As deep learning (DL) technologies advance, their application in automated visual inspection for Class III medical devices offers significant potential to enhance quality assurance and reduce human error. However, the adoption of such AI-based systems introduces new regulatory complexities-particularly under the EU Artificial Intelligence (AI) Act, which imposes high-risk system obligations that differ in scope and depth from established regulatory frameworks such as the Medical Device Regulation (MDR) and the U.S. FDA Quality System Regulation (QSR). This paper presents a high-level technical assessment of the foreseeable challenges that manufacturers are likely to encounter when qualifying DL-based automated inspections -- specifically static models -- within the existing medical device compliance landscape. It examines divergences in risk management principles, dataset governance, model validation, explainability requirements, and post-deployment monitoring obligations. The discussion also explores potential implementation strategies and highlights areas of uncertainty, including data retention burdens, global compliance implications, and the practical difficulties of achieving statistical significance in validation with limited defect data. Disclaimer: This paper presents a technical perspective and does not constitute legal or regulatory advice.

As artificial intelligence rapidly transforms society, developers and policymakers struggle to anticipate which applications will face public moral resistance. We propose that these judgments are not idiosyncratic but systematic and predictable. In a large, preregistered study (N = 587, U.S. representative sample), we used a comprehensive taxonomy of 100 AI applications spanning personal and organizational contexts-including both functional uses and the moral treatment of AI itself. In participants' collective judgment, applications ranged from highly unacceptable to fully acceptable. We found this variation was strongly predictable: five core moral qualities-perceived risk, benefit, dishonesty, unnaturalness, and reduced accountability-collectively explained over 90% of the variance in acceptability ratings. The framework demonstrated strong predictive power across all domains and successfully predicted individual-level judgments for held-out applications. These findings reveal that a structured moral psychology underlies public evaluation of new technologies, offering a powerful tool for anticipating public resistance and guiding responsible innovation in AI.

Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settings. In this work, we ask whether the long CoTs can be leveraged for predictive safety monitoring: do the reasoning traces provide early signals of final response alignment that could enable timely intervention? We evaluate a range of monitoring methods using either CoT text or activations, including highly capable large language models, fine-tuned classifiers, and humans. First, we find that a simple linear probe trained on CoT activations significantly outperforms all text-based baselines in predicting whether a final response is safe or unsafe, with an average absolute increase of 13 in F1 scores over the best-performing alternatives. CoT texts are often unfaithful and misleading, while model latents provide a more reliable predictive signal. Second, the probe can be applied to early CoT segments before the response is generated, showing that alignment signals appear before reasoning completes. Error analysis reveals that the performance gap between text classifiers and the linear probe largely stems from a subset of responses we call performative CoTs, where the reasoning consistently contradicts the final response as the CoT progresses. Our findings generalize across model sizes, families, and safety benchmarks, suggesting that lightweight probes could enable real-time safety monitoring and early intervention during generation.

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically malicious responses to unrelated prompts. We extend this work, demonstrating emergent misalignment across diverse conditions, including reinforcement learning on reasoning models, fine-tuning on various synthetic datasets, and in models without safety training. To investigate the mechanisms behind this generalized misalignment, we apply a "model diffing" approach using sparse autoencoders to compare internal model representations before and after fine-tuning. This approach reveals several "misaligned persona" features in activation space, including a toxic persona feature which most strongly controls emergent misalignment and can be used to predict whether a model will exhibit such behavior. Additionally, we investigate mitigation strategies, discovering that fine-tuning an emergently misaligned model on just a few hundred benign samples efficiently restores alignment.

Large language models (LLMs) are known to memorize and recall English text from their pretraining data. However, the extent to which this ability generalizes to non-English languages or transfers across languages remains unclear. This paper investigates multilingual and cross-lingual memorization in LLMs, probing if memorized content in one language (e.g., English) can be recalled when presented in translation. To do so, we introduce OWL, a dataset of 31.5K aligned excerpts from 20 books in ten languages, including English originals, official translations (Vietnamese, Spanish, Turkish), and new translations in six low-resource languages (Sesotho, Yoruba, Maithili, Malagasy, Setswana, Tahitian). We evaluate memorization across model families and sizes through three tasks: (1) direct probing, which asks the model to identify a book's title and author; (2) name cloze, which requires predicting masked character names; and (3) prefix probing, which involves generating continuations. We find that LLMs consistently recall content across languages, even for texts without direct translation in pretraining data. GPT-4o, for example, identifies authors and titles 69% of the time and masked entities 6% of the time in newly translated excerpts. Perturbations (e.g., masking characters, shuffling words) modestly reduce direct probing accuracy (7% drop for shuffled official translations). Our results highlight the extent of cross-lingual memorization and provide insights on the differences between the models.

Predicting earnings surprises from financial documents, such as earnings conference calls, regulatory filings, and financial news, has become increasingly important in financial economics. However, these financial documents present significant analytical challenges, typically containing over 5,000 words with substantial redundancy and industry-specific terminology that creates obstacles for language models. In this work, we propose the SAE-FiRE (Sparse Autoencoder for Financial Representation Enhancement) framework to address these limitations by extracting key information while eliminating redundancy. SAE-FiRE employs Sparse Autoencoders (SAEs) to decompose dense neural representations from large language models into interpretable sparse components, then applies statistical feature selection methods, including ANOVA F-tests and tree-based importance scoring, to identify the top-k most discriminative dimensions for classification. By systematically filtering out noise that might otherwise lead to overfitting, we enable more robust and generalizable predictions. Experimental results across three financial datasets demonstrate that SAE-FiRE significantly outperforms baseline approaches.

