Welcome to the PMBug forums - a watering hole for folks interested in gold, silver, precious metals, sound money, investing, market and economic news, central bank monetary policies, politics and more. You can visit the forum page to see the list of forum nodes (categories/rooms) for topics.
Why not register an account and join the discussions? When you register an account and log in, you may enjoy additional benefits including no Google ads, market data/charts, access to trade/barter with the community and much more. Registering an account is free - you have nothing to lose!
Google announced new AI-powered features today for the new Pixel 8 series phones, such as Magic Editor, which enables background filling and subject repositioning, and Best Take, which combines multiple shots to create the best group photo.
Magic Editor will let you tap or circle an object and then let it shift or resize the object. Magic Editor also uses generative AI to recreate the background when you shift the selected object. This feature also lets users make changes to the background using presets.
Magic Editor will suggest contextual changes to the image based on lighting and background. Plus, Users will be able to choose from multiple results of an edit. The company first announced this feature in May at Google I/O.
...
Qualcomm’s Snapdragon 8 series of chipsets powers most high-end Android phones on the market. The company has now peeled the curtain back on its latest flagship processor, the Snapdragon 8 Gen 3.
Between the revised CPU, tweaked GPU, AI enhancements, and new camera tricks, there’s no shortage of improvements and new additions here.
...
Generative AI is everywhere, and Qualcomm is taking advantage of this trend. The company says that the Snapdragon 8 Gen 3’s upgraded Hexagon NPU is designed with generative AI in mind. Headline improvements include up to 98% faster performance than the previous generation, a 40% efficiency boost, a two-fold boost to bandwidth in large shared memory, and more bandwidth feeding the Tensor Accelerator. Whealton says it’s also implemented a separate voltage rail for the Tensor Accelerator, allowing the NPU and Tensor silicon to each run at different power levels for a better balance of performance and efficiency.
Qualcomm says the chipset supports large language models with over 10 billion parameters running at almost 15 tokens per second. So what do all these improvements mean for actual use cases?
One major benefit is that you can expect much faster image generation via Stable Diffusion. Qualcomm previously demonstrated on-device Stable Diffusion on a Snapdragon 8 Gen 2 reference handset, taking over 15 seconds to generate an image from a text prompt. However, the company says Stable Diffusion now takes less than a second to generate an image. The company also says it’s working with Snapchat to implement this faster Stable Diffusion solution in the app.
Another interesting addition is “on-device personalization” for AI. Qualcomm says it’ll use your device’s sensors (e.g. GPS, Wi-Fi, microphone, Bluetooth, camera) to personalize chatbot queries. So if you were to ask a chatbot about the best restaurants or activities to do, you can expect more personalized responses based on your location and other factors instead of having to explicitly specify this in your query.
Qualcomm is also touting the privacy benefits of on-device personalization. The company sought to assuage concerns that apps would have access to this personalization data. Vinesh Sukumar, Qualcomm’s head of AI and machine learning, claimed that any app using this function would only get a “refined element of the input prompt that is filtered” before it gets to the app. He added that this personalization data is discarded after a prompt is generated.
Either way, Qualcomm will showcase an AI system demo running on-device at the Snapdragon Summit, powered by Meta’s Llama 2 LLM. The company notes that this demo offers “end-to-end” voice support, so you can talk to the chatbot and have it talk back to you.
Finally, the Snapdragon 8 Gen 3 will pack support for multi-modal generative AI models. That means you can input text, images, and speech and have these generative models output text, images, and speech in return.
This improved generative AI support entails more than just better voice assistants and failed attempts at naughty AI-generated art, though.
...
Meet Grok, the first technology out of Elon Musk's new AI company, xAI.
Grok, the company said, is modeled on "The Hitchhiker's Guide to the Galaxy." It is supposed to have "a bit of wit," "a rebellious streak" and it should answer the "spicy questions" that other AI might dodge, according to a Saturday statement from xAI.
...
Grok also has access to data from X, which xAI said will give it a leg-up. Musk, on Sunday, posted a side-by-side comparison of Grok answering a question versus another AI bot, which he said had less current information.
Still, xAI hedged in its statement, as with any Large Language Model, or LLM, Grok "can still generate false or contradictory information."
