# NuseReal

Researchers at EPFL have uncovered a fundamental flaw in the training of machine learning systems and elaborated a new formulation for strengthening them against adversarial attacks — epfl — 28 September 2023 (LINK)

— By completely rethinking the way that most Artificial Intelligence (AI) systems protect against attacks, researchers at EPFL's School of Engineering have developed a new training approach to ensure that machine learning models, particularly deep neural networks, consistently perform as intended, significantly enhancing their reliability.

Can we rely on AI cybersecurity — costs & disadvantages (exclusive report) — cryptopolitan — 22 September 2023 (LINK)

— Its conclustion: it brings many compelling benefits, including long-term.

Microsoft introduces Unified AI assistant CoPilot enhancing Windows 11 with AI capabilities from 26 September — www.cryptopolitan.com — 21 September 2023 (LINK)

ASML — the cornerstone and vital link in the Artificial Intelligence supply chain — www.cryptopolitan.com — 18 September 2023 (LINK)

New study pit ChatGPT against top MBA students and found it generated ideas much faster than humans — www.mensjournal.com — 13 September 2023 (LINK)

Google launches $20 million fund to support responsible AI development — decrypt.co — 12 September 2023 (LINK)

AI has now learned how to deceive humans — bgr.com — 10 September 2023 (LINK)

— ChatGPT and other AI systems are prone to "hallucinate" information, making it up on the spot. Researchers writing on The Conversation say Meta's CICERO AI is one of the most disturbing examples of how deceptive AI can be. This model was designed to play Diplomacy, and Meta says that it was built to be "largely honest and helpful". In fact, CICERO even went so far as to premeditate deception, where it worked with a human player to trick another human player into leaving itself to open invasion.

AI impact is poised to enhance jobs, not erase them, according to a 21 August ILO study — www.cryptopolitan.com — 10 September 2023 (LINK)

— Jobs held by managers, professionals, and technicians exhibit minimal vulnerability to automation, with only a small fraction of tasks at high risk and around a quarter at medium risk.

High-income countries face the potential automation of about 5.5% of total employment, whereas low-income countries encounter automation risks affecting a mere 0.4% of employment. But, the potential for augmentation appears nearly equal across countries, implying that with the right policies, AI could offer substantial benefits to developing nations.

Amazon requires authors to disclose use of AI material in books — www.cryptopolitan.com — 9 September 2023 (LINK)

Where are all of the AI jobs? A Comprehensive look at the global market — www.cryptopolitan.com — 9 September 2023 (LINK)

— USA tops the charts. As of 2022, California and Texas boasted the highest demand for AI workers, followed by New York, Virginia, Ohio, Florida, Georgia, and Illinois.

AI vs. human writing: experts fooled almost 62% of the time — neurosciencenews.com — 8 September 2023 (LINK)

Google delivers a flurry of Generative AI announcements at Google Cloud Next 2023 — www.forbes.com — 6 September 2023 (LINK)

Generative AI's biggest security flaw, vulnerability to indirect prompt injection attacks, is not easy to fix — /www.wired.co.uk — 6 September 2023 (LINK)

Chinese tech giants announce public availability of AI models — www.cryptopolitan.com — 5 September 2023 (LINK)

This AI model can help prevent up to 76% of wildfires — www.weforum.org — 4 September 2023 (LINK)

AI Experiment backfires as newspaper giant Gannett temporarily halts AI sports reporting for awkward phrasing and lack of detail — www.cryptopolitan.com — 1 September 2023 (LINK)

AI's dirty secret: poor people in the developing world are doing most of the work — futurism.com — 29 August 2023 (LINK)

— While AI has triggered a billion-dollar arms race in the US, those who are actually doing the brunt of the work are often going unnoticed, underpaid, or ignored altogether

US court rules against copyright filing for AI-generated works — cryptopolitan — 20 August 2023 (LINK)

ChatGPT shows 'significant and systemic' left-wing bias, study finds — ground.news: 7 media reports — 17 August 2023 (LINK)

How much will Microsoft's generative AI cost you? $30 a month — www.cryptopolitan.com — 19 July 2023 (LINK)

UN Secretary General embraces calls for a new UN agency on AI in the face of 'potentially catastrophic and existential risks' — edition.cnn.com — 18 July 2023 (LINK)