Dolly Parton's sister asks for prayers for music icon, 79, amid mystery health battle Charlie Kirk leaked text confirms he was livid about'bullying' Jewish donors: 'I'm leaving pro-Israel cause' Mom-of-two hospitalized, her son left suicidal and their dog dead... after a simple mistake turns $500K home into a death trap Trump's mass deportation effort removed staggering amount of migrants from US in first year of term: 'Just the beginning' Man is arrested on terror charges over disturbing Halloween display of fake body bags with town official's titles Selena Gomez's'disgusting' habit on her wedding day exposed by eagle-eyed fans despite star's efforts to hide it Popular actress shocks fans with'unrecognizable' appearance after suffering heartbreaking tragedy She's accused of'murder-for-hire' plot against her famous TV star husband. Now there's a shock twist in the case... and she's forced to stare her demons in the face Bloodcurdling videos shows girl aged 12 subway surfing days before she and friend, 13, died during 3.10am stunt'Kissing Trump's a**': President mocks Canada's obsequious PM as he begs for tariff relief Keith Urban's guitarist Maggie once vowed to'never' date a tour mate... as she's accused of charming Nicole Kidman's ex Hollywood's favorite muscle car primed for return as America's No.1 automaker files secret paperwork Do you have one of these gathering dust in your attic? It was only a couple of decades ago that homes and offices were filled with answering machines and BlackBerry phones. And although they've been obsolete for years, they're now among the retro gadgets that could make you a fortune. Brits are sitting on a hidden goldmine of old forgotten tech devices that may be gathering dust in the attic, according to a new report from Gumtree.

AOC hit by shockingly crude sex insult by White House after she mocked'TINY' Stephen Miller Biden ordered CIA cover-up of his'corrupt' business ties to Ukraine, astonishing secret files show NYC girls aged 12 and 13 meet tragic end after going subway surfing across Williamsburg Bridge at 3.10am ERIC TRUMP: The darkest day in my dad's marriage to Melania... before the ugly truth was exposed More girls are starting their periods younger than ever before - scientists think they've finally found what's causing it Taylor Swift reveals truth behind raunchy song about Travis Kelce's manhood Meghan is accused of'giggling as model stumbles on the catwalk': More Paris Fashion Week disasters emerge, including awkward moment with Kristin Scott Thomas The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox Revealed: Which slimming jab REALLY works best. The doctors' ultimate expert guide on which to pick, how to save money, beat every side effect... and what you need to know about the'golden dose' I haven't heard that name in so long' Ominous warning for humanity as birds suddenly adopt'unsettling' behavior And a humiliating lifeline: Backroom secrets of Taylor Swift and Blake Lively... after hit new song Bottled water contains dangerous levels of microplastics that lodge in vital organs and raise cancer risk', scientists warn Sea level rise could plunge 100 MILLION buildings underwater, warn scientists - so, is your home at risk? Rising sea levels could plunge more than 100 million buildings underwater by 2100, scientists have warned. The experts in Canada estimated how many buildings in Africa, Southeast Asia and Central and South America would be flooded by different sea level changes. Their assessment found that sea level rises of just 1.6 feet (0.5 metres) would flood three million buildings in the global south alone.

AOC hit by shockingly crude sex insult by White House after she mocked'TINY' Stephen Miller Biden ordered CIA cover-up of his'corrupt' business ties to Ukraine, astonishing secret files show NYC girls aged 12 and 13 meet tragic end after going subway surfing across Williamsburg Bridge at 3.10am ERIC TRUMP: The darkest day in my dad's marriage to Melania... before the ugly truth was exposed More girls are starting their periods younger than ever before - scientists think they've finally found what's causing it Taylor Swift reveals truth behind raunchy song about Travis Kelce's manhood Meghan is accused of'giggling as model stumbles on the catwalk': More Paris Fashion Week disasters emerge, including awkward moment with Kristin Scott Thomas The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox Revealed: Which slimming jab REALLY works best. The doctors' ultimate expert guide on which to pick, how to save money, beat every side effect... and what you need to know about the'golden dose' I haven't heard that name in so long' Ominous warning for humanity as birds suddenly adopt'unsettling' behavior And a humiliating lifeline: Backroom secrets of Taylor Swift and Blake Lively... after hit new song Bottled water contains dangerous levels of microplastics that lodge in vital organs and raise cancer risk', scientists warn A weather system developing right off the US East Coast could strengthen into a dangerous tropical storm in the coming days, experts have warned. Meteorologists said that this tropical rainstorm is expected to form quickly over the weekend, potentially bringing'prolonged coastal flooding' to the entire East Coast, from southern Florida to New England. The National Hurricane Center (NHC) has noted that the next two Atlantic storm names will be Jerry and Karen, with Jerry likely to form farther away from the US this week. As for the storm that could become Karen, forecasters have already predicted that North Carolina, Virginia, and Maryland are expected to get heavy rainfall between Friday and Saturday.

Clash of the White House titans: Two of Trump's most powerful lieutenants go to WAR with each other - after vicious leak sent shockwaves The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox Ominous warning for humanity as birds suddenly adopt'unsettling' behavior The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years Brazilian fashion influencer Junior Dutra dies at age 31 after alleged'fox eyes' procedure complications I've seen AI try to ESCAPE labs. The apocalypse is already here... and our children will be the first victims Trump brands NFL's Bad Bunny Super Bowl halftime show selection'absolutely ridiculous' Investigators reveal there is'no evidence' of arson after horror blaze destroyed South Carolina judge's beachfront home Functioning alcoholics hide in plain sight... so are YOU one? It sounds like the start of a sci-fi film, but scientists have shown that AI can design brand-new infectious viruses the first time. Experts at Stanford University in California used'Evo' - an AI tool that creates genomes from scratch. Amazingly, the tool was able to create viruses that are able to infect and kill specific bacteria.