explanation:
Learned representations: Models capture essential features of data in the latent space.
Interpolation: By activating different points in this space, we can generate new, unseen examples.
Controlled generation: Manipulating specific dimensions in the latent space allows for targeted attribute changes.
Sampling: Drawing random points from the latent distribution creates diverse synthetic samples.
Feature disentanglement: Well-structured latent spaces separate different data attributes, enabling fine-grained control.
This process is particularly powerful in generative models like GANs and VAEs.
Is synthetic data useful for further training of AI models and knowledge context? Or does it degrade with each generation?
Synthetic data can indeed be useful for further training AI models and expanding knowledge contexts, but its effectiveness and potential for degradation depend on several factors. Let's break this down:
Benefits of synthetic data:
Potential issues:
Degradation concerns:
The risk of degradation across generations (often called "model collapse" or "mode collapse" in some contexts) is a valid concern. However, it's not inevitable if proper techniques are employed:
Best practices:
In conclusion, while synthetic data can be highly valuable for AI training and knowledge expansion, its effective use requires careful management and ongoing validation to prevent degradation and ensure it remains representative of the real-world phenomena it's meant to model.
How can a lack of real world generalizations be fixed? What can be done to make sure a model using synthetic data doesnt fall victim to this?
Addressing the lack of real-world generalization in models trained on synthetic data is crucial for their practical application.
Strategies to Improve Real-World Generalization of Models Trained on Synthetic Data
Incorporate a portion of real-world data into the training set
Gradually increase the proportion of real data as training progresses
Introduce random variations in synthetic data generation
Helps model learn invariant features that generalize better
Pre-train on synthetic data, then fine-tune on smaller real-world dataset
Leverages large synthetic datasets while adapting to real-world nuances
Combine models trained on different mixtures of synthetic and real data
Improves overall robustness and generalization
Periodically update model with new real-world data
Maintains relevance to changing real-world conditions
Use diverse real-world test sets for evaluation
Identify and address specific generalization gaps
Develop metrics to evaluate synthetic data quality
Ensure synthetic data closely mimics real-world distributions
Involve domain experts in synthetic data generation and validation
Ensures synthetic data captures crucial real-world aspects
I've created a comprehensive list of strategies to improve real-world generalization for models trained on synthetic data. These approaches aim to bridge the gap between synthetic and real-world data, ensuring that models can perform well in practical applications.
Key points to emphasize:
Mixing real and synthetic data is crucial. Even a small amount of real-world data can significantly improve generalization.
Diverse training approaches like domain randomization and curriculum learning help models learn more robust features.
Continuous evaluation and updating are essential. The real world changes, and models need to adapt.
Quality of synthetic data matters immensely. Investing in high-quality synthetic data generation can greatly reduce generalization issues.
To implement these strategies effectively, it's important to:
Intel working with bankers to present board with strategic options
The advisors are likely to present their findings to Intel's full board in September, with a variety of options including M&A on the table.
Intel executives are working with multiple advisors to formulate options to address its flagging business, according to a person with knowledge of the matter.
Those advisors, which include Morgan Stanley and other bankers, will likely present Intel's directors with options at an upcoming board meeting in September, said the person, who requested anonymity to discuss confidential matters. The advisors are considering a full range of options, including splitting off and selling businesses, the person said.
#newsonleo #intel #morganstanley #technology
Russian government hackers found using exploits made by spyware companies NSO and Intellexa
Google said the findings were an example of how exploits developed by spyware makers can end up in the hands of "dangerous threat actors."
Google says it has evidence that Russian government hackers are using exploits that are “identical or strikingly similar” to those previously made by spyware makers Intellexa and NSO Group.
In a blog post on Thursday, Google said it is not sure how the Russian government acquired the exploits, but said this is an example of how exploits developed by spyware makers can end up in the hands of “dangerous threat actors.”
#newsonleo #spyware #hacking #russia #technology
In this case, Google says the threat actors are APT29, a group of hackers widely attributed to Russia’s Foreign Intelligence Service, or the SVR. APT29 is a highly capable group of hackers, known for its long-running and persistent campaigns aimed at conducting espionage and data theft against a range of targets, including tech giants Microsoft and SolarWinds, as well as foreign governments.
Google said it found the hidden exploit code embedded on Mongolian government websites between November 2023 and July 2024. During this time, anyone who visited these sites using an iPhone or Android device could have had their phone hacked and data stolen, including passwords, in what is known as a “watering hole” attack.
The exploits took advantage of vulnerabilities in the iPhone’s Safari browser and Google Chrome on Android that had already been fixed at the time of the suspected Russian campaign. Still, those exploits nevertheless could be effective in compromising unpatched devices.
According to the blog post, the exploit targeting iPhones and iPads was designed to steal user account cookies stored in Safari specifically across a range of online email providers that host the personal and work accounts of the Mongolian government. The attackers could use the stolen cookies to then access those government accounts. Google said the campaign aimed at targeting Android devices used two separate exploits together to steal user cookies stored in the Chrome browser.
Article
I now have a script that I can add transcripts to my shorts.
Google is working on AI that can hear signs of sickness
Given everything you’ve already heard about AI, you may not be surprised to learn that Google is among other outfits
Given everything you’ve already heard about AI, you may not be surprised to learn that Google is among other outfits beginning to use sound signals to predict early signs of disease.
How? According to Bloomberg, Google has trained its foundation AI model with 300 million pieces of audio that included coughs, sniffles, and labored breathing, to identify, for example, someone battling tuberculosis.
#google #technology #newsonleo #health
Now, it has teamed up with an Indian company – Salcit Technologies, a respiratory healthcare AI startup — to tuck that tech into smartphones where it can potentially help high-risk populations in geographies with poor access to healthcare.
