Thursday, December 29, 2022

Vitalik Buterin: The Ezra Klein Show

Ethereum’s Founder on What Crypto Can — and Can’t — Do Vitalik Buterin explains digital currency’s potential to transform our world. .

there’s this other side too, this more idealistic side, the side of crypto that is not just interested in, but truly obsessed with blockchains and protocols as a way of bringing governance and community into the digital era, as a way of unlocking new forms of cooperation. ........ there’s this other side of crypto that is really important to why the ecosystem has been so vibrant for so long through so many crashes. .......... They obsess over quadratic voting mechanisms, and coins tied to city governance, and decentralized autonomous organizations. .......... The central figure on the set of crypto is Vitalik Buterin. Buterin co-founded Ethereum. He wrote the white paper for the ideas behind it when he was just a teenager. And his insight — and it was a big one — was that, if you could program a currency like Bitcoin that cut out the need for a central authority, then you could use that same cryptographic technology to make almost a programming language that could then program any kind of digital agreement or contract and bind anybody who agreed to it in almost any digital way. .........

Bitcoin can be digital money, but Ethereum can be digital infrastructure. It can be the structure — a binding structure — of how people cooperate online. And Ethereum took off.

........... He’s Ethereum’s benevolent dictator, and he’s become something like the philosopher king of crypto. ......... He’s a digital nomad who lives out of a backpack and seems to think about really nothing but blockchains and what can be built on them.

Wednesday, December 28, 2022


A New Chat Bot Is a ‘Code Red’ for Google’s Search Business . A new wave of chat bots like ChatGPT use artificial intelligence that could reinvent or even replace the traditional internet search engine. ......... Over the past three decades, a handful of products like Netscape’s web browser, Google’s search engine and Apple’s iPhone have truly upended the tech industry and made what came before them look like lumbering dinosaurs. ....... Three weeks ago, an experimental chat bot called ChatGPT made its case to be the industry’s next big disrupter. ......... It can serve up information in clear, simple sentences, rather than just a list of internet links. It can explain concepts in ways people can easily understand. It can even generate ideas from scratch, including business strategies, Christmas gift suggestions, blog topics and vacation plans. ....... its release led Google’s management to declare a “code red.” .......... For more than 20 years, the Google search engine has served as the world’s primary gateway to the internet. But with a new kind of chat bot technology poised to reinvent or even replace traditional search engines, Google could face the first serious threat to its main search business. ........ Google has already built a chat bot that could rival ChatGPT. In fact, the technology at the heart of OpenAI’s chat bot was developed by researchers at Google. ......... Google may be reluctant to deploy this new tech as a replacement for online search, however, because it is not suited to delivering digital ads, which accounted for more than 80 percent of the company’s revenue last year. ......... For companies that have become extraordinarily successful doing one market-defining thing, it is hard to have a second act with something entirely different.” .......... Because these new chat bots learn their skills by analyzing huge amounts of data posted to the internet, they have a way of blending fiction with fact. They deliver information that can be biased against women and people of color. They can generate toxic language, including hate speech. ............. Even if Google perfects chat bots, it must tackle another issue: Does this technology cannibalize the company’s lucrative search ads? If a chat bot is responding to queries with tight sentences, there is less reason for people to click on advertising links. ........... “Google has a business model issue ..... If Google gives you the perfect answer to each query, you won’t click on any ads.” ........... Google must decide whether it will overhaul its search engine and make a full-fledged chat bot the face of its flagship service. .......... Google has been reluctant to share its technology broadly because, like ChatGPT and similar systems, it can generate false, toxic and biased information. ......... Five years ago, Microsoft released a chat bot, called Tay, that spewed racist, xenophobic and otherwise filthy language and was forced to immediately remove it from the internet — never to return. In recent weeks, Meta took down a newer chat bot for many of the same reasons. .......... the technology could produce false or offensive statements. Since its release on the last day of November, ChatGPT — which can produce similarly toxic material — has been used by over a million people. ......... as OpenAI and other companies improve their chat bots — working to solve problems with toxicity and bias — this could become a viable replacement for today’s search engines. Whoever gets there first could be the winner. ........... “Last year, I was despondent that it was so hard to dislodge the iron grip of Google,” said Sridhar Ramaswamy, who previously oversaw advertising for Google, including Search ads, and now runs Neeva. “But technological moments like this create an opportunity for more competition.” .

how can i best increase my social media reach

There are several strategies you can use to increase your social media reach:
  1. Use relevant hashtags: Using relevant hashtags in your social media posts can help make your content discoverable to a wider audience.
  2. Collaborate with influencers or other businesses: Partnering with influencers or other businesses can help expose your content to their followers and increase your reach.
  3. Create shareable content: Try to create content that is interesting and engaging, as this will encourage your followers to share your posts with their own followers.
  4. Engage with your audience: Make an effort to respond to comments and messages from your followers, as this can help build a sense of community and encourage more engagement with your content.
  5. Use paid promotion: Many social media platforms offer paid promotion options that can help increase the visibility of your posts to a targeted audience.
  6. Utilize the features of each platform: Each social media platform has its own unique features that can help increase the reach of your content. For example, you can use Instagram Stories or Facebook Live to create content that disappears after a certain amount of time, which can increase the urgency for users to view and share your content.

how will the world know jesus is back as promised

According to Christian belief, Jesus will return at the end of the world to judge all people and bring about the end of the age. The Bible does not provide a specific description of how Jesus' return will be perceived or announced. Some Christians believe that Jesus' return will be a visible and dramatic event that will be witnessed by all people, while others believe that it will be a more subtle and private event. Ultimately, it is believed that Jesus' return will be evident to those who are looking for it and have faith in him.

