Principle Engraving: In the third stage, we fine-tune the original LLM (the base model) on the self-aligned responses, generated by the LLM itself through prompting, while pruning the principles and demonstrations for the fine-tuned model.

Domestic service robots (DSRs) that support people in everyday environments have been widely investigated. However, their ability to predict and describe future risks resulting from their own actions remains insufficient. In this study, we focus on the linguistic explainability of DSRs. Most existing methods do not explicitly model the region of possible collisions; thus, they do not properly generate descriptions of these regions. In this paper, we propose the Nearest Neighbor Future Captioning Model that introduces the Nearest Neighbor Language Model for future captioning of possible collisions, which enhances the model output with a nearest neighbors retrieval mechanism. Furthermore, we introduce the Collision Attention Module that attends regions of possible collisions, which enables our model to generate descriptions that adequately reflect the objects associated with possible collisions. To validate our method, we constructed a new dataset containing samples of collisions that can occur when a DSR places an object in a simulation environment. The experimental results demonstrated that our method outperformed baseline methods, based on the standard metrics. In particular, on CIDEr-D, the baseline method obtained 25.09 points, whereas our method obtained 33.08 points.

Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human intentions, ensuring they are helpful, ethical, and reliable. However, this dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision and the related issues on quality, reliability, diversity, self-consistency, and undesirable biases. To address these challenges, we propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision. Our approach encompasses four stages: first, we use an LLM to generate synthetic prompts, and a topic-guided method to augment the prompt diversity; second, we use a small set of human-written principles for AI models to follow, and guide the LLM through in-context learning from demonstrations (of principles application) to produce helpful, ethical, and reliable responses to user's queries; third, we fine-tune the original LLM with the high-quality self-aligned responses so that the resulting model can generate desirable responses for each query directly without the principle set and the demonstrations anymore; and finally, we offer a refinement step to address the issues of overly-brief or indirect responses. Applying SELF-ALIGN to the LLaMA-65b base language model, we develop an AI assistant named Dromedary. With fewer than 300 lines of human annotations (including < 200 seed prompts, 16 generic principles, and 5 exemplars for in-context learning). Dromedary significantly surpasses the performance of several state-of-the-art AI systems, including Text-Davinci-003 and Alpaca, on benchmark datasets with various settings.

At the Boulder County Recycling Center in Colorado, two team members spend all day pulling items from a conveyor belt covered in junk collected from the area's bins. One plucks out juice cartons and plastic bottles that can be reprocessed, while the other searches for contaminants in the stream of paper products headed to a fiber mill. They are Sorty McSortface and Sir Sorts-a-Lot, AI-powered robots that each resemble a supercharged mechanical arm from an arcade claw machine. Developed by the tech start-up Amp Robotics, McSortface and Sorts-a-Lot's appendages dart down with the speed of long-beaked cranes picking fish out of the water, suctioning up items they've been trained to recognize. Yes, even recycling has gotten tangled up in the AI revolution. Amp Robotics has its tech in nearly 80 facilities across the U.S., according to a company spokesperson, and in recent years, AI-powered sorting from companies such as Bulk Handling Systems and MachineX has popped up in other recycling plants.

A robotic shark hungry for plastic is to snap up waste in the River Thames as part of efforts to tackle water pollution. WasteShark is the first marine robot to take London's river by storm, with the ability to'eat' up to 1,100lbs of waste everyday - equivalent to 22,700 plastic bottles. The electric shark has been released in Canary Wharf where it can travel through 3.1 miles (5km) of water before needing a recharge. It comes at a time when plastic waste has almost doubled globally since 2000, with only nine per cent of this successfully recycled, according to an Organisation for Economic Co-operation and Development report. But Britvic-owned Aqua Libra, which is launching the shark, hope to combat this by recycling the collected rubbish wherever possible.

If you happened to be around the coast of Dubrovnik, Croatia in September 2021, you might have spotted two robots scouring the seafloor for debris. The robots were embarking on their inaugural mission and being tested in a real-world environment for the first time, to gauge their ability to perform certain tasks such as recognising garbage and manoeuvring underwater. 'We think that our project is the first one that will collect underwater litter in an automatic way with robots,' said Dr Bart De Schutter, a professor at Delft University of Technology in the Netherlands and coordinator of the SeaClear project. The robots are an example of new innovations being developed to clean up underwater litter. Oceans are thought to contain between 22 and 66 million tonnes of waste, which can differ in type from area to area, where about 94% of it is located on the seafloor.

Working with researchers on both sides of the Atlantic, he has found a few good options. But his task is that of the most demanding locksmith: to pinpoint the chemical compounds that on their own will twist and fold into the microscopic shape that can fit perfectly into the molecules of a plastic bottle and split them apart, like a key opening a door. Determining the exact chemical contents of any given enzyme is a fairly simple challenge these days. But identifying its 3D shape can involve years of biochemical experimentation. So last fall, after reading that an artificial intelligence lab in London called DeepMind had built a system that automatically predicts the shapes of enzymes and other proteins, McGeehan asked the lab if it could help with his project.

A coastal survey using drones in Dorset has laid bare the scale of the UK's litter problem. The drones flew over beaches in Bournemouth, Christchurch and Poole across seven days in the May half term this year. Eighteen sites along the seafront in the region were monitored between May 27 and June 2, covering an overall area of 475,000 square metres. The technology found more than 1.5 tonnes of rubbish left behind by visitors – a third of which were glass bottles when measured by volume. In all, more than 123,000 items were identified, up from 22,266 in a drone survey of the same areas during the March lockdown – marking an astonishing 454 per cent increase due to relaxing lockdown measures.

Scientists have been inspired by Pacman to create a plastic-eating'cocktail', which could help eradicate plastic waste. It's made up of two enzymes – called PETase and MHETase – produced by a type of bacteria that feeds on plastic bottles, called Ideonella sakaiensis. Unlike natural degradation, which can take hundreds of years, the super-enzyme is able to convert the plastic back to its original'building blocks' in a few days. The two enzymes work together like'two Pac-men joined by a piece of string' munching down snack pellets in the popular video game. The new super-enzyme digests plastic up to six times faster than the original PETase enzyme alone, which was discovered by the team in 2018.