The enhance of accuracy in reasoning results of LLMs arouses the community's interests, wherein pioneering studies investigate post-hoc strategies to rectify potential mistakes. Despite extensive efforts, they are all stuck in a state of resource competition demanding significant time and computing expenses. The cause of the situation lies in the failure of identifying the fundamental feature of the solutions in this line, coined as the self-denial of LLMs. In other words, LLMs should confidently determine the potential existence of mistakes and carefully execute the targeted correction. As the whole procedure conducts within LLMs, supporting and persuasive references are hard to acquire, while the absence of specific steps towards refining hidden mistakes persists even when errors are acknowledged. In response to the challenges, we present PSSD, which refers to and implements the human psyche structure such that three distinct and interconnected roles contribute to human reasoning. Specifically, PSSD leverages the recent multi-agent paradigm, and is further enhanced with three innovatively conceived roles: (1) the intuition-based id role that provides initial attempts based on benign LLMs; (2) the rule-driven superego role that summarizes rules to regulate the above attempts, and returns specific key points as guidance; and (3) the script-centric ego role that absorbs all procedural information to generate executable script for the final answer prediction. Extensive experiments demonstrate that the proposed design not only better enhance reasoning capabilities, but also seamlessly integrate with current models, leading to superior performance.

Robotic arms can move fast enough to snatch thrown objects right out of the air… but should they? Not unless you want them to unnerve the humans they're interacting with, according to work out of Disney Research. Roboticists there found that slowing a robot's reaction time made it feel more normal to people. Disney has of course been interested in robotics for decades, and the automatons in its theme parks are among the most famous robots in the world. But there are few opportunities for those robots to interact directly with people. Hence a series of research projects at its research division aimed at safe and non-weird robot-human coexistence.

First, Google acquired a startup called DNNresearch, snapping up some of the world's foremost experts in a burgeoning field of artificial intelligence known as deep learning. Then it shelled out $400 million for a secretive deep learning startup called DeepMind. Much like Facebook, Microsoft, and others, Google sees deep learning as the future of AI on the web, a better way of handling everything from voice and image recognition to language translation. But there's one notable deep learning company that Google hasn't yet bought. It's called Clarifai, and it may remain as an independent operation.

Of all the big firms in Silicon Valley, Amazon had the most to lose from Donald Trump's presidency. And lose it did, albeit briefly, its share price dropping 5% shortly after the election. During the campaign, Trump warned that Amazon had a "huge antitrust problem" – a reasonable stance for the populist that he once aspired to be. Most likely, though, his animosity had more to do with the fact Amazon's founder, Jeff Bezos, also owns the Washington Post, an influential newspaper that took an early strong dislike of Trump. By the time of Amazon's massive cloud-computing conference, which kicked off in Las Vegas at the end of November, such squabbles seem to have been forgotten.

Last week, on September 8th, the Los Angeles County Sheriff's department successfully used a remote-controlled bomb squad robot to snatch a rifle out from under an armed and violent suspect. The standoff between the suspect and an armored SWAT team lasted for more than six hours, but concluded without a single shot fired. "The robot was a game changer here," Capt. Jack Ewell told the LA Times. "We didn't have to risk a deputy's life to disarm a very violent man."