Attempt 2:
There are many different beliefs about the return of Jesus, and it is not within the scope of this service to discuss or promote any particular belief or interpretation of religious texts. As an artificial intelligence, I do not have the ability to predict the future or know when or how Jesus might return. It is important to respect the beliefs of others and engage in respectful dialogue about differing viewpoints.

A Coming-Out Party for Generative A.I., Silicon Valley’s New Craze A celebration for Stability AI, the start-up behind the controversial Stable Diffusion image generator, represents the arrival of a new A.I. boom......... In Silicon Valley, crypto and the metaverse are out. Generative A.I. is in. ......... generative A.I. — the wonky umbrella term for A.I. that doesn’t just analyze existing data but creates new text, images, videos, code snippets and more. ........ DALL-E 2, the image generator that OpenAI released this spring, has more than 1.5 million users creating more than two million images every day ........... Sequoia Capital, the venture capital firm, recently said in a blog post that it thought generative A.I. could create “trillions of dollars of economic value.” ......... widespread concern that the company’s lax rules could lead to a flood of violent imagery, nonconsensual nudity, and A.I.-generated propaganda and misinformation. .......... Already, Stable Diffusion and its open-source offshoots have been used to create plenty of offensive images (including, judging by a quick scan of Twitter, a truly astonishing amount of anime pornography). ........ In recent days, several Reddit forums have been shut down after being inundated with nonconsensual nude images, largely made with Stable Diffusion. The company tried to rein in the chaos, telling users not to “generate anything you’d be ashamed to show your mother,” but has stopped short of setting up stricter filters. ............. people had created graphic images of “violently beaten Asian women” using Stable Diffusion. ........... He argues that radical freedom is necessary to achieve his vision of a democratized A.I. that is untethered from corporate influence. .............. “We trust people, and we trust the community,” he said, “as opposed to having a centralized, unelected entity controlling the most powerful technology in the world.” ........... He is a British former hedge fund manager who spent much of the past decade trading oil and advising companies and governments on Middle East strategy and the threat of Islamic extremism. More recently, he organized an alliance of think tanks and technology groups that tried to use big data to help governments make better decisions about Covid-19. .......... Mr. Mostaque, who initially funded Stability AI himself, has quickly become a polarizing figure within the A.I. community. ........ He took plenty of veiled shots at tech giants like Google and OpenAI, which has received funding from Microsoft. He denounced targeted advertising, the core of Google’s and Facebook’s business models, as “manipulative technology,” and he said that, unlike those companies, Stability AI would not build a “panopticon” that spied on its users. (That one drew a groan from Mr. Brin.) .......... the computer the company uses to train its A.I. models, which has more than 5,000 high-powered graphics cards and is already one of the largest supercomputers in the world, would grow to five or 10 times its current size within the next year. That firepower would allow the company to expand beyond A.I.-generated images into video, audio and other formats, as well as make it easy for users around the world to operate their own, localized versions of its algorithms. ........... Mostaque believes that putting generative A.I. into the hands of billions of people will lead to an explosion of new opportunities. ...........

“So much of the world is creatively constipated, and we’re going to make it so that they can poop rainbows,” he said.

............ transparency, not top-down control, is what will keep generative A.I. from becoming a dangerous force.

Generative A.I. Is Here. Who Should Control It? Emad Mostaque, the founder of Stability AI, says his Stable Diffusion image generator is the key to unlocking creativity. His critics say it’s a potential threat. .

Generative AI: A Creative New World A powerful new class of large language models is making it possible for machines to write, code, draw and create with credible and sometimes superhuman results. ........... Humans are good at analyzing things. Machines are even better. Machines can analyze a set of data and find patterns in it for a multitude of use cases, whether it’s fraud or spam detection, forecasting the ETA of your delivery or predicting which TikTok video to show you next. They are getting smarter at these tasks. This is called “Analytical AI,” or traditional AI. ........ Up until recently, machines had no chance of competing with humans at creative work—they were relegated to analysis and rote cognitive labor. But machines are just starting to get good at creating sensical and beautiful things. This new category is called “Generative AI,” meaning the machine is generating something new rather than analyzing something that already exists. ............. Generative AI is well on the way to becoming not just faster and cheaper, but better in some cases than what humans create by hand. Every industry that requires humans to create original work—from social media to gaming, advertising to architecture, coding to graphic design, product design to law, marketing to sales—is up for reinvention. ..........

generative AI should unlock better, faster and cheaper creation across a wide range of end markets

