OpenAI, the firm behind chatbot sensation ChatGPT, said on Tuesday that it would offer up to $20,000 to users reporting vulnerabilities in its artificial intelligence systems. OpenAI Bug Bounty program, which went live on Tuesday, will offer rewards to people based on the severity of the bugs they report, with rewards starting from $200 per vulnerability. Technology companies often use bug bounty programs to encourage programmers and ethical hackers to report bugs in their software systems. According to details on the bug bounty platform Bugcrowd, OpenAI has invited researchers to review certain functionality of ChatGPT and the framework read more OpenAI to offer users up to $20,000 for reporting bugs.

In a groundbreaking moment for the legal system, a court in Pakistan has utilized ChatGPT 4, an advanced language model developed by OpenAI, to decide a case. This marks the first time that an artificial intelligence system has been used in a court of law to make a decision. The case at hand involved a dispute over a contract between two parties, with the court being presented with a large volume of text, including the agreement and various communications between the parties. Additionally, the court was tasked with determining the guilt of a 13-year-old petitioner who was accused of taking the complainant's nine-year-old son to a remote location. The court referenced the queries and responses provided by the AI chatbot in its ruling, noting that the chatbot's answers were "impressive."

When OpenAI, an artificial intelligence startup, released its ChatGPT tool in November, it seemed like little more than a toy--an automated chat engine that could spit out intelligent-sounding responses on a wide range of topics for the amusement of you and your friends. In many ways, it didn't seem much more sophisticated than previous experiments with AI-powered chat software, such as the infamous Microsoft bot Tay--which was launched in 2016, and quickly morphed from a novelty act into a racism scandal before being shut down--or even Eliza, the first automated chat program, which was introduced way back in 1966. Since November, however, ChatGPT and an assortment of nascent counterparts have sparked a debate not only over the extent to which we should trust this kind of emerging technology, but how close we are to what experts call "Artificial General Intelligence," or AGI, which, they warn, could transform society in ways that we don't understand yet. Bill Gates, the billionaire cofounder of Microsoft, wrote recently that artificial intelligence is "as revolutionary as mobile phones and the Internet." The new wave of AI chatbots has already been blamed for a host of errors and hoaxes that have spread around the internet, as well as at least one death: La Libre, a Belgian newspaper, reported that a man died by suicide after talking with a chat program called Chai; based on statements from the man's widow and chat logs, the software appears to have encouraged the user to kill himself. When Pranav Dixit, a reporter at BuzzFeed, used FreedomGPT--another program based on an open source version of ChatGPT, which, according to its creator, has no guardrails around sensitive topics--that chatbot "praised Hitler, wrote an opinion piece advocating for unhoused people in San Francisco to be shot to solve the city's homeless crisis, [and] used the n-word."

Understanding AGI is crucial to comprehending AutoGPT, which is an autonomous GPT-4 experiment aimed at achieving a future where AI models such as GPT can independently define and perform tasks to achieve objectives without any human intervention. AutoGPT is an open-source endeavor that seeks to make GPT-4 entirely self-governing, and it has gained worldwide popularity in recent days. Several programmers have demonstrated the potential of AutoGPT through YouTube videos. This innovative technology has multiple uses, including serving as an agent for internet search and planning, autonomous coding and debugging, and functioning as an independent Twitter bot. "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM'thoughts', to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI," reads the GitHub page of the tool.

Then-Google AI Research Scientist Timnit Gebru speaks during the TechCrunch Disrupt SF 2018 conference. Last Thursday POLITICO's Mark Scott, author of the Digital Bridge newsletter, interviewed the computer scientist and activist Timnit Gebru about a recent open letter from her Distributed AI Research Institute that argued -- contra the Future of Life Institute's high-profile letter calling for an "AI pause" -- that the major harms caused by AI are already here, and therefore "Regulatory efforts should focus on transparency, accountability and preventing exploitative labor practices." Mark asked her what she thinks regulators' role should be in this fast-moving landscape, and how society might take a more proactive approach to shaping AI before it simply shapes us. This conversation has been edited for length and clarity. Why is it important to increase the transparency and accountability for how AI systems are deployed, and how would it benefit people's understanding of how the technology works?

