Ed. note: This is the latest in the article series, Cybersecurity: Tips From the Trenches, by our friends at Sensei Enterprises, a boutique provider of IT, cybersecurity, and digital forensics services.
Catchy title, right? Well, we must ‘fess up – OpenAI’s ChatGPT lent us a hand. We submitted this request: “Suggest several striking titles for an article about why lawyers are afraid of being replaced by AI.” We got 12 proposed titles in return, all of them credible as well as catchy.
ChatGPT takes the world by storm, including the cybersecurity world
We have been blown away by the number of articles about OpenAI’s ChatGPT since it was released in late November 2022. We’ll start with the worries about cybersecurity.
Within two months of ChatGPT’s release, the Washington Post reported that there were already examples on the dark web of cybercriminals advertising “buggy, but functional malware, social engineering tutorials, scams and moneymaking schemes,” all enabled by ChatGPT.
The malware examined was significantly short of the caliber of malware that nation-backed hackers would use. At present. Make no doubt about it, the quality of the malware will improve as the AI improves and as cybercriminals learn how to get around the future safeguards from OpenAI meant to prevent the abuse of its AI.
It strikes us that history teaches us that it is only a matter of time before the cybercriminals succeed.
On the good news front, the MIT Technology Review has reported that a watermark for chatbots can spot text written by an AI. If true, this may have an impact on students who are cheating by using AI (a huge source of concern across the country). It may also hinder cybercriminals.
The entire security world is watching the evolution of ChatGPT, no doubt about that.
ChatGPT Credibly Passes Law School and Other Exams
University of Minnesota law professors decided to find out if ChatGPT could pass their final exams. It did indeed pass, with a C+. Not stellar, but not bad either. It had a good grasp of basic legal rules, but trouble with math. Author Nelson could identify with that. And she still passed the bar.
The AI fared better at Wharton School of Business at the University of Pennsylvania, earning a B to B- grade. One of the professors said that it did “an amazing job” at answering basic operations management and process-analysis questions but struggled with more advanced prompts and made “surprising mistakes” with basic math.
Doesn’t it just blow you away that a computer has trouble with math?
Is AI leading us to a dystopian future?
We asked ChatGPT that specific question and it replied that it is possible that AI could lead to a dystopian future if it is not developed and used responsibly. It went on to say AI could be used for malicious purposes and that it could perpetuate and amplify societal biases.
It also said that AI could lead to a more prosperous and efficient future if it is used ethically. That’s the sticking point, isn’t it? Most readers will be familiar with the lessons of the movie “The Terminator” – and we all know how that turned out.
Is it possible that AI will one day replace some lawyers?
When asked this question, the AI waffled a bit and said, “it is possible that AI could eventually replace some aspects of a lawyer’s job, such as document review, legal research and contract analysis.” Perhaps to make us feel better, it offered its opinion that “it is unlikely that AI will completely replace the role of lawyers as the legal profession requires a high degree of critical thinking, problem-solving and decision-making skills that are currently difficult for AI to replicate.” Note the word “currently.”
Ultimately, it opined that “it is more likely that AI will become a tool that lawyers use to augment their abilities, rather than a replacement for lawyers altogether.” Only partial comfort there . . .
On the other hand, Suffolk University Law School Dean Andrew Perlman says the AI is getting better and better – in fact, he was blown away after testing ChatGPT. He’d like to see how it has progressed in a few years and is clearly expecting major advancement. Which brings us to the next topic . . .
Why are lawyers afraid of being replaced by AI?
ChatGPT had four thoughts when we submitted our query:
1. Lawyers may be afraid of losing their jobs as AI can perform some tasks more quickly and efficiently than humans.
2. Automation can change the way legal services are provided and how they are perceived by the public, leading to a decline in the prestige and power of the legal profession.
3. Lawyers may worry that the increasing use of AI will lead to a loss of the human touch that is essential in the legal profession.
4. Some lawyers may also be resistant to change and may have concerns about the unknown aspect of AI and its potential to disrupt the legal field.
We thought the observations above were pretty darn good – and accurate.
We missed a chance to have AI “argue in court”
Several years ago, Joshua Browder, the CEO of DoNotPay, devised a way for people contesting traffic tickets to use arguments in court generated by AI. He had planned to have his AI help a defendant fight a traffic ticket in a California court with the person challenging a ticket wearing earbuds hat would dictate into the defendant’s ear. The system uses both ChatGPT and DaVinci.
State bar officials were appalled, and threatening letters began to roll in. According to Browder, “One even said a referral to the district attorney’s office and prosecution and prison time would be possible.” He said that one state bar official noted that the unauthorized practice of law is a misdemeanor. The case – and the threats – made headlines everywhere.
Do you want to play in the sandbox too?
We’ve never seen so many lawyers eager to test AI. Doing so is very fast and easy. You simply go to https://chat.OpenAI.com and register for an account with your email address. Easy peasy. You may find it hard to stop playing with the AI– we sure did. Do it soon. Shortly, it will reportedly cost you $42 a month to play in the sandbox.
Final words
Anything that Microsoft invests a reported $10 billion in is something to keep an eye on. It is clear that Microsoft intends to be at the forefront of generative AI, which means generating test, images, social media posts and other media from short text reports. As major tech companies race to join the next generation of AI, will ethical AI take a back seat? It’s worrisome.
We suspect that many things we once thought impossible will be made possible by the new generation of AI. As Napoleon Bonaparte once said, “Impossible is a word to be found only the dictionary of fools.”
Sharon D. Nelson (snelson@senseient.com) is a practicing attorney and the president of Sensei Enterprises, Inc. She is a past president of the Virginia State Bar, the Fairfax Bar Association, and the Fairfax Law Foundation. She is a co-author of 18 books published by the ABA.
John W. Simek (jsimek@senseient.com) is vice president of Sensei Enterprises, Inc. He is a Certified Information Systems Security Professional (CISSP), Certified Ethical Hacker (CEH), and a nationally known expert in the area of digital forensics. He and Sharon provide legal technology, cybersecurity, and digital forensics services from their Fairfax, Virginia firm.
Michael C. Maschke (mmaschke@senseient.com) is the CEO/Director of Cybersecurity and Digital Forensics of Sensei Enterprises, Inc. He is an EnCase Certified Examiner, a Certified Computer Examiner (CCE #744), a Certified Ethical Hacker, and an AccessData Certified Examiner. He is also a Certified Information Systems Security Professional.
