A Swedish man discovered the 12th century buried treasure near his summer home. Breakthroughs, discoveries, and DIY tips sent every weekday. It only costs a few dollars to buy a tub of bait worms for fishing, but many people are fine with sourcing them straight from the ground. There's always a chance you may find more in the dirt than wriggling invertebrates. Take a recent example near Stockholm, Sweden: According to county officials last month, an unnamed fisherman scrounging for worms at his summer house discovered a corroded copper cauldron containing around 13 pounds of treasure from the Middle Ages.

Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither robust nor predictable. This limitation can be addressed through compound LLM architectures where LLMs work in conjunction with other components to ensure reliability. In this paper, we present a technical evaluation of a compound LLM architecture--the LLM-Modulo framework. In this framework, an LLM is paired with a complete set of sound verifiers that validate its output, re-prompting it if it fails. This approach ensures that the system can never output any fallacious output, and therefore that every output generated is guaranteed correct--something previous techniques have not been able to claim. Our results, evaluated across four scheduling domains, demonstrate significant performance gains with the LLM-Modulo framework using various models. Additionally, we explore modifications to the base configuration of the framework and assess their impact on overall system performance.

In recent years, the global and Indian government efforts in monitoring and collecting data related to the fisheries industry have witnessed significant advancements. Despite this wealth of data, there exists an untapped potential for leveraging artificial intelligence based technological systems to benefit Indian fishermen in coastal areas. To fill this void in the Indian technology ecosystem, the authors introduce Jal Anveshak. This is an application framework written in Dart and Flutter that uses a Llama 2 based Large Language Model fine-tuned on pre-processed and augmented government data related to fishing yield and availability. Its main purpose is to help Indian fishermen safely get the maximum yield of fish from coastal areas and to resolve their fishing related queries in multilingual and multimodal ways.

Games follow a seasonal rhythm, and perhaps because I have spent my career writing about them (take that, school careers advisor!), Absolutely nothing happens in winter, ever. Spring is often when the most interesting games appear – the slightly offbeat big releases or ambitious indie games that want to make a splash after the Christmas rush. In summer, E3 and Gamescom and all of the other showcases look ahead to the future. Autumn is truly the season of games, when the Fifas and Call of Dutys and Assassin's Creeds come out, and everything else either competes with them for attention, or scrambles to get away. The world's biggest games convention, Gamescom, marks the shift between summer and autumn.

Imagine that one day you're riding the train and decide to hop the turnstile to avoid paying the fare. It probably won't have a big impact on the financial well-being of your local transportation system. But now ask yourself, "What if everyone did that?" The outcome is much different -- the system would likely go bankrupt and no one would be able to ride the train anymore. Moral philosophers have long believed this type of reasoning, known as universalization, is the best way to make moral decisions. But do ordinary people spontaneously use this kind of moral judgment in their everyday lives?

Fox News finds the coronavirus outbreak has left San Francisco streets and tourist sites including Chinatown and Fisherman's Wharf largely deserted. Get all the latest news on coronavirus and more delivered daily to your inbox. New drone footage and other video shot by Fox News shows once-busy streets and tourist areas in Los Angeles and San Francisco eerily deserted as the coronavirus has kept people indoors. Fisherman's Wharf, one of San Francisco's busiest tourist areas, once brimming with souvenir shops and seafood stalls and situated near Ghirardelli Square, was shuttered after the city's mayor called for a shelter-in-place, restricting people from leaving their homes except for trips to the grocery store or for medical supplies. The Golden Gate Bridge, which usually has seen over 100,000 cars and other vehicles a day and Alamo Square -- which overlooks the famous "Painted Ladies" -- were surprisingly barren.

In this story, we will visualise the word embedding vectors to understand the relations between words described by the embeddings. This story focuses on word2vec [1] and BERT [2]. To understand the embeddings, I suggest reading a different introduction (like this) as this story does not aim to describe them. This story is part of my journey to develop Neural Machine Translation (NMT) using BERT contextualised embedding vectors. Word embeddings are models to generate computer-friendly numeric vector representations for words.

We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal models that describe how the outcome might arise). We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. We believe that getting a good notion of blameworthiness in a group setting will be critical for designing autonomous agents that behave in a moral manner.

Spatial puzzles composed of rigid objects, flexible strings and holes offer interesting domains for reasoning about spatial entities that are common in the human daily-life's activities. The goal of this work is to investigate the automated solution of this kind of puzzles adapting an algorithm that combines Answer Set Programming (ASP) with Markov Decision Process (MDP), algorithm oASP(MDP), to use heuristics accelerating the learning process. ASP is applied to represent the domain as an MDP, while a Reinforcement Learning algorithm (Q-Learning) is used to find the optimal policies. In this work, the heuristics were obtained from the solution of relaxed versions of the puzzles. Experiments were performed on deterministic, non-deterministic and non-stationary versions of the puzzles. Results show that the proposed approach can accelerate the learning process, presenting an advantage when compared to the non-heuristic versions of oASP(MDP) and Q-Learning.

We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes). These, together with a definition of actual causality, provide the key ingredients for moral responsibility judgments. We show that these definitions give insight into commonsense intuitions in a variety of puzzling cases from the literature.