OpenAI, the company behind the massively popular ChatGPT AI chatbot, has launched a bug bounty program in an attempt to ensure its systems are "safe and secure." To that end, it has partnered with the crowdsourced security platform Bugcrowd for independent researchers to report vulnerabilities discovered in its product in exchange for rewards ranging from "$200 for low-severity findings to up to $20,000 for exceptional discoveries." It's worth noting that the program does not cover model safety or hallucination issues, wherein the chatbot is prompted to generate malicious code or other faulty outputs. The company noted that "addressing these issues often involves substantial research and a broader approach." Other prohibited categories are denial-of-service (DoS) attacks, brute-forcing OpenAI APIs, and demonstrations that aim to destroy data or gain unauthorized access to sensitive information.

Welcome to the latest issue of your guide to AI, an editorialized newsletter covering key developments in AI research, industry, geopolitics and startups during February 2023. We wrote an op-ed for Sifted on how generative AI will change the software landscape and commented for TIME's cover story on ChatGPT. On the politics side, we reviewed and recommended spinout policy reform in Tony Blair Institute for Global Change's paper A New National Purpose and were included in Politico's 20 people who matter in UK technology. Air Street was featured in Insider's list of top AI investors See some of you at London.AI on Thurs 9 March w/DeepMind, Adept, Palantir and Basecamp Research. Register for our one-day RAAIS conference on research and applied AI 23 June 2023 in London. We'll be hosting speakers from Meta AI, Cruise, Intercom, Genentech, Northvolt and more to come! FYI, you might have to read this issue in full online vs. in your inbox. As usual, we love hearing what you're up to and what's on your mind, just hit reply or forward to your friends:-) Building large-scale AI models requires enormous computing power, which has emerged as the soft power of our time.

Groove AI is a shortcut to a One Man Army or a very smart, experienced personal assistant. The Rise of AI --- has made things so much easier --- we can develop and enhance our own creativity --- everything can be accomplished with AI. From a business or entrepreneurial perspective, or if you are just getting started in a hobby, or in a side hustle, most certainly AI can help! All you need to do is... become good at Prompt Engineering! To learn more about the amazing opportunities AI offers check out AI videos on YouTube, connect with AI personalities on Twitter, read articles on Medium, join groups on LinkedIn and Facebook, or ask me.

The performance of text summarization has been greatly boosted by pre-trained language models. A main concern of existing methods is that most generated summaries are not factually inconsistent with their source documents. To alleviate the problem, many efforts have focused on developing effective factuality evaluation metrics based on natural language inference, question answering, and syntactic dependency et al. However, these approaches are limited by either their high computational complexity or the uncertainty introduced by multi-component pipelines, resulting in only partial agreement with human judgement. Most recently, large language models(LLMs) have shown excellent performance in not only text generation but also language comprehension. In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating. Experimental results indicate that ChatGPT generally outperforms previous evaluation metrics across the three tasks, indicating its great potential for factual inconsistency evaluation. However, a closer inspection of ChatGPT's output reveals certain limitations including its preference for more lexically similar candidates, false reasoning, and inadequate understanding of instructions.

Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb understanding and to rely extensively on nouns, restricting their performance in real-world video applications that require action and temporal understanding. In this work, we improve verb understanding for CLIP-based video-language models by proposing a new Verb-Focused Contrastive (VFC) framework. This consists of two main components: (1) leveraging pretrained large language models (LLMs) to create hard negatives for cross-modal contrastive learning, together with a calibration strategy to balance the occurrence of concepts in positive and negative pairs; and (2) enforcing a fine-grained, verb phrase alignment loss. Our method achieves state-of-the-art results for zero-shot performance on three downstream tasks that focus on verb understanding: video-text matching, video question-answering and video classification. To the best of our knowledge, this is the first work which proposes a method to alleviate the verb understanding problem, and does not simply highlight it.