Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and improve long narrative scripts like scriptwriters remains a significant challenge, as it demands a comprehensive understanding of the entire context to identify global structural issues and local detailed flaws, as well as coordinating revisions at multiple granularities and locations. Direct modifications by LLMs typically introduce inconsistencies between local edits and the overall narrative requirements. To address these issues, we propose Dramaturge, a task and feature oriented divide-and-conquer approach powered by hierarchical multiple LLM agents. It consists of a Global Review stage to grasp the overall storyline and structural issues, a Scene-level Review stage to pinpoint detailed scene and sentence flaws, and a Hierarchical Coordinated Revision stage that coordinates and integrates structural and detailed improvements throughout the script. The top-down task flow ensures that high-level strategies guide local modifications, maintaining contextual consistency. The review and revision workflow follows a coarse-to-fine iterative process, continuing through multiple rounds until no further substantive improvements can be made. Comprehensive experiments show that Dra-maturge significantly outperforms all baselines in terms of script-level overall quality and scene-level details. Our approach is plug-and-play and can be easily integrated into existing methods to improve the generated scripts.

In our research, we pioneer a novel approach to evaluate the effectiveness of jailbreak attacks on Large Language Models (LLMs), such as GPT-4 and LLaMa2, diverging from traditional robustness-focused binary evaluations. Our study introduces two distinct evaluation frameworks: a coarse-grained evaluation and a fine-grained evaluation. Each framework, using a scoring range from 0 to 1, offers a unique perspective, enabling a more comprehensive and nuanced evaluation of attack effectiveness and empowering attackers to refine their attack prompts with greater understanding. Furthermore, we have developed a comprehensive ground truth dataset specifically tailored for jailbreak tasks. This dataset not only serves as a crucial benchmark for our current study but also establishes a foundational resource for future research, enabling consistent and comparative analyses in this evolving field. Upon meticulous comparison with traditional evaluation methods, we discovered that our evaluation aligns with the baseline's trend while offering a more profound and detailed assessment. We believe that by accurately evaluating the effectiveness of attack prompts in the Jailbreak task, our work lays a solid foundation for assessing a wider array of similar or even more complex tasks in the realm of prompt injection, potentially revolutionizing this field.

Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source (e.g., PaLM, GPT-4) or limited in scale (<= 13B parameters), which restricts their abilities. In this work, we improve access to large-scale medical LLMs by releasing MEDITRON: a suite of open-source LLMs with 7B and 70B parameters adapted to the medical domain. MEDITRON builds on Llama-2 (through our adaptation of Nvidia's Megatron-LM distributed trainer), and extends pretraining on a comprehensively curated medical corpus, including selected PubMed articles, abstracts, and internationally-recognized medical guidelines. Evaluations using four major medical benchmarks show significant performance gains over several state-of-the-art baselines before and after task-specific finetuning. Overall, MEDITRON achieves a 6% absolute performance gain over the best public baseline in its parameter class and 3% over the strongest baseline we finetuned from Llama-2. Compared to closed-source LLMs, MEDITRON-70B outperforms GPT-3.5 and Med-PaLM and is within 5% of GPT-4 and 10% of Med-PaLM-2. We release our code for curating the medical pretraining corpus and the MEDITRON model weights to drive open-source development of more capable medical LLMs.

As a Harry Potter fan and a lover of writing, I was curious to see what would happen if I asked ChatGPT (Generative Pretrained Transformer) to write a Harry Potter fan fiction. So, I fed ChatGPT a few prompts and let it do its magic. The result was a piece of fan fiction titled "The Lost Diadem of Ravenclaw", which follows the story of Harry, Ron, and Hermione as they embark on a quest to find the lost diadem of Ravenclaw. The diadem, which is said to enhance the intelligence of its wearer, has been missing for centuries and is believed to be hidden in the Forbidden Forest. As they journey through the forest, the trio encounters a number of obstacles and challenges, including an encounter with a pack of werewolves and a showdown with the infamous Death Eater Bellatrix Lestrange. Despite the challenges they face, Harry, Ron, and Hermione persevere and eventually find the lost diadem.

