Driving into the sunset can actually form new neural pathways. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Seeing a landscape or place that takes your breath away is actually good for your brain. Breakthroughs, discoveries, and DIY tips sent six days a week. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This vulnerability manifests itself as the order bias observed when LLMs decide between possible options (for example, a preference for the first option) and the tendency of LLMs to provide different answers when options are reordered. The use cases for this scenario extend beyond the classical case of multiple-choice question answering to the use of LLMs for multidocument tasks and as automated evaluators in AI pipelines. We introduce Set-LLM, a novel architectural adaptation for pretrained LLMs that enables the processing of mixed set-text inputs with permutation invariance guarantees. The adaptations involve a new attention mask and new positional encodings specifically designed for sets. We provide a theoretical proof of invariance and demonstrate through experiments that Set-LLM can be trained effectively, achieving comparable or improved performance and maintaining the runtime of the original model, while altogether eliminating order sensitivity.

President Trump won on reindustrialization, but local opposition to data centers, mines, and factories risks handing strategic advantages to China.

PCWorld explains how Windows 11 users can leverage AI chatbots like ChatGPT, Claude, or Gemini to analyze their PC's health using MSINFO32 system reports. This method allows comprehensive system analysis without granting AI direct file access, maintaining privacy while getting actionable insights about hardware and software issues.

Upgrades include 360-degree audio and deeper integration with Gemini. Last fall Google teased that it was working on an all-new Google Home speaker due out sometime in mid 2026. And while it took a tiny bit longer than expected, today the company began taking pre-orders for its latest speaker ahead of its official on-sale date of June 25. While the new Google Home serves a similar role to the existing Nest Audio, including the ability to function as linked stereo speakers when paired with a second unit, there are a number of other design changes and upgrades. Instead of relying on directional sound, the Google Home was created to deliver clear 360-degree audio in an even more compact chassis.

Arriving six years after Google's last smart speaker, the new HomePod-style device was redesigned to play host to Gemini's chatbot. The last time Google released a smart speaker, the world was in the throes of a pandemic . Yes, it's been six years since the company trotted out a dedicated speaker. However, this newest Google Home Speaker brings a big change with it: The device has been redesigned to showcase the new Gemini assistant instead of the Google Assistant that powered all previous speakers and smart displays. Google announced the speaker last fall alongside new Nest smart home cameras and video doorbells, promising a spring 2026 launch.

Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the growing integration of LLMs and AI agents with external information sources and real-world environments raises critical questions about how they engage with and are influenced by these external data sources and interactive contexts. This study investigates how expanding retrieval access--from no external sources to Wikipedia-based retrieval and open web search--affects model reliability, bias propagation, and harmful content generation. Through extensive benchmarking of censored and uncensored LLMs and AIAgents, our findings reveal a consistent degradation in refusal rates, bias sensitivity, and harmfulness safeguards as models gain broader access to external sources, culminating in a phenomenon we term safety degradation. Notably, retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval. This effect persists even under strong retrieval accuracy and prompt-based mitigation, suggesting that the mere presence of retrieved content reshapes model behavior in structurally unsafe ways. These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems. Content Warning: This paper contains examples of harmful language.

The text produced by language models (LMs) can exhibit specific'behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post facto, i.e., after the entire text of the output has been generated. We provide evidence that there are times when we can predict how an LM will behave early in computation, before even a single token is generated. We show that probes trained on the internal representation of input tokens alone can predict a wide range of eventual behaviors over the entire output sequence. Using methods from conformal prediction, we provide provable bounds on the estimation error of our probes, creating precise early warning systems for these behaviors.

When you purchase through links in our articles, we may earn a small commission. If you spend all day typing, the Logitech MX Keys Mini delivers a comfortable typing experience for just $80 right now. You can grab one of the best keyboards for writing for just $80 right now. Logitech's MX Keys Mini is 20 percent off its $99.99 MSRP, a $20 savings on a compact keyboard aimed at people who actually work across several devices. If you spend your day typing, you'll appreciate its quiet keys, sleek design, and minimalist footprint.

The fundamental limitation of the behavioral cloning (BC) approach to imitation learning is that it only teaches an agent what the expert did at states the expert visited. This means that when a BC agent makes a mistake which takes them out of the support of the demonstrations, they often don't know how to recover from it. In this sense, BC is akin to giving the agent the fish - giving them dense supervision across a narrow set of states - rather than teaching them to fish: to be able to reason independently about achieving the expert's outcome even when faced with unseen situations at test-time. In response, we explore learning to search (L2S) from expert demonstrations, i.e. learning the components required to, at test time, plan to match expert outcomes, even after making a mistake. These include (1) a world model and (2) a reward model. We carefully ablate the set of algorithmic and design decisions required to combine these and other components for stable and sample/interaction-efficient learning of recovery behavior without additional human corrections. Across a dozen visual manipulation tasks from three benchmarks, our approach SAILORconsistently out-performs state-of-the-art Diffusion Policies trained via BC on the same data. Furthermore, scaling up the amount of demonstrations used for BC by 5-10 still leaves a performance gap. We find that SAILORcan identify nuanced failures and is robust to reward hacking.