I have a Salvadoran godson who has been in the black hole of President Nayib Bukele's jails for more than three years. He has not been allowed to send letters or to receive visits from anybody, including lawyers. My family and I have tried, through multiple channels, to get him out, without success. This grotesque mockery of justice is what President Trump is trying to normalize, and it is hard for me to understand how we as a country have fallen so far so fast. How does emulating a dictatorship, like that in El Salvador, prove that America is "great"?

In a cramped conference room in Bristol, Ilan Gur is trying to convince a group of plant biologists that they can change the world. The 44-year-old has the patter you'd expect from a Californian startup founder, but he's also one of the UK's most senior civil servants, so what comes next is unexpected. Close your eyes, he asks the scientists, and imagine pushing past the very edges of your research. The attendees take a beat, shifting slightly on their uncomfortable chairs. Positive visualization is not quite what they had expected from a workshop introducing them to the Advanced Research and Invention Agency (ARIA), the UK government's new high-risk, high-reward science funding agency.

We test the robustness of debate as a method of scalable oversight by training models to debate with data generated via self-play. In a long-context reading comprehension task, we find that language model based evaluators answer questions more accurately when judging models optimized to win debates. By contrast, we find no such relationship for consultancy models trained to persuade a judge without an opposing debater present. In quantitative and qualitative comparisons between our debate models and novel consultancy baselines, we find evidence that debate training encourages stronger and more informative arguments, showing promise that it can help provide high-quality supervision for tasks that are difficult to directly evaluate.

Nathan Heller on the Order of the Third Bird, a secret society that includes writers and artists, many of whom have spawned new initiatives like the Strother School of Radical Attention, which offers an education against the distractions of apps, digital ads, and shorter attention spans.

Elon Musk's Neuralink hit the headlines this morning, after the entrepreneur announced that his firm had implanted a chip in the brain of a human for the first time. Having gained FDA approval, Musk announced that a device called'Telepathy' had been implanted and that the unnamed patient was recovering well. But after Neuralink's early trials saw 1,500 animals killed during rushed experiments, experts have raised serious concerned about the implant's safety. Speaking to MailOnline, Dr Dean Burnett, honorary research associate at Cardiff University, called the human trials'disconcerting and alarming.' 'The speed at which [Musk] has gone from having no involvement in neurosurgical implants to making massive global statements is disconcerting and alarming,' he said.

The financial services sector has been an eager adopter of robotic process automation (RPA): by one estimate, it accounts for 29% of the RPA market, more than any other sector. So it stands to reason that the industry is an early adopter of intelligent automation, the combination of RPA with AI. "Financial services [institutions] have always been among of the top adopters of intelligent automation," says Sarah Burnett, industry analyst and evangelist at process mining vendor KYP.ai. Financial institutions have adopted a range of use cases for intelligent automation, from simple integrations of cognitive services into RPA systems to, in a few cases, AI-powered decision making. As such, they have also encountered the security risks and governance challenges that arise from intelligent automation sooner than most. Intelligent automation is a broad term, representing a range of possibilities for integrating AI and machine learning into process automation.

By now, the average business user has been deluged with the term Artificial Intelligence so much that he or she likely knows it frequently involves machine learning for enterprise applications of Conversational AI, intelligent search, or Natural Language Generation. With the general population still captivated by the hype around deep learning, neural networks, and predictive models, it's easy to consider rules-based systems for these applications as passé, or perhaps worse, outdated approaches to the suite of natural language technologies. According to Arria NLG CTO Neil Burnett, however, nothing could be further from reality. "Using rules is a better approach than just a [pure] machine learning approach," Burnett revealed. "We still do a good amount of rules-based generation. It's a little more elaborate than you might imagine. It's kind of a rules based approach mixed in with a little bit of ML as well."

After years of failed attempts to curb surveillance technologies, Baltimore is close to enacting one of the nation's most stringent bans on facial recognition. But Baltimore's proposed ban would be very different from laws in San Francisco or Portland, Oregon: It would last for only one year, police would be exempt, and certain private uses of the tech would become illegal. City councilmember Kristerfer Burnett, who introduced the proposed ban, says it was shaped by the nuances of Baltimore, though critics complain it could unfairly penalize, or even jail, private citizens who use the tech. Last year, Burnett introduced a version of the bill that would have banned city use of facial recognition permanently. When that failed, he instead introduced this version, with a built-in one year "sunset" clause requiring council approval to be extended.

Some people use the terms artificial intelligence (AI) and machine learning (ML) interchangeably. The distinction between the two may seem trivial – after all, machine learning is a subset of AI. However, IT leaders and line-of-business leaders need to understand and be able to articulate the differences between AI and ML. As business interest in AI solutions grows, so too does the number of vendors flooding the market with "intelligent" solutions. Without clarity on AI and ML, enterprises can end up pursuing misguided – and ultimately disappointing projects – or falling for fake AI solutions.

As organizations became engulfed in big data – high-volume, high-velocity, and/or high-variety information assets – the question quickly became how to effectively derive insight and business value from it. "Big data naturally leads to advanced analytics. When we can capture a lot of information about a business topic that you can improve, you don't want just to scratch the surface. You want to discover the unknown, find out the root cause, predict what will happen, address issues with extreme precision," says Jean-Michel Franco, senior director of product at Talend. "This is more than what humans can do alone, without the help of the machine."