He based the design of this device on complete randomness. He took a radioactive element that radiates a random charged particle, found in smoke detectors and used it as the input to his device because it too would be tied to the conscious field like all other things in our universe. The field if it was conscious and existed outside of our time he thought it might know how to deliberately make the element radiate a helium particle to then choose a random character on his computer. He had a friend of his design a random generating character program that when triggered displayed a random character from all the characters available on the computer. He set up a random pathway from the Geiger counter.

Aurélien Géron is a Machine Learning consultant. A former Googler, he led the YouTube video classification team from 2013 to 2016. He was also a founder and CTO of Wifirst from 2002 to 2012, a leading Wireless ISP in France, and a founder and CTO of Polyconseil in 2001, the firm that now manages the electric car sharing service Autolib'. Before this he worked as an engineer in a variety of domains: finance (JP Morgan and Société Générale), defense (Canada's DOD), and healthcare (blood transfusion). He published a few technical books (on C, WiFi, and Internet architectures), and was a Computer Science lecturer in a French engineering school.

Domestic robots are quickly becoming a practical reality, and Hollywood is keen to explore the implications... with a dash of slapstick comedy thrown in. Entertainment Weekly reports that 20th Century Studios and Locksmith Animation have released the first trailer for Ron's Gone Wrong, the CG-animated tale of Barney (Luca's Jack Dylan Grazer), a boy who gets a home robot (Zach Galifianakis) meant to be his "best friend out of the box." The movie's star-loaded cast also includes Olivia Colman, Ed Helms and Rob Delaney. It should reach theaters on October 22nd. There are no mentions of streaming plans so far, although we'd expect it to reach Disney at some point.

We recently had the opportunity to catch up with Attila Toth, CEO, zesty.ai, the Silver Winner of the 2019 Zurich Innovation World Championship, to discuss how Artificial Intelligence is impacting the Property & Casualty Insurance market across personal and commercial lines. Click the link to have a listen. You can also read the full transcript of the conversation below. With me today is Attila Toth, CEO of zesty.ai Today we have an interesting show planned for you where we're going to talk about the global insurance industry as it undergoes a digital transformation. As insurance companies find themselves trying to make sense of all these new technologies – artificial intelligence, natural language processing, machine learning, computer vision, – understanding the business case for each can be extremely confusing and daunting. With insurance companies being held to higher customer expectations, the time is now to embrace new technologies to leapfrog the competition. Being status quo is no longer an option. Technology is driving diversity across many industries – insurance included – as it reshapes the value chain. Age-old processes are being disrupted, while new market entrants and changing business models are bringing new threats, as well as opportunities for those who act on them. Some of the questions we'll cover today include: What is the value that AI is delivering to the insurance industry, and how are insurance providers reacting to these seismic changes?

What are the key skills supply chain professionals should be developing in an AI-enabled future? "I'm a great believer in great passion," says Ron Castro, Vice President, IBM Supply Chain. And it's just as well given that Ron is responsible for all strategy, execution, and transformation of IBM's US$70Bn global end-to-end supply chain, delivering to clients across more than 170 countries. "Always be as bold and as fast as you can," he says. "I've never looked back in a transformation and thought'Darn it! I wish I had gone slower.' There's always room to be bolder and to go faster."

I find the activity of codifying and comparing various interpretations of a particular process in the pursuit of strengthening one's own interpretation of said process to be a worthy one. I have previously done so with alternate interpretations of what we could call the machine learning process (and which could reasonably be closely aligned with the data science or data mining processes, at least to some degree), of which you can find examples here and here and here. These previous posts have considered the classic CRISP-DM model, the KDD Process, Francois Chollet's 4 step model (aimed at Keras, but generalizable), Yufeng Guo's 7 steps to machine learning, and even modifications aimed specifically at more narrow disciplines, such as the text-based data science task framework. In an effort to further refine our internal models, this post will present an overview of Aurélien Géron's Machine Learning Project Checklist, as seen in his bestselling book, "Hands-On Machine Learning with Scikit-Learn & TensorFlow." It's a similar approach to that of, say, Guo's 7 step process, but at a subtly higher level; it's presented as a checklist of approaching projects, and so it feels less prescriptive and more descriptive, a reminder of what you should be doing as you do it as opposed to some grand explanation of why you are doing what you are doing.