Ross versus ChatGPT
Ross Monaghan
Former CEO now sharing his skills and knowledge as an educator, strategist, and trainer.
Headlines about employees secretly using AI have been making news, writes AI expert Dr. Lance Eliot in Forbes.?So I asked ChatGPT to summarise Eliot’s article in an interesting way that made readers want to view the full article. Then I did the same.
Who did the better job?
Prompt: Summarise the following in 100 words. Make it interesting and make me want to read the full story.
ChatGPT: The recent headlines claiming the existence of secret cyborgs using generative AI in the workplace have caught everyone's attention. The idea of colleagues masquerading as regular humans while using advanced AI technology is intriguing. However, the truth is far less exciting. The term "secret cyborgs" is misleading, as no one in the office has AI embedded in their bodies. The reality is that some employees are using generative AI tools like ChatGPT to aid in their work, while keeping it a secret from their co-workers. This article explores the reasons behind their secrecy and the importance of implementing proper AI governance in organisations.
Ross:?Organisations need an AI governance structure to ensure employees are using the technology appropriately and ethically, according to AI expert Lance Eliot’s article in Forbes this week.?
Citing recent media coverage of cyborg employees secretly using AI to get their work done more quickly, Eliot says organisations are now realising that policy structures need to be in place to ensure ethical and legal use of generative and other AI.
Whilst he’s not a fan of the word cyborg being used to describe employees using AI, he does believe the recent publicity has highlighted the need to take action on governance issues.
Local Government: US city among first to draft ethical AI guidelines
A city in Arizona, USA, is one of the first to consider implementing a policy aimed at ensuring city officials use AI responsibly and ethically.
According to 12News, the City of Tempe has “preemptively vowed to only utilise AI while fostering ‘transparency, fairness, accountability, and individual rights’”.
The draft policy outlines a range of issues, including how it hopes to achieve a human-centred approach, human-AI collaboration, fairness and avoidance of bias, and accountability and oversight.
The draft policy is available here.?
Privacy: “Venn diagram of AI concerns and privacy concerns is a circle.”
The President of secure messaging app Signal, has suggested that AI is best described as “a surveillance technology” and described a Venn diagram of AI concerns and privacy concerns as a circle.
Participating in a Bloomberg conference in San Francisco last week, Meredith Whittaker outlined a number of privacy issues. According to TechCrunch, Whittaker’s message was “...enchanted as the world may be now by chatbots like ChatGPT and Bard, the technology underpinning them is dangerous, especially as power grows more concentrated by those at the top of the advanced AI pyramid”.
Journalism: Guidelines for AI diversity
The Sir Lenny Henry Centre for Media Diversity has published guidelines aimed at helping reporters use generative AI responsibly and in a diverse and inclusive way. They include six principles:
According to the Centre, “the use of AI in journalism raises specific challenges when it comes to the issue of Diversity, Equity and Inclusion, and there are still ongoing discussions whether Generative AI can be used ethically and effectively in newsrooms”.
The guidelines are available to download here.?
Politics: US FEC deadlock means it won’t regulate AI in political advertising
The US Federal Election Commission (FEC) will not implement rules related to AI content in political advertising. A decision on the issue was deadlocked along party lines.
Bloogberg Law reports that the decision was made after NGO Public Citizen requested rulemaking on deceptive AI campaign ads. Federal law prohibits “fraudulent misrepresentation” of other candidates or political parties, the group said.?
According to a Republican Commissioner, Allen Dickerson, the FEC lacks the jurisdiction to regulate AI deep fakes.
“Instead of coming to us, they should take this up with Congress,” he said.
Last month the US Republican National Committee used artificial intelligence to create a 30-second ad imagining what President Joe Biden's second term might look like. In New Zealand the National Party also used AI-generated content in a campaign ad.
领英推荐
Education: First automatic cars, now generative AI
Generative AI is not just a shameful development, it is a deeply frightening one, according to author and academic, Douglas Hofstadter.
Writing in The Altantic, following his university’s suggestion that staff should “experiment appropriately with AI”, Hofstandter said he was “blown away” by the suggestion.?
“I’m sorry, but I can’t imagine the cowardly, cowed, and counterfeit-embracing mentality that it would take for a thinking human being to ask such a system to write in their place, say, an email to a colleague in distress, or an essay setting forth original ideas, or even a paragraph or a single sentence thereof.”
“Such a concession would be like intentionally lying down and inviting machines to walk all over you,” Hofstadter concluded.
Awards: Don’t expect to see ChatGPT on the red carpet
The Recording Academy has clarified rules about what music content will be eligible to win a Grammy Award.?
Award nominations using some AI assistance in their production will be eligible for an award, but human content must be front and centre.?
“At this time what we’re doing is continuing to value and celebrate human creation,” according to the Academy’s CEO, Harvey Mason Jr.
“We don’t proclaim to have all the facts and all the answers on exactly the best way to treat AI. No one does.
“We’re trying to do our best to try and make sure we get this right and we’ll continue to assess as this tech advances,” Mason told Rolling Stone magazine.?
HR: More AI jobs being posted thanks to interest in ChatGPT
There has been an increase in job seeker interest in AI-related jobs, according to a report in HR World.?
The report suggests Generative AI-related job postings in the US increased by 20 percent in May 2023.
“Indeed (.com)'s data showed that searches for generative AI jobs jumped to147 per million total jobs searched in May, from virtually zero a year earlier,” according to the report.
Security: AI cyber attacks an upcoming trend
“Ransom for reputation” and AI-driven cyber attacks are the top cybersecurity trends identified by the Cyber Security Agency of Singapore (CSA) in its Singapore Cyber Landscape (SCL) 2022 report.?
Whilst public shaming on “leak sites” is the top trend, it is closely followed by AI-facilitated attacks.?
The Edge reports that “threat actors (can) use AI-enabled deep fakes to impersonate C-suite executives to facilitate account takeovers, business fraud, or impact the share price or reputation of an organisation.”
You can download the report here.?
Regulation: UN calls for AI watchdog group?
In brief
Reputation Week provides general advice only and should not be used as a basis for making decisions about your particular circumstances.
Communications change specialist: I disrupt people’s thinking by asking thoughtful questions to spark an idea, transform things and deliver better results.
1 年Oh Ross I just love the refreshing approach you've taken to this. I reakon you won but I did laugh at the ChatGPT line: "The term "secret cyborgs" is misleading, as no one in the office has AI embedded in their bodies.?" AI has a sense of humour but may not realise it ;-).
Writer & content consultant | Helping brands and entrepreneurs tell stories that matter | Brand journalist and word-nerd for hire
1 年This is a great idea Ross! And for the record, I think you won ?? I've been thinking a lot about AI and its role for those of us who write for a living. Is using AI to generate a first draft before you then review, edit and refine really 'cheating?' Do we need to credit/declare AI-generated content and if so, how? What are the fundamental differences between human-written content and AI-generated content - if there even are any? It's such a fascinating space and one that will no doubt evolve faster than we can analyse and adapt to it.
Group Head of Risk, Insurance and Internal Audit
1 年https://riskacademy.blog/best-risk-management-prompts-for-chatgpt/