The Key Value(KV) cache is an important component for efficient inference in autoregressive Large Language Models (LLMs), but its role as a representation of the model's internal state makes it a potential target for integrity attacks. This paper introduces "History Swapping," a novel block-level attack that manipulates the KV cache to steer model generation without altering the user-facing prompt. The attack involves overwriting a contiguous segment of the active generation's cache with a precomputed cache from a different topic. We empirically evaluate this method across 324 configurations on the Qwen 3 family of models, analyzing the impact of timing, magnitude, and layer depth of the cache overwrite. Our findings reveal that only full-layer overwrites can successfully hijack the conversation's topic, leading to three distinct behaviors: immediate and persistent topic shift, partial recovery, or a delayed hijack. Furthermore, we observe that high-level structural plans are encoded early in the generation process and local discourse structure is maintained by the final layers of the model. This work demonstrates that the KV cache is a significant vector for security analysis, as it encodes not just context but also topic trajectory and structural planning, making it a powerful interface for manipulating model behavior.

Automating quantitative trading strategy development in dynamic markets is challenging, especially with increasing demand for personalized investment solutions. Existing methods often fail to explore the vast strategy space while preserving the diversity essential for robust performance across changing market conditions. We present QuantEvolve, an evolutionary framework that combines quality-diversity optimization with hypothesis-driven strategy generation. QuantEvolve employs a feature map aligned with investor preferences, such as strategy type, risk profile, turnover, and return characteristics, to maintain a diverse set of effective strategies. It also integrates a hypothesis-driven multi-agent system to systematically explore the strategy space through iterative generation and evaluation. This approach produces diverse, sophisticated strategies that adapt to both market regime shifts and individual investment needs. Empirical results show that QuantEvolve outperforms conventional baselines, validating its effectiveness. We release a dataset of evolved strategies to support future research.

This sweet Sonos soundbar gets a rare discount for Amazon's Prime Big Deal Days. All products featured on WIRED are independently selected by our editors. However, we may receive compensation from retailers and/or from purchases of products through these links. Amazon Prime Day comes around but once, or twice, or maybe like three times (?) a year, and it's a great time to stock up on tech, including grabbing one of the best soundbars you can buy on sale. This Sonos Beam Gen 2 Prime Day soundbar deal certainly qualifies, offering clear and expressive performance and a ton of features for a serious discount during Amazon's Prime Big Deal Days event.

Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.

The integration of a complex set of Electronic Design Automation (EDA) tools to enhance interoperability is a critical concern for circuit designers. Recent advancements in large language models (LLMs) have showcased their exceptional capabilities in natural language processing and comprehension, offering a novel approach to interfacing with EDA tools. This research paper introduces ChatEDA, an autonomous agent for EDA empowered by a large language model, AutoMage, complemented by EDA tools serving as executors. ChatEDA streamlines the design flow from the Register-Transfer Level (RTL) to the Graphic Data System Version II (GDSII) by effectively managing task planning, script generation, and task execution. Through comprehensive experimental evaluations, ChatEDA has demonstrated its proficiency in handling diverse requirements, and our fine-tuned AutoMage model has exhibited superior performance compared to GPT-4 and other similar LLMs.

In the spring of that year, the good Swedes at Volvo introduced Drive Me, a program to get regular Josefs, Frejas, Joeys, and Fayes into autonomous vehicles. By 2017, Volvo executives promised, the company would distribute 100 self-driving SUVs to families in Gothenburg, Sweden. The cars would be able to ferry their passengers through at least 30 miles of local roads, in everyday driving conditions--all on their own. "The technology, which will be called Autopilot, enables the driver to hand over the driving to the vehicle, which takes care of all driving functions," said Erik Coelingh, a technical lead at Volvo. Now, in the waning weeks of 2017, Volvo has pushed back its plans.

In the spring of that year, the good Swedes at Volvo introduced Drive Me, a program to get regular Josefs, Frejas, Joeys, and Fayes into autonomous vehicles. By 2017, Volvo executives promised, the company would distribute 100 self-driving SUVs to families in Gothenburg, Sweden. The cars would be able to ferry their passengers through at least 30 miles of local roads, in everyday driving conditions--all on their own. "The technology, which will be called Autopilot, enables the driver to hand over the driving to the vehicle, which takes care of all driving functions," said Erik Coelingh, a technical lead at Volvo. Now, in the waning weeks of 2017, Volvo has pushed back its plans.

Inventor and author Ray Kurzweil, who currently runs a group at Google writing automatic responses to your emails in cooperation with the Gmail team, recently talked with WIRED Editor-in-Chief Nicholas Thompson at the Council on Foreign Relations. Here's an edited transcript of that conversation. Nicholas Thompson: Let's begin with you explaining the law of accelerating returns, which is one of the fundamental ideas underpinning your writing and your work. Ray Kurzweil: Halfway through the Human Genome Project, 1 percent of the genome had been collected after seven years. So mainstream critics said, "I told you this wasn't gonna work.

Miniature robots stage a group dance at a smart manufacturing conference in Nanjing, East China's Jiangsu Province on December 7. Photo: VCG Some insiders claim that bubbles are already growing in China's artificial intelligence (AI) sector, following the rapid expansion of the industry. Firms that lack long-term strategies to counteract the emergence of such scenarios may go bankrupt sooner rather than later. Like many attractive industries at their early stages, China's AI domain has been favored by both private capital and the government, Zhu Pinpin, founder of Shanghai Xiaoi Robot Technology Co, told the Global Times on Monday. "To some extent, we expected a bubble, as investors and governments pushed forward expansion of the industry," he said. Opportunities in virtual reality and AI have grown exponentially recently, with both considered good bets on the venture capital (VC) investment circuit, according to a quarterly report that KPMG released in October.

When Britain leaves the European Union, many immigrants will be forced out of the country. But many of those people provide much-needed labor, and calls to automate the jobs they leave behind are impractical. Eighteen months after the U.K. voted to leave the EU, many details of the exit remain unnegotiated. But the process is broadly expected to have one big impact: a clampdown on immigration from EU countries. In fact, immigration has already declined since the vote, with the U.K.'s Office of National Statistics reporting that net migration into the U.K. is down from 336,000 in the 12 months preceding June 2016 to 230,000 in the 12 months preceding June 2017.