It was only a matter of time before the culture wars came to AI. Since the release of ChatGPT in late 2022, Elon Musk has railed on Twitter against what he has called "Woke AI." He has specifically criticized ChatGPT's developer, OpenAI, for the features designed to prevent the chatbot from parroting racism and sexism. Now, the billionaire is courting AI researchers with a proposal to start a new AI company to rival the developer of ChatGPT, the tech news site The Information reported on Wednesday. "The danger of training AI to be woke--in other words, lie--is deadly," Musk tweeted in December.

The biggest tech story of the year is shaping up around the seemingly sudden arrival of AI chatbots into mainstream attention: piggybacking off last year's viral reception to text-to-image generators like DALL-E 2, the launch of OpenAI's ChatGPT in November has since spurred not only widespread media coverage and netizen adoption, but also an industry-wide arms race. Whatever polite corporate doffing made to AI's thicket of ethical ramifications over the past few decades disintegrated nearly overnight in favor of Silicon Valley's primal fear of competition, and we now live in a society where Microsoft's newly AI-powered Bing ("Sydney," to her friends), Google's Bard, Meta's LLaMA, and Snapchat's My AI (which at least allows you the dignity of naming your chatbot yourself) seem poised to transform us all. The AI future feels nigh, if not terribly optimistic. In an era where major breakthroughs in tech render either inscrutable--admit it, you still don't know what a blockchain is, do you?--or We're kind of used to it already: After spending the greater part of Web 2.0 accepting the sleight of hand that invisible, algorithmic forces exert on our day-to-day, the consumer-friendly AI-powered machinations of driverless cars and actually efficient task assistants and decent predictive-text features has become a foregone conclusion.

When OpenAI launched ChatGPT, with zero fanfare, in late November 2022, nobody inside the company was prepared for a viral mega-hit. It was viewed in-house as a "research preview," a tease of a more polished version of a two-year-old technology and a way to iron out some of its flaws. But then it absolutely blew up. The firm has been scrambling to catch up--and capitalize on its success--ever since. To get the inside story behind the chatbot--how it was made, how OpenAI has been updating it since release, and how its makers feel about its success--our senior AI editor Will Douglas Heaven talked to four people who helped build what has become the most popular internet app ever.

Audrey Kim's dog Murphy uses a combination of head nods and 10 buttons on the ground to communicate, she says, and has a habit of making friends with crows. She taught him to use the buttons because she believes consciousness is a spectrum and intelligence is mysterious. Those tenets also led her to become curator of the Misalignment Museum, a temporary exhibition about the future of artificial intelligence that opens today in San Francisco, ground zero for recent excitement about generative AI and chatbots like OpenAI's ChatGPT. The Misalignment Museum imagines a future in which AI starts to take the route mapped out in countless science fiction films--becoming self aware and setting about killing off humanity. Fortunately, in Kim's vision the algorithms self-correct and stop short of killing all people.

To get the inside story behind the chatbot--how it was made, how OpenAI has been updating it since release, and how its makers feel about its success--I talked to four people who helped build what has become one of the most popular internet apps ever. In addition to Agarwal and Fedus, I spoke to John Schulman, a cofounder of OpenAI, and Jan Leike, the leader of OpenAI's alignment team, which works on the problem of making AI do what its users want it to do (and nothing more). What I came away with was the sense that OpenAI is still bemused by the success of its research preview, but has grabbed the opportunity to push this technology forward, watching how millions of people are using it and trying to fix the worst problems as they come up. Since November, OpenAI has already updated ChatGPT several times. The researchers are using a technique called adversarial training to stop ChatGPT from letting users trick it into behaving badly (known as jailbreaking).

Scammers could use ChatGPT to write phishing emails at a fraction of the cost of a human-penned missive, potentially cutting the cost per email by about 96 per cent. The popular chatbot, which is based on a large language model (LLM), was released by OpenAI in November 2022 and has since become a useful tool in many industries.

Reinforcement Learning (RL) is an area of machine learning figuring out how agents take actions in an unknown environment to maximize its rewards. Unlike classical Markov Decision Process (MDP) in which agent has full knowledge of its state, rewards, and transitional probability, reinforcement learning utilizes exploration and exploitation for the model uncertainty. Under the condition that the model usually has a large state space, a neural network (NN) can be used to correlate its input state to its output actions to maximize the agent's rewards. However, building and training an efficient neural network is challenging. Inspired by Double Q-learning and Asynchronous Advantage Actor-Critic (A3C) algorithm, we will propose and implement an improved version of Double A3C algorithm which utilizing the strength of both algorithms to play OpenAI Gym Atari 2600 games to beat its benchmarks for our project.

Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown promising few-shot performance benefited from the contrastive language-image pre-training. We then question, if the more diverse pre-training knowledge can be cascaded to further assist few-shot representation learning. In this paper, we propose CaFo, a Cascade of Foundation models that incorporates diverse prior knowledge of various pre-training paradigms for better few-shot learning. Our CaFo incorporates CLIP's language-contrastive knowledge, DINO's vision-contrastive knowledge, DALL-E's vision-generative knowledge, and GPT-3's language-generative knowledge. Specifically, CaFo works by 'Prompt, Generate, then Cache'. Firstly, we leverage GPT-3 to produce textual inputs for prompting CLIP with rich downstream linguistic semantics. Then, we generate synthetic images via DALL-E to expand the few-shot training data without any manpower. At last, we introduce a learnable cache model to adaptively blend the predictions from CLIP and DINO. By such collaboration, CaFo can fully unleash the potential of different pre-training methods and unify them to perform state-of-the-art for few-shot classification. Code is available at https://github.com/ZrrSkywalker/CaFo.

History has long been a theater of war, the past serving as a proxy in conflicts over the present. Ron DeSantis is warping history by banning books on racism from Florida's schools; people remain divided about the right approach to repatriating Indigenous objects and remains; the Pentagon Papers were an attempt to twist narratives about the Vietnam War. The Nazis seized power in part by manipulating the past--they used propaganda about the burning of the Reichstag, the German parliament building, to justify persecuting political rivals and assuming dictatorial authority. That specific example weighs on Eric Horvitz, Microsoft's chief scientific officer and a leading AI researcher, who tells me that the apparent AI revolution could not only provide a new weapon to propagandists, as social media did earlier this century, but entirely reshape the historiographic terrain, perhaps laying the groundwork for a modern-day Reichstag fire. These are powerful and easy-to-use programs that produce synthetic text, images, video, and audio, all of which can be used by bad actors to fabricate events, people, speeches, and news reports to sow disinformation.

Discover (and save!) your own Pins on Pinterest.