China mandates that companies offering AI services to the public must follow "core values of socialism" — ground.news: 21 reports — 13 July 2023 (LINK)

ChatGPT-maker OpenAI signs deal with AP to license news stories — ground.news: 50 media reports — 13 July 2023 (LINK)

Researchers at Stanford have developed an Artificial Intelligence (AI) model,'StockBot', which uses LSTMs to predict stock prices with gains higher than the most aggressive ETFs — www.marktechpost.com — 11 July 2023 (LINK)

ChatGPT saw its first-ever user decline in June — www.engadget.com — 9 July 2023 (LINK)

AI revolutionizes brain tumor management with advanced diagnosis, treatment, and prognosis — /www.cryptopolitan.com — 8 July 2023 (LINK)

ChatGPT monthly traffic has dropped for the first time — ground.news: 14 media reports — 7 July 2023 (LINK)

US military is training AI to give orders and handle state secrets — decrypt.co — 7 July 2023 (LINK)

Harvard is using ChatGPT to teach computer science — www.zdnet.com — 3 July 2023 (LINK)

First misinformation susceptibility test finds 'very online' Gen Z and millennials are most vulnerable to fake news — phys.org — 28 June 2023 (LINK)

— When it came to age, only 11% of 18- to 29-year-olds got a high score (more than 16 headlines correct), while 36% got a low score (10 headlines or fewer correct). By contrast, 36% of those 65 or older got a high score, while just 9% of older adults got a low score.

Additionally, the longer someone spent online for fun each day, the greater their susceptibility to misinformation, according to the MIST. Some 30% of those spending 0–2 recreation hours online each day got a high score, compared to just 15% of those spending 9 or more hours online.

The survey also analyzed channels through which respondents receive their news. The "legacy media" came out top. For example, over 50% of those who got their news from the Associated Press, or NPR, or newer outlets such as Axios, achieved high scores.

Social media had the news audiences most susceptible to misinformation. Some 53% of those who got news from Snapchat received low scores, with just 4% getting high scores. Truth Social was a close second, followed by WhatsApp, TikTok and Instagram.

How newsrooms around the world use AI: a JournalismAI 2023 global survey — blogs.lse.ac.uk — 26 June 2023 (LINK)

— ost newsrooms we surveyed have already experimented with generative AI technologies like ChatGPT, but not necessarily to create content. The use cases we've learned about are quite diverse: code writing, summaries, enhancing headlines and SEO. One respondent said they were using ChatGPT as a 'banter buddy', "Imagine having a trusted companion in ChatGPT, ready to engage in lively banter and brainstorming sessions," they said.

ChatGPT on Threat: Over 100K Logins Leaked on the DarkWeb — thenewscrypto.com — 23 June 2023 (LINK)

— Cyber attacks primarily target users in Asia-Pacific. India impacted with 12,632 compromised ChatGPT accounts.

Cortical Labs trains human brain cells on computer chips for advanced AI — www.cryptopolitan.com — 23 June 2023 (LINK)

All Chatbots Like ChatGPT and Google Bard Don't Meet EU AI Law Standards: Study — decrypt.co — 21 June 2023 (LINK)

More Than 100,000 ChatGPT User Accounts Compromised by Malware, Reveals Dark Web Report — www.techtimes.com — 20 June 2023 (LINK)

— The Asia-Pacific region accounted for nearly 41,000 compromised accounts between June 2022 and May 2023, followed by Europe with almost 17,000. Surprisingly, North America ranked fifth, with approximately 4,700 affected accounts.

UN Report Raises 'Serious and Urgent' Concerns About AI Deepfakes — www.cryptopolitan.com — 13 June 2023 (LINK)

ChatGPT can only tell 25 jokes, and can't come up with new ones, researchers find — www.businessinsider.com — 10 June 2023 (LINK)

Researchers unveil first Chat-GPT-designed robot — actu.epfl.ch — 7 June 2023 (LINK)

Nearly 4,000 people lost their jobs last month because of AI — the first time that's been cited as a reason — www.businessinsider.com — 2 June 2023 (LINK)

MIT researchers develop self-learning language models that outperform larger counterparts — venturebeat.com — 1 June 2023 (LINK)

AI presents 'risk of extinction' on par with nuclear war, pandemics, industry leaders say — ground.news: 226 media reports — 30 May 2023 (LINK)

UNESCO unveils new AI roadmap for classrooms — news.un.org — 26 May 2023 (LINK)

New superbug-killing antibiotic discovered using AI — ground.news: 20 media reports — 25 May 2023 (LINK)

Pakistan aims to produce 1 million AI-trained IT graduates by 2027 — cointelegraph.com — 24 May 2023 (LINK)

— Some of the intended use cases for AI in Pakistan include predicting the weather, agriculture supply chain optimization and health services transformation.

