China’s Baidu unveiled its much-awaited artificial intelligence-powered chatbot known as Ernie Bot on Thursday, but disappointed investors with its use of pre-recorded videos and the lack of a public launch, sending its shares tumbling.
The just over an hour-long presentation, which came two days after Alphabet Inc’s (GOOGL.O) Google unveiled a flurry of AI tools for its email, collaboration and cloud software, gave the world a glimpse of what could be China’s strongest rival to U.S. research lab OpenAI’s ChatGPT. Read More
Tag Archives: ChatBots
OpenAI co-founder on company’s past approach to openly sharing research: ‘We were wrong’
OpenAI announced its latest language model, GPT-4, but many in the AI community were disappointed by the lack of public information. Their complaints track increasing tensions in the AI world over safety.
Yesterday, OpenAI announced GPT-4, its long-awaited next-generation AI language model. The system’s capabilities are still being assessed, but as researchers and experts pore over its accompanying materials, many have expressed disappointment at one particular feature: that despite the name of its parent company, GPT-4 is not an open AI model.
OpenAI has shared plenty of benchmark and test results for GPT-4, as well as some intriguing demos, but has offered essentially no information on the data used to train the system, its energy costs, or the specific hardware or methods used to create it. Read More
OpenAI Introduces GPT-4
OpenAI announced GPT-4, its latest milestone in scaling up deep learning.
GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks. For example, it passes a simulated bar exam with a score around the top 10% of test takers; in contrast, GPT-3.5’s score was around the bottom 10%. We’ve spent 6 months iteratively aligning GPT-4 using lessons from our adversarial testing program as well as ChatGPT, resulting in our best-ever results (though far from perfect) on factuality, steerability, and refusing to go outside of guardrails.
… We are releasing GPT-4’s text input capability via ChatGPT and the API (with a waitlist). To prepare the image input capability for wider availability, we’re collaborating closely with a single partner to start. We’re also open-sourcing OpenAI Evals, our framework for automated evaluation of AI model performance, to allow anyone to report shortcomings in our models to help guide further improvements. Read More
Spotify launches ‘DJ,’ a new feature offering personalized music with AI-powered commentary
Ahead of Spotify’s upcoming Stream On event, where the company is expected to announce a redesigned home feed and other updates, the company today launched a new AI feature called “DJ” to better personalize the music listening experience for its users. Similar to a radio DJ, Spotify’s DJ feature will deliver a curated selection of music alongside AI-powered spoken commentary about the tracks and artists you like, using what Spotify says is a “stunningly realistic voice.”
The idea, explains the company, is for Spotify to get to know users so well that the DJ can choose what to play for you when you hit the button. Or, as Spotify says, it’s putting an “AI DJ in your pocket.” Read More
Large language models are having their Stable Diffusion moment
The open release of the Stable Diffusion image generation model back in August 2022 was a key moment. I wrote how Stable Diffusion is a really big deal at the time.
People could now generate images from text on their own hardware!
More importantly, developers could mess around with the guts of what was going on.
The resulting explosion in innovation is still going on today. Most recently, ControlNet appears to have leapt Stable Diffusion ahead of Midjourney and DALL-E in terms of its capabilities.
It feels to me like that Stable Diffusion moment back in August kick-started the entire new wave of interest in generative AI—which was then pushed into over-drive by the release of ChatGPT at the end of November. Read More
China’s ChatGPT Black Market Is Thriving
A booming illicit market for OpenAI’s chatbot shows the huge potential, and risks, for Chinese generative AI.
Yuxin Guo is a master’s student studying at a Beijing University. For a few months, she had been following online discussions about ChatGPT, the generative AI tool that produces almost natural-sounding language in response to text prompts. One video she found on social media platform Weibo showed how college students in the US were using the technology to write research papers. In February, she finally decided to try it out for herself.
“I got curious because so many people are talking about it,” Guo says, “although not a lot of people seem to clearly know how to access it.”
ChatGPT isn’t available in China—it’s not blocked, but OpenAI, which built the tool, hasn’t made it available there—so Guo went onto Taobao, China’s biggest ecommerce site, where hundreds of thousands of merchants offer everything from iPhone cases to foreign driver’s licenses.
