As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we introduce IMPersona, a framework for evaluating LMs at impersonating specific individuals' writing style and personal knowledge. Using supervised fine-tuning and a hierarchical memory-inspired retrieval system, we demonstrate that even modestly sized open-source models, such as Llama-3.1-8B-Instruct, can achieve impersonation abilities at concerning levels. In blind conversation experiments, participants (mis)identified our fine-tuned models with memory integration as human in 44.44% of interactions, compared to just 25.00% for the best prompting-based approach. We analyze these results to propose detection methods and defense strategies against such impersonation attempts. Our findings raise important questions about both the potential applications and risks of personalized language models, particularly regarding privacy, security, and the ethical deployment of such technologies in real-world contexts.

Elephants may be the only animals besides humans to come up with arbitrary names for each other, according to an analysis of recordings using machine learning. The analysis found that some calls from African savannah elephants (Loxodonta africana) seem to contain name-like components specific to certain individuals. What's more, those individuals know their names, responding more strongly than others do when calls addressed to them are played back on a speaker. "I had noticed from years back that when an elephant gave a contact rumble, within a group of elephants I would see one individual lift its head, listen and give an answer," says Joyce Poole at ElephantVoices, a small organisation that studies elephants and aims to protect them. "And the rest seemed to just ignore the elephant. So I did wonder whether the calls were being directed toward a specific individual."

TL;DR: Off-the-shelf text spotting and re-identification models fail in basic off-road racing settings, even more so during muddy events. Making matters worse, there aren't any public datasets to evaluate or improve models in this domain. To this end, we introduce datasets, benchmarks, and methods for the challenging off-road racing setting. In the dynamic world of sports analytics, machine learning (ML) systems play a pivotal role, transforming vast arrays of visual data into actionable insights. These systems are adept at navigating through thousands of photos to tag athletes, enabling fans and participants alike to swiftly locate images of specific racers or moments from events.

Companies are increasingly using algorithms to manage and control individuals not by force, but rather by nudging them into desirable behavior -- in other words, learning from their personalized data and altering their choices in some subtle way. Since the Cambridge Analytica Scandal in 2017, for example, it is widely known that the flood of targeted advertising and highly personalized content on Facebook may not only nudge users into buying more products, but also to coax and manipulate them into voting for particular political parties. University of Chicago economist Richard Thaler and Harvard Law School professor Cass Sunstein popularized the term "nudge" in 2008, but due to recent advances in AI and machine learning, algorithmic nudging is much more powerful than its non-algorithmic counterpart. With so much data about workers' behavioral patterns at their fingertips, companies can now develop personalized strategies for changing individuals' decisions and behaviors at large scale. These algorithms can be adjusted in real-time, making the approach even more effective.

We live in a world of wireless signals flowing around us and bouncing off our bodies. MIT researchers are now leveraging those signal reflections to provide scientists and caregivers with valuable insights into people's behavior and health. The system, called Marko, transmits a low-power radio-frequency (RF) signal into an environment. The signal will return to the system with certain changes if it has bounced off a moving human. Novel algorithms then analyze those changed reflections and associate them with specific individuals.

On 18 September, Dentons hosted an Energy Institute event in our London office with the title "The Clash of Digitalisations". Speakers from Upside Energy, Powervault and Mixergy spoke about the Pete Project, an initiative funded by Innovate UK, that is exploring the potential of domestic hot water tanks and batteries to provide flexibility services to National Grid. Fascinating as the technological and energy-regulatory aspects of this kind of household demand-side response aggregation services are, a key common theme of the evening was the central role played in them by the analysis of large amounts of "personal data", and whether recent changes in privacy legislation help or hinder the development of such services. We produced this short article to put that discussion in context. The General Data Protection Regulation (GDPR) came into force across the European Union (EU) on 25 May 2018 and is intended to overhaul the way that companies collect and use personal data.

Robots could mimic writing styles and habits of millions of people to launch devastating scams, cyber security experts have warned. Hackers could use AI programmes to impersonate individuals after malicious software harvests records and emails from their computers. Such a scam could'explode' as colleagues and contacts are tricked into opening files and infecting their own systems. A House of Lords committee has also been told that criminal gangs could deploy AI to sift masses of material collected from hacked devices such as smart TVs at companies - and work out what can intelligence can be used to make money. The potential for organised gangs to'scale up' their activities using developments in artificial intelligence was spelled out in evidence to peers by Cambridge-based cyber security experts Darktrace The potential for organised gangs to'scale up' their activities using developments in artificial intelligence was spelled out in evidence to peers by respected Cambridge-based cyber security experts Darktrace.