Apple's tax on AI inventions has begun. It will cost OpenAI and others hundreds of millions of dollars a year. — Business Insider — 22 May 2023 (LINK)

WHO cautions on use of ChatGPT, Bard in healthcare — thestatesman — 16 May 2023 (LINK)

6 takeaways from the OpenAI senate hearing — mashable.com — 16 May 2023 (LINK)

Wendy's to begin replacing drive-thru staff with AI chatbots — /newatlas — 10 May 2023 (LINK)

China makes first ChatGPT arrest after man allegedly generates fake news of train crash — ground.news: 21 media reports — 8 May 2023 (LINK)

ChatGPT can pick stocks better than your fund manager — CNN — 5 May 2023 (LINK)

— Between March 6 and April 28, a dummy portfolio of 38 stocks gained 4.9% while 10 leading investment funds clocked an average loss of 0.8%, according to an experiment conducted by financial comparison site finder.com.

AI pioneer says its threat to world may be 'more urgent' than climate change — ground.news: 11 media reports — 5 May 2023 (LINK)

I used GPT-4 to write my biography. it got a lot wrong — source — 14 April 2023 (LINK)

"A really big deal" — Dolly is a free, open source, ChatGPT-style AI model — arstechnica — 13 April 2023 (LINK)

The newest version of ChatGPT passed the US medical licensing exam with flying colors — and diagnosed a 1 in 100,000 condition in seconds — insider.com — 6 April 2023 (LINK)

ChatGPT and AI: What they mean for small business — intracen — 6 April 2023 (LINK)

— Smart digital technologies are already widely used in agriculture in high-income countries. For instance, AI is being used in robotic milking systems in places such as Braz, Austria, to decide which cow should be milked when, with little supervision from the farmer. In low-income countries, on the other hand, AI is mainly limited to small-scale smart farming and satellite imagery processing at the level of smallholder farming. But looking around, we can anticipate future uses, if an appropriate business model can be found.

In Senegal, chatbots are being used instead of customer care operators as clients and investors alike want to reduce costs. In the Philippines, some of its 1.2 million business-process-management jobs — to a large extent customer care for global clients — could be replaced through robotic process automation.

"ITC's SME Trade Academy is already experimenting with tools such as Synthesia to produce videos with human-like avatars in multiple languages and accents. We need to help our beneficiaries leverage this technology as well, for instance the tailor in Burundi who is using ChatGPT to draft marketing materials like brochures and website content."

Generative AI In The Enterprise — Use Cases & Early Learnings — forbes ● — 26 March 2023 (LINK)

— In customer support, generative AI — including GPT3+ and other Large Learning Models, is transforming conversational chatbot capabilities into one that feels natural, is more accurate, and is better able to sense and react to tone and emotions.

Around business insights, generative AI now allows business users to ask questions in natural language. The AI can now convert these into SQL queries, run against the internal databases, and return the answer in a structured narrative — all within minutes. The advantage here isn't just the efficiency — it's the speed of decision-making and the ability for business users to interrogate the data more directly and interactively.

Third, in programming automation, Large language models are highly accurate in multiple languages — including computer language. Software developers are reducing the time to write code and associated documentation by almost 50%. For example, the Microsoft Power Automate program — a tool for robotic process automation — can now be programmed using natural language to automate tasks and workflows in a more intuitive and user-friendly manner. Not only is this more efficient than getting large teams of programmers and testers involved, but it also reduces time and iteration to get automation up and running.

—Enterprises should set up a small focused group tasked with experimenting with Generative AI and reengineering core business processes. This group should report to the highest levels in the organization and be goaled with figuring out how to disrupt current processes and business models. Because it has the potential to disrupt existing ways of doing things, it requires a sharp focus and clear sponsorship.

