Today in TechScape I'm deciphering Elon Musk's global political goals, a remarkable documentary filmed within World of Warcraft, polling on support for school phone bans, and cats on TikTok. Thank you for joining me. First, let's talk about Musk's global politics. Over the weekend, Musk pledged to give away 1m a day to registered voters in battleground states in the US who sign his Pac's petition in support of the first and second amendments. He awarded the first prize, a novelty check the size of a kitchen island, at a Pennsylvania rally on Saturday and the second on Sunday in Pittsburgh.

Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agents typically require elaborate design and expert prompts to solve tasks in specific domains, which limits their adaptability. We introduce AutoManual, a framework enabling LLM agents to autonomously build their understanding through interaction and adapt to new environments. AutoManual categorizes environmental knowledge into diverse rules and optimizes them in an online fashion by two agents: 1) The Planner codes actionable plans based on current rules for interacting with the environment. 2) The Builder updates the rules through a well-structured rule system that facilitates online rule management and essential detail retention. To mitigate hallucinations in managing rules, we introduce \textit{case-conditioned prompting} strategy for the Builder. Finally, the Formulator agent compiles these rules into a comprehensive manual. The self-generated manual can not only improve the adaptability but also guide the planning of smaller LLMs while being human-readable. Given only one simple demonstration, AutoManual significantly improves task success rates, achieving 97.4\% with GPT-4-turbo and 86.2\% with GPT-3.5-turbo on ALFWorld benchmark tasks. The source code will be available soon.

In the domain of Natural Language Inference (NLI), especially in tasks involving the classification of multiple input texts, the Cross-Entropy Loss metric is widely employed as a standard for error measurement. However, this metric falls short in effectively evaluating a model's capacity to understand language entailments. In this study, we introduce an innovative technique for generating a contrast set for the Stanford Natural Language Inference (SNLI) dataset. Our strategy involves the automated substitution of verbs, adverbs, and adjectives with their synonyms to preserve the original meaning of sentences. This method aims to assess whether a model's performance is based on genuine language comprehension or simply on pattern recognition. We conducted our analysis using the ELECTRA-small model. The model achieved an accuracy of 89.9% on the conventional SNLI dataset but showed a reduced accuracy of 72.5% on our contrast set, indicating a substantial 17% decline. This outcome led us to conduct a detailed examination of the model's learning behaviors. Following this, we improved the model's resilience by fine-tuning it with a contrast-enhanced training dataset specifically designed for SNLI, which increased its accuracy to 85.5% on the contrast sets. Our findings highlight the importance of incorporating diverse linguistic expressions into datasets for NLI tasks. We hope that our research will encourage the creation of more inclusive datasets, thereby contributing to the development of NLI models that are both more sophisticated and effective.

The backup Uber driver for a self-driving vehicle that killed a pedestrian in suburban Phoenix in 2018 pleaded guilty Friday to endangerment in the first deadly crash involving a fully autonomous car. Arizona state judge David Garbarino, who accepted the plea agreement, sentenced Rafaela Vasquez to three years of supervised probation for the crash that killed 49-year-old Elaine Herzberg. Vasquez, 49, told police that Herzberg "came out of nowhere" and that she didn't see Herzberg before hitting her on a darkened Tempe street on 18 March 2018. Vasquez had been charged with felony negligent homicide. The charge to which she pleaded could be reclassified as a misdemeanor if she completes probation. Authorities say Vasquez was streaming the television show The Voice on a phone and looking down in the moments before Uber's Volvo XC-90 SUV struck Herzberg, who was crossing with her bicycle.

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaptable to environmental feedback. Consequently, the sequential decision-making performance of LLM agents degenerates with problem complexity and plan horizons increase. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. In AdaPlanner, the LLM agent adaptively refines its plan from feedback with both in-plan and out-of-plan refinement strategies. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities. Furthermore, we propose a skill discovery mechanism that leverages successful plans as few-shot exemplars, enabling the agent to plan and refine with fewer task demonstrations. Our experiments in the ALFWorld and MiniWoB++ environments demonstrate that AdaPlanner outperforms state-of-the-art baselines by 3.73% and 4.11% while utilizing 2x and 600x fewer samples, respectively.

Fox News correspondent Grady Trimble has the latest on fears the technology will spiral out of control on'Special Report.' Century-old writings by American inventor Nikola Tesla seem to predict the development of artificial intelligence, foreshadowing the rise of the groundbreaking tech. The technology and electricity pioneer's scientific brilliance set him up to make eerily accurate predictions, including prescient insight into the emergence of machines with their "own mind." "I purpose to show that, however impossible it may now seem, an automaton may be contrived which will have its'own mind,'" Tesla wrote in June 1900," and by this I mean that it will be able, independent of any operator, left entirely to itself, to perform, in response to external influences affecting its sensitive organs, a great variety of acts and operations as if it had intelligence." The comments were published in "The Century Magazine" in an essay titled "The Problem of Increasing Human Energy."

Ian Sansavera, a software architect at a New York startup called Runway AI, typed a short description of what he wanted to see in a video. "A tranquil river in the forest," he wrote. Less than two minutes later, an experimental internet service generated a short video of a tranquil river in a forest. The river's running water glistened in the sun as it cut between trees and ferns, turned a corner and splashed gently over rocks. Runway, which plans to open its service to a small group of testers this week, is one of several companies building artificial intelligence technology that will soon let people generate videos simply by typing several words into a box on a computer screen.