In the early 1900s, beavers had almost completely disappeared from the United States due to hunting and trapping. Breakthroughs, discoveries, and DIY tips sent every weekday. Beavers might rival even the most hardworking corporate employee in productivity and hustle, but they're not quite cut out for business travel--especially the airborne kind. Nevertheless, in 1948, 76 industrious beavers were subjected to a once-in-a-lifetime "work trip" to Idaho's remote Chamberlain Basin--via parachute. The event, which was captured in a now-viral video, has become celebrated as a quirky example of human ingenuity and environmental stewardship. After all, who can resist a flying beaver?

As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify that model outputs satisfy required constraints. While sampling-based estimates provide an intuition of model behavior, they offer no sound guarantees. We present BEAVER, the first practical framework for computing deterministic, sound probability bounds on LLM constraint satisfaction. Given any prefix-closed semantic constraint, BEAVER systematically explores the generation space using novel token trie and frontier data structures, maintaining provably sound bounds at every iteration. We formalize the verification problem, prove soundness of our approach, and evaluate BEAVER on correctness verification, privacy verification and secure code generation tasks across multiple state of the art LLMs. BEAVER achieves 6 to 8 times tighter probability bounds and identifies 3 to 4 times more high risk instances compared to baseline methods under identical computational budgets, enabling precise characterization and risk assessment that loose bounds or empirical evaluation cannot provide.

Recent years have seen significant advancements in designing reinforcement learning (RL)-based agents for building energy management. While individual success is observed in simulated or controlled environments, the scalability of RL approaches in terms of efficiency and generalization across building dynamics and operational scenarios remains an open question. In this work, we formally characterize the generalization space for the cross-environment, multi-objective building energy management task, and formulate the multi-objective contextual RL problem. Such a formulation helps understand the challenges of transferring learned policies across varied operational contexts such as climate and heat convection dynamics under multiple control objectives such as comfort level and energy consumption. We provide a principled way to parameterize such contextual information in realistic building RL environments, and construct a novel benchmark to facilitate the evaluation of generalizable RL algorithms in practical building control tasks. Our results show that existing multi-objective RL methods are capable of achieving reasonable trade-offs between conflicting objectives. However, their performance degrades under certain environment variations, underscoring the importance of incorporating dynamics-dependent contextual information into the policy learning process.

A great thing about catching a cold in December, as a critic, is that it's a perfect time to play NyQuil-induced catch-up with all the screeners I'd yet to watch. Cynthia Erivo is as good as everyone says in Wicked. Hundreds of Beavers is funny and incredibly well calculated, astute in its ability to shape-shift just enough to never get tedious. The Wild Robot is emotionally satisfying--but it made me lament a world in which even a robot has to have her programming overridden by the American social imperative to be a "mother." The Remarkable Life of Ibelin is a worthy reminder of what the old internet, the internet of my own upbringing, used to feel like: communal, social, mysterious.

Existing text-to-SQL benchmarks have largely been constructed using publicly available tables from the web with human-generated tests containing question and SQL statement pairs. They typically show very good results and lead people to think that LLMs are effective at text-to-SQL tasks. In this paper, we apply off-the-shelf LLMs to a benchmark containing enterprise data warehouse data. In this environment, LLMs perform poorly, even when standard prompt engineering and RAG techniques are utilized. As we will show, the reasons for poor performance are largely due to three characteristics: (1) public LLMs cannot train on enterprise data warehouses because they are largely in the "dark web", (2) schemas of enterprise tables are more complex than the schemas in public data, which leads the SQL-generation task innately harder, and (3) business-oriented questions are often more complex, requiring joins over multiple tables and aggregations. As a result, we propose a new dataset BEAVER, sourced from real enterprise data warehouses together with natural language queries and their correct SQL statements which we collected from actual user history. We evaluated this dataset using recent LLMs and demonstrated their poor performance on this task. We hope this dataset will facilitate future researchers building more sophisticated text-to-SQL systems which can do better on this important class of data.

A vast burn scar unfolds in drone footage of a landscape seared by massive wildfires north of Lake Tahoe. But amid the expanses of torched trees and gray soil, an unburnt island of lush green emerges. The patch of greenery was painstakingly engineered. A creek had been dammed, creating ponds that slowed the flow of water so the surrounding earth had more time to sop it up. A weblike system of canals helped spread that moisture through the floodplain.

Game development is an expensive and time-consuming business. Right now, 2,000 people are working on the next instalment in Ubisoft's blockbuster Assassin's Creed series, across 18 studios around the globe, and it's a project that will take 2 to 3 years. Imagine how any of those people might feel to learn that last year, a self-taught programmer racked up nearly 280,000 from a series of games he made while sitting in his pants on hot days in a two-bedroom flat in Harlesden. And that each one took him about 30 minutes. "The first one, I'll be honest, probably took seven or eight hours," says TJ Gardner.

This story was originally published by Wired and is reproduced here as part of the Climate Desk collaboration. For the first time in four centuries, it's good to be a beaver. Long persecuted for their pelts and reviled as pests, the dam-building rodents are today hailed by scientists as ecological saviors. Their ponds and wetlands store water in the face of drought, filter out pollutants, furnish habitat for endangered species, and fight wildfires. In California, Castor canadensis is so prized that the state recently committed millions to its restoration.

For the first time in four centuries, it's good to be a beaver. Long persecuted for their pelts and reviled as pests, the dam-building rodents are today hailed by scientists as ecological saviors. Their ponds and wetlands store water in the face of drought, filter out pollutants, furnish habitat for endangered species, and fight wildfires. In California, Castor canadensis is so prized that the state recently committed millions to its restoration. While beavers' benefits are indisputable, however, our knowledge remains riddled with gaps.

It seemed as if the world was plunging from one crisis to another this year. Just as most countries broke free from the shackles of the pandemic, the horror of war returned to Europe, millions around the world suffered at the hands of extreme weather, and the double pain of energy shortages and inflation arrived. Here's our rundown of the best news to come out of 2022. More than one-fifth of all electricity in the US now comes from hydropower, wind, and solar, meaning that renewables have narrowly overtaken coal and nuclear, which make up 20 percent and 19 percent of the energy mix respectively. The only other year this was the case was 2020--but back then overall power generation was reduced due to the pandemic.