Hacker demonstrates security flaws in GPT-4 just one day after launch — source — 24 March 2023 (LINK)

Testing readability tests: Flesch–Kincaid, ARI, and Gunning Fog: ARI (Hemingway) is the most stable but all tests are quite old and there's no agreement on how to count words — uxdesign — 23 March 2023 (LINK)

GitHub unveils Copilot X: The future of AI-powered software development — venturebeat — 22 March 2023 (LINK)

GPT passes some of my programming courses — lemire.me — 22 March 2023 (LINK)

Oops. Stanford basically just stole ChatGPT and cloned it for 600 bucks — hotair.com — 20 March 2023 (LINK)

ChatGPt's successor GPT-4 lists twenty jobs it can 'potentially replace' — ground.news: 10 sources — 19 March 2023 (LINK)

— in the order of how easy it will be for ChatGPT to replace, are:

1. data entry clerk
2. customer service representative
3. proofreader
4. paralegal
5. bookkeeper
6. translator
7. copywriter
8. market research analyst
9. social media manager
10. appointment scheduler
11. telemarketer
12. virtual assistant
13. transcriptionist
14. news reporter
15. travel agent
16. tutor
17. technical support analyst
18. email marketer
19. content moderator
20. recruiter

A recent World Economic Forum report said that 85 million jobs would be dispaced by 2025 as a direct consequence of the tug-of-war between humans and machines.

Teachers and students warm up to ChatGPT — axios — 7 March 2023 (LINK)

How to use the 'JAILBREAK' version of ChatGPT: Simple trick lets you access an unfiltered alter-ego of the AI chatbot — dailymail.co.uk — 4 March 2023 (LINK)

8 Reasons Why Content Writers Can't Rely on AI Chatbots — makeuseof — 24 February 2023 (LINK)

1. AI Doesn't Fact-Check Information
2. Language Models Like GPT-3 Follow Templates
3. Overdependence on AI Makes You a Lazy Researcher
4. AI Scrapes Commonly Published Information
5. AI Generates the Same Results for Similar Questions
6. AI Can't Adopt Your Tone
7. Writing Tools Don't Incorporate SEO Tactics Into Its Pieces
8. Many Premium Plagiarism Checkers Flag AI-Generated Pieces

Man beats machine at Go in human victory over AI: amateur exploited weakness in systems that have otherwise dominated grandmasters — arstechnica — 19 February 2023 (LINK)

Google wasn't the only one to make errors in its A.I. demo. Analysis finds Microsoft's Bing flubbed a string of financial figures — fortune ● — 15 February 2023 (LINK)

Outsmart ChatGPT: 8 Tips for Creating Assignments It Can't Do — edweek — 14 February 2023 (LINK)

ChatGPT's 100 Millionth User Means the Age of AI Is Here — source — 14 February 2023 (LINK)

New AI methods to tackle the illegal wildlife trade on the internet — phys.org — 9 February 2023 (LINK)

Generative AI Copyright Overview Part 1 — jdsupra.com — 9 February 2023 (LINK)

— In a previous case a U.S. circuit court ruled: "Google's commercial nature and profit motivation do not justify denial of fair use" for digitizing the texts of published and copyrighted books. But "the works produced by a generative AI system may serve as a significant market substitute — this weighs against fair use."

"The answer is not clear at this point whether a generative AI system may use input data that is protected by copyright law. On one hand, new works are being created from the input data with minimal display of any copyrighted works. "

AIs as doctors? ChatGPT nearly passes US medical licensing exam — jpost — 9 February 2023 (LINK)

Google's AI bot mistake wipes $100bn off shares — BBC — 8 February 2023 (LINK)

Microsoft's new Bing and Edge hands-on: Surprisingly well-integrated AI — source — 7 February 2023 (LINK)

ChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Why — vice — 8 February 2023 (LINK)

Google announces ChatGPT rival Bard, with wider availability in 'coming weeks' — theverge — 6 February 2023 (LINK)

ChatGPT Becomes Fastest-Growing Platform In The World As It Hits 100 Million Users In 2 Months — mashable — 6 February 2023 (LINK)

'Upending the world': Swiss teachers take on ChatGPT — rawstory.com — 6 February 2023 (LINK)

An interview with AI: What ChatGPT says about itself — finance.yahoo.com — 5 February 2023 (LINK)

— Is ChatGPT taking my job someday? ChatGPT claims humans have little to worry about, but I'm not so sure.