.............. generative AI brings the marginal cost of creation and knowledge work down towards zero, generating vast labor productivity and economic value—and commensurate market cap. ........... The fields that generative AI addresses—knowledge work and creative work—comprise billions of workers. Generative AI can make these workers at least 10% more efficient and/or creative: they become not only faster and more efficient, but more capable than before. Therefore, Generative AI has the potential to generate trillions of dollars of economic value. ............ as the models get bigger and bigger, they begin to deliver human-level, and then superhuman results. Between 2015 and 2020, the compute used to train these models increases by 6 orders of magnitude and their results surpass human performance benchmarks in handwriting, speech and image recognition, reading comprehension and language understanding. OpenAI’s GPT-3 stands out: the model’s performance is a giant leap over GPT-2 and delivers tantalizing Twitter demos on tasks from code generation to snarky joke writing. .......... Just as mobile unleashed new types of applications through new capabilities like GPS, cameras and on-the-go connectivity, we expect these large models to motivate a new wave of generative AI applications. And just as the inflection point of mobile created a market opening for a handful of killer apps a decade ago, we expect killer apps to emerge for Generative AI. The race is on. ............ If we allow ourselves to dream multiple decades out, then it’s easy to imagine a future where Generative AI is deeply embedded in how we work, create and play: memos that write themselves; 3D print anything you can imagine; go from text to Pixar film; Roblox-like gaming experiences that generate rich worlds as quickly as we can dream them up. While these experiences may seem like science fiction today, the rate of progress is incredibly high—we have gone from narrow language models to code auto-complete in several years—and if we continue along this rate of change and follow a “Large Model Moore’s Law,” then these far-fetched scenarios may just enter the realm of the possible.

8 Podcasts for the Spiritual Searcher Even as organized religion loses adherents, Americans continue to seek higher meaning in their lives. .

17 Great Podcasts For The Spiritually Curious Time to clear up some space on your cell phones.
35 Best Religious Podcasts
Most popular podcasts about religion and spirituality
Top 10 Religion & Spirituality Podcasts

How Is Everyone Making Those A.I. Selfies? Images generated with Lensa AI are all over social media, but at what cost? ....... “If most of the images you fed the system were of white faces, then it’s not surprising that when it tries to make an image that looks supposedly ‘better,’ it just makes it whiter” ........ “As cinema didn’t kill theater and accounting software hasn’t eradicated the profession, AI won’t replace artists but can become a great assisting tool.” .

Did the Tesla Story Ever Make Sense? Tesla and Bitcoin may have more in common than you think. ......... Elon Musk’s purchase of Twitter and the reputational self-immolation that followed ......... Tesla sales have surely depended at least in part on the perception that Musk himself is a cool guy ........ I’m familiar with the phenomenon of people who are genuinely brilliant in some areas but utter fools in other domains. For all I know, Musk is or was a highly effective leader at Tesla and SpaceX. .......... we more or less understand the durability of the dominance of Apple and Microsoft, and it’s hard to see how Tesla could ever achieve something similar, no matter how brilliant its leadership. ......... Both Apple and Microsoft benefit from strong network externalities — loosely speaking, everyone uses their products because everyone else uses their products. ........ These days Microsoft has a better reputation than it used to, but as far as I can tell its market strength still reflects comfort a ........ I can attest from personal experience that once you’re in the iPhone/iPad/MacBook ecosystem, you won’t give up on its convenience unless offered something a lot better. .......... Electric cars may well be the future of personal transportation. In fact, they had better be, since electrification of everything, powered by renewable energy, is the only plausible way to avoid climate catastrophe. But it’s hard to see what would give Tesla a long-term lock on the electric vehicle business. ......... investors fell in love with a story line about a brilliant, cool innovator, despite the absence of a good argument about how this guy, even if he really was who he appeared to be, could found a long-lived money machine. .......... nobody has yet managed to find any serious use for cryptocurrency other than money laundering ........ I definitely won’t trust Elon Musk with my cat.

GPT-3 points to a future in which we are even less sure if what we are reading is real or fake. That goes for tweets, online conversations, even long-form prose. ........... At the end of July, Liam Porr, a student at the University of California, Berkeley, generated several blog posts with GPT-3 and posted them on the internet, where they were read by 26,000 people. Sixty viewers were inspired to subscribe to the blog, and only a few suspected that the posts were written by a machine. ......... One of the blog posts — which argued that you can increase your productivity if you avoid thinking too much about everything you do — rose to the top of the leader board on Hacker News, a site where seasoned Silicon Valley programmers, engineers and entrepreneurs rate news articles and other online content. (“In order to get something done, maybe we need to think less,” the post begins. “Seems counterintuitive, but I believe sometimes our thoughts can get in the way of the creative process.”) ............ “People get sucked in,” he said, “even if they know they are being sucked in.” .........

In practice, the system fails about as often as it succeeds.

.......... its talent for conversation breaks down after a few exchanges, when it cannot “remember” what it said just a few seconds before. ........ Processing all of that internet data requires a specialized supercomputer running for months on end, an undertaking that is enormously expensive. When asked if such a project ran into the millions of dollars, Sam Altman, OpenAI’s chief executive, said the costs were actually “higher,” running into the tens of millions.