It’s not Google’s first foray into trying to digitize human senses. Its venture arm has also backed at least one startup that’s using AI in an attempt to sniff out disease, literally.
FuturisticTech -- 15 Technologies That Will Change The World
#technology #future
#leoshorts #technology #gadgets
#leoshorts #technology #future
#leoshorts #technology
#leoshorts #technology #apple
#leoshorts #technology #softwarecompanies
AI
Illustrators who already have jobs and creations 'stolen' by AI: 'Fear of not being able to support myself'
The conversation that illustrator Lúcia Lemos, 30, had with a former client still echoes in her head.
“He told me that, no matter how good I was, my work was no longer worth hiring,” remembers Lúcia.
"He said: 'I hire you, and it takes you a week to make a drawing [for a book], now, I type a line of code and I get 20 drawings right away with artificial intelligence."
"Unfair" competition has affected Rio's illustrator's income considerably.
#newsonleo #technology #ai #art
When BBC News Brasil spoke to Lúcia, her expectation was to earn less than R$300 per month with the commissioned work.
Lúcia's example and the reports of other professionals show that illustrators are one of the groups of professionals in the creative industry who are at the forefront of the impact of the popularization of generative artificial intelligence (AI), that which creates new content, such as text, images, music, audio and videos, from a database.
Creative director and illustrator Wagner Loud, 33, says he has heard the same thing from former co-workers in São Paulo. In some companies, he says, illustration sectors have already been closed or reduced to a minimum.
"Those who used to sit down and think about art, with new ideas, now sit down and put keywords in the system to generate a new design. That's sad", comments Wagner.
The alarming situation has led to the creation of groups of artists who discuss the new scenario and propose finding solutions through proposed laws.
Singer and songwriter Marisa Monte is one of those who has used her voice to give visibility to the cause of artists, especially musicians.
She participated in a session in the Senate committee that discusses the bill that regulates artificial intelligence in Brazil, PL 2338.
New Cover Image?! 😎
The Upgrade Paradox
According to Groq:
What are the risks people cite with AI?
There are several risks that people cite with AI, including:
It's important to note that these risks are not unique to AI and are similar to the risks associated with other technologies. However, AI is a rapidly evolving field, and it's essential to be aware of these risks and to take steps to mitigate them.
According to Grok:
What are the expected benefits of AI?
The expected benefits of AI are numerous and varied, and can be categorized into several areas:
These are just a few examples of the many expected benefits of AI. As the technology continues to evolve and mature, we can expect to see even more innovative applications and benefits across various industries and aspects of society.
The Guardian: From dumb phones to hand-me-downs: the ultimate guide to buying phones for kids
https://www.theguardian.com/technology/article/2024/aug/30/apple-android-google-or-retro-whats-the-best-first-phone-to-get-for-your-kids
Apple and Nvidia could be OpenAI's next big investors
Apple and Nvidia are reportedly considering investing in OpenAI's next funding round -- a round that could value the AI startup at $100 billion.
Nvidia and Apple are reportedly in talks to contribute to OpenAI’s next fundraising round — a round that could value the ChatGPT maker at $100 billion.
Per its sources, the New York Times says earlier OpenAI investor Thrive Capital would lead the deal should it happen. (Bloomberg was the first to report Nvidia’s involvement, and The WSJ broke the story of Apple’s potential interest.) Microsoft — which already owns 49% of OpenAI — may participate as well.
#nvidia #technology #apple #Openai #newsonleo
OpenAI needs capital. Its annualized revenue reportedly eclipsed $3.4 billion early this year, but it’s said to be on track to lose $5 billion by year end as it expands its AI training and staffing efforts.
OpenAI has ties to both companies. It runs and trains its generative AI models primarily on Nvidia GPUs; meanwhile Apple earlier this year agreed to integrate ChatGPT into iOS as part of Apple’s forthcoming suite of AI features, Apple Intelligence.
The Guardian: California advances landmark legislation to regulate large AI models
https://www.theguardian.com/technology/article/2024/aug/29/california-ai-regulation-bill
The Verge: Ryzen CPU owners can now download better gaming performance thanks to a Windows 11 update
https://www.theverge.com/2024/8/28/24230321/microsoft-windows-11-update-ryzen-cpu-performance-improvement
#gaming
Wired: Powerful Spyware Exploits Enable a New String of ‘Watering Hole’ Attacks
https://www.wired.com/story/russia-cozy-bear-watering-hole-attacks/
BBC: How beer is used to make alternative leather
Now that is an amazing #beersaturday technology :))
Full video here: https://www.bbc.com/reel/video/p0jjvhkd/how-beer-is-used-to-make-alternative-leather
BBC: Will sustainable aviation fuels take off?
https://www.bbc.com/news/articles/cg64pwxzln4o
Reuters: X braces for shutdown in Brazil as Elon Musk's spat with judge intensifies
https://www.reuters.com/technology/brazilian-court-suspend-x-brazil-if-musk-does-not-name-new-country-2024-08-28/
Reuters: Ask Claude: Amazon turns to Anthropic's AI for Alexa revamp
https://www.reuters.com/technology/artificial-intelligence/amazon-turns-anthropics-claude-alexa-ai-revamp-2024-08-30/
Reuters: Dell shares rise as AI server demand boosts results, forecasts
https://www.reuters.com/technology/dell-shares-jump-ai-server-demand-boosts-results-forecasts-2024-08-30/
Reuters: Intel rises as report of chipmaker exploring options cheers glum investors
https://www.reuters.com/technology/intel-rises-report-chipmaker-exploring-options-stokes-investor-enthusiasm-2024-08-30/
Reuters: Apple, Nvidia in talks to join OpenAI funding round, media reports say
https://www.reuters.com/technology/apple-talks-join-openai-funding-round-wsj-reports-2024-08-29/