The prototype is in its early beta phase, only two months in training and is available to a select number of users to test out before the company releases it more widely. Users can sign up for a waitlist for a chance to use the bot. Eventually, Musk said on X, Grok will be a feature of X Premium+, which costs $16 per month.
...
We’re rolling out custom versions of ChatGPT that you can create for a specific purpose—called GPTs. GPTs are a new way for anyone to create a tailored version of ChatGPT to be more helpful in their daily life, at specific tasks, at work, or at home—and then share that creation with others. For example, GPTs can help you learn the rules to any board game, help teach your kids math, or design stickers.
Anyone can easily build their own GPT—no coding is required. You can make them for yourself, just for your company’s internal use, or for everyone. Creating one is as easy as starting a conversation, giving it instructions and extra knowledge, and picking what it can do, like searching the web, making images or analyzing data. Try it out at chatgpt.com/create.
...
We released the first version of GPT-4 in March and made GPT-4 generally available to all developers in July. Today we’re launching a preview of the next generation of this model, GPT-4 Turbo.
GPT-4 Turbo is more capable and has knowledge of world events up to April 2023. It has a 128k context window so it can fit the equivalent of more than 300 pages of text in a single prompt. We also optimized its performance so we are able to offer GPT-4 Turbo at a 3x cheaper price for input tokens and a 2x cheaper price for output tokens compared to GPT-4. ...
It's also biased towards the alphabet community and is biased against white people. It is ridiculously easy to make it show those biases. I think these are the genderless liberal freaks programming this crap.
View attachment 11042
How about ANY of 'em??????Top row, far right.............???????????
Top row, far right.............???????????
How about ANY of 'em??????
I'm thinking photoshopped. Some are funny to look at but aren't real. At least I'd hope they aren't real.
OpenAI’s board of directors said Friday that Sam Altman will step down as CEO and will be replaced on an interim basis by technology chief Mira Murati.
The company said it conducted “a deliberative review process” and “concluded that he was not consistently candid in his communications with the board, hindering its ability to exercise its responsibilities.”
“The board no longer has confidence in his ability to continue leading OpenAI,” the statement said.
...
Former OpenAI CEO Sam Altman will be joining Microsoft to lead a new advanced AI research team, according to Microsoft CEO Satya Nadella.
Nadella said on the social media platform X, formerly known as Twitter, that Altman and Greg Brockman, former OpenAI president and board chair, alongside other colleagues, will be joining Microsoft to lead a new advanced artificial intelligence research team.
...
It's been just a few days since Sam Altman, the former CEO of OpenAI, was ousted in a shock move — and his replacement has already been named.
After a weekend of rumor and speculation, Emmett Shear — former co-founder and CEO of Twitch — confirmed he will take the top job at probably the most high-profile AI company in the world.
...
...
The sacking set in motion a dizzying sequence of events that kept the tech industry glued to its social feeds all weekend: First, it wiped $48 billion off the valuation of Microsoft, OpenAI’s biggest partner. Speculation about malfeasance swirled, but employees, Silicon Valley stalwarts and investors rallied around Altman, and the next day talks were being held to bring him back. Instead of some fiery scandal, reporting indicated that this was at core a dispute over whether Altman was building and selling AI responsibly. By Monday, talks had failed, a majority of OpenAI employees were threatening to resign, and Altman announced he was joining Microsoft.
All the while, something else went up in flames: the fiction that anything other than the profit motive is going to govern how AI gets developed and deployed. Concerns about “AI safety” are going to be steamrolled by the tech giants itching to tap in to a new revenue stream every time.
...
After the unexpected firing of former OpenAI CEO Sam Altman on Friday, OpenAI's board of directors approached Dario Amodei, the co-founder and CEO of rival large-language model developer Anthropic, about a merger of the two companies, according to a report by The Information, which cited a "person with direct knowledge."
The person said OpenAI's board approached Amodei after they fired Altman on Friday. They noted the deal was sweetened to allow Amodei to replace Altman as CEO.
The Information reported Amodei declined the offer, adding, "It's not clear whether the merger proposal led to any serious discussion."
...
WTF does Larry Summers know about AI?
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?