ChatGPT logins have become a hot commodity on Taobao, as have foreign phone numbers—particularly virtual ones that can receive verification codes. Read More
D-ID’s new web app gives a face and voice to OpenAI’s ChatGPT
D-ID, the Israeli startup behind Deep Nostalgia, announced today that it’s launching the beta version of its new web app that allows users to talk face-to-face with photorealistic AI. The web app, called chat.D-ID, combines D-ID’s text-to-video streaming technology with OpenAI’s ChatGPT to make conversations with AI more accessible.
The startup’s CEO and co-founder, Gil Perry, told TechCrunch that D-ID believes giving ChatGPT a voice and face will allow more people to use the technology, as people who can’t read and write will now be able to converse with AI. Another goal of the chat.D-ID to make it easier for elderly people to use AI. The company believes its new web app opens up access to ChatGPT more widely.
“The app is an easier way to use the power of AI and converse with ChatGPT,” Perry said. “We are wired to communicate with faces, we understand the situation better when we do. We feel more comfortable and we can observe complex information better when we’re in what feels like a real scenario. Video is more effective than text, so the app increases the power of large language models by adding a face.” Read More
You Are Not a Parrot
And a chatbot is not a human. And a linguist named Emily M. Bender is very worried what will happen when we forget this.
Nobody likes an I-told-you-so. But before Microsoft’s Bing started cranking out creepy love letters; before Meta’s Galactica spewed racist rants; before ChatGPT began writing such perfectly decent college essays that some professors said, “Screw it, I’ll just stop grading”; and before tech reporters sprinted to claw back claims that AI was the future of search, maybe the future of everything else, too, Emily M. Bender co-wrote the octopus paper.
Bender is a computational linguist at the University of Washington. She published the paper in 2020 with fellow computational linguist Alexander Koller. The goal was to illustrate what large language models, or LLMs — the technology behind chatbots like ChatGPT — can and cannot do. Read More
More than you’ve asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models
We are currently witnessing dramatic advances in the capabilities of Large Language Models (LLMs). They are already being adopted in practice and integrated into many systems, including integrated development environments (IDEs) and search engines. The functionalities of current LLMs can be modulated via natural language prompts, while their exact internal functionality remains implicit and unassessable. This property, which makes them adaptable to even unseen tasks, might also make them susceptible to targeted adversarial prompting. Recently, several ways to misalign LLMs using Prompt Injection (PI) attacks have been introduced. In such attacks, an adversary can prompt the LLM to produce malicious content or override the original instructions and the employed filtering schemes. Recent work showed that these attacks are hard to mitigate, as state-of-the-art LLMs are instruction-following. So far, these attacks assumed that the adversary is directly prompting the LLM. In this work, we show that augmenting LLMs with retrieval and API calling capabilities (so-called Application-Integrated LLMs) induces a whole new set of attack vectors. These LLMs might process poisoned content retrieved from the Web that contains malicious prompts pre-injected and selected by adversaries. We demonstrate that an attacker can indirectly perform such PI attacks. Based on this key insight, we systematically analyze the resulting threat landscape of Application-Integrated LLMs and discuss a variety of new attack vectors. To demonstrate the practical viability of our attacks, we implemented specific demonstrations of the proposed attacks within synthetic applications. In summary, our work calls for an urgent evaluation of current mitigation techniques and an investigation of whether new techniques are needed to defend LLMs against these threats. Read More
How will Language Modelers like ChatGPT Affect Occupations and Industries?
Recent dramatic increases in AI language modeling capabilities has led to many questions about the effect of these technologies on the economy. In this paper we present a methodology to systematically assess the extent to which occupations, industries and geographies are exposed to advances in AI language modeling capabilities. We find that the top occupations exposed to language modeling include telemarketers and a variety of post-secondary teachers such as English language and literature, foreign language and literature, and history teachers. We find the top industries exposed to advances in language modeling are legal services and securities, commodities, and investments. Read More
Rick's Cafe AI 