Israel's president the first world leader to publicly use ChatGPT in a speech partly written by the AI — Business Insider — 4 February 2023 (LINK)

— Herzog opened his speech with an intro written by ChatGPT. He then ended the speech with a ChatGPT generated "inspirational quote" about AI.

ChatGPT Gets an MBA B- in test — bloomberg — 7 February 2023 (LINK)

A judge in Colombia really used ChatGPT to make a court ruling — bgr.com — 3 February 2023 (LINK)

— Judge Juan Manuel Padilla Garcia, a judge in the First Circuit Court in Cartagena, Colombia, confirmed that he used the AI tool to "pose legal questions about the case and included its responses in his decision." He said: "What we are really looking for is to optimize the time spent drafting judgments after corroborating the information provided by AI."

I asked ChatGPT to make the case for and against crypto and it weighed in on regulation, energy, and decentralization — Business Insider — 2 February 2023 (LINK)

10 AI prompts for journalists using chatGPT — linkedin — 31 January 2023 (LINK)

The Dangers of AI Writing and How to Spot AI-Generated Text — makeuseof.com — 30 January 2023 (LINK)

• Look for Repetition of Words and Phrases
• Search for Unnatural Transitions and Errors
• Examine Any Fact-Heavy, Dry Texts
• Check for the Absence of Emotions or Personal Experiences
• Use an AI Content Detector Tool

Here are all the academic exams ChatGPT has passed (and failed) — semafor — 30 January 2023 (LINK)

Real estate agents say they can't imagine working without ChatGPT now — CNN — 28 January 2023 (LINK)

The first AI-written speech delivered by congressman is as flavorless as you'd expect — theverge — 28 January 2023 (LINK)

The 6 biggest problems with ChatGPT right now — source — 27 January 2023 (LINK)

• Capacity issues
• Plagiarism and cheating
• Racism, sexism, and bias
• Accuracy problems: OpenAI admits that the chatbot has "limited knowledge of world events after 2021"
• The shady way it was trained
• There's no mobile app

Generative AI market size to hit $110.8bn and other AI stats every marketer should know — thedrum — 26 January 2023 (LINK)

— 5: The number of days that passed after the launch of ChatGPT in November 2022 for the generative AI model to reach more than one million users.

Congressman gives speech written by AI (video) — CNN — 26 January 2023 (LINK)

Can ChatGPT review restaurants? Our food critic tests it out — chicagotribune — 26 January 2023 (LINK)

— When I asked if it had ever been to a restaurant I knew would have loads written about it online, ChatGPT wrote back: "As an AI, I do not have physical presence and therefore I haven't been to any physical location."

But when I asked it to write a restaurant review of Alinea, it didn't hesitate: "— is a truly unique dining experience. The food is meticulously crafted and visually stunning, with an emphasis on creativity and innovation. The flavors are bold and complex, and the dishes are expertly paired with a wide selection of wines. The service is impeccable, with attentive and knowledgeable staff who are happy to explain the dishes and the techniques used to prepare them. The atmosphere is elegant and intimate, making it the perfect spot for a special occasion. Overall, Alinea is a must-visit for anyone interested in cutting-edge culinary experiences."

While basically coherent, and not too far off from some Yelp reviews, you may have noticed an almost complete lack of specifics. Replace the restaurant's name and the "review" could apply to any number of fine-dining restaurants in Chicago.

"ChatGPT can get more specific, but I found it also became less accurate. When I asked it to write a detailed restaurant review of Alinea, mentioning every single course, it started spitting out names of dishes I don't think ever appeared on the restaurant's menu."

OpenAI executives say releasing ChatGPT for public use was a last resort after running into multiple hurdles — and they're shocked by its popularity — Business Insider — 25 January 2023 (LINK)

Nonprofits release free tool to detect AI-written student work — fastcompany.com — 25 January 2023 (LINK)

Why AI For Project Management Is The Ultimate Game-Changer — hive.com — 25 January 2023 (LINK)

How to use AI Art and ChatGPT to Create a Insane Web Designs (video) — learnzone — 25 January 2023 (LINK)

ChatGPT (barely) passes all 3 parts of US Medical Licensing Examinations — moneycontrol.com — 25 January 2023 (LINK)

ChatGPT's creator OpenAI has doubled in value since 2021 as the language bot goes viral and Microsoft pours in $10 billion — Business Insider — 24 January 2023 (LINK)

World's Third Richest Person Says He's Developed "Addiction" to ChatGPT — futurism.com — 24 January 2023 (LINK)

— He notes ChatGPT's "comical faitures": From being horrible at math, to pretty blatantly plagiarizing, to not so comical — and really just all-around horrifying — outcomes like one image generating AI's failure to protect against the creation of non-consensual pornography, generative AIs have a lot of harmful downsides.

San Francisco startup Writer develops tool to detect writing by ChatGPT — bizjournals.com● — 24 January 2023 (LINK)

These 7 AI creation tools show how much AI can really do — digitaltrends.com — 25 January 2023 (LINK)

Leveraging ChatGPT: Practical Ideas for Educators — ascd — 24 January 2023 (LINK)

1. Make Grammar More Dynamic
2. Create Study Guides
3. Flip the Classroom
4. Build Information-Literacy Skills

ChatGPT: Chatbots can help us rediscover the rich history of dialogue — theconversation — 24 January 2023 (LINK)

Here's How Art Schools Are Dealing With The Rise of AI Generators — vice — 24 January 2023 (LINK)

Why generative AI will make 2023 the year of the communications engineer — source — 24 January 2023 (LINK)

I'm going to lose my job to an AI — ChatGPT does an hour of my work in seconds — the-sun — 24 January 2023 (LINK)

Unlocking the Potential of K-12 Students with ChatGPT: How AI Could Transform Education — shakeuplearning.com — 24 January 2023 (LINK)

"Buckle up for the ride": What publishers need to know about AI, from Reuters Institute — reuters / whatsnewinpublishing.com — 23 January 2023 (LINK)

— Almost three in ten companies (28%) say AI is now a regular part of their activities, with a further 39% saying they have been conducting experiments in this area.

Will ChatGPT Kill the Ad Industry? — mediapost.com — 23 January 2023 (LINK)

What is new in ChatGPT pro? Features and pricing explained — sportskeeda — 22 January 2023 (LINK)

Layoffs in a likely recession this year could be determined by software programs — usatoday.com — 23 January 2023 (LINK)

— A whopping 98% of human resources leaders say they'll rely at least partly on software programs, or algorithms, to decide whom to cut if they have to conduct layoffs in an anticipated recession in 2023, according to a recent survey by Capterra, which helps small businesses choose software. That's up from just 2% of large companies that turned to Big Data in the Great Recession of 2007-09, according to Capterra, a unit of tech research giant Gartner. In November, Capterra surveyed 300 HR managers at mostly larger firms as well as some small to mid-size businesses.

CNET pauses its controversial AI-generated stories 'for now' — mashable — 21 January 2023 (LINK)

A New Scientific Paper Credits ChatGPT AI as a Coauthor — futurism.com — 21 January 2023 (LINK)

— A not-yet-peer-reviewed paper on ChatGPT's ability to pass the United States Medical Licensing Exam (USMLE) lists 11 researchers affiliated with the healthcare startup Ansible Health — and ChatGPT itself, raising eyebrows amongst experts.

ChatGPT can be tricked into coding malware, say security researchers — moneycontrol.com — 21 January 2023 (LINK)

ChatGPT is a pretty good student: Why schools need to figure out this AI technology fast — thestar — 21 January 2023 (LINK)

Artificial Intelligence Program Claude Just Passed A Law Exam but only a "marginal pass" — giantfreakinrobot.com — 21 January 2023 (LINK)

People are using AI for therapy, whether the tech is ready for it or not — fastcompany — 21 January 2023 (LINK)

Selling Artificial Intelligence To The Business: Keep It Clear, Keep It Simple — forbes ● — 21 January 2023 (LINK)

What a Digital Worker Could Mean for the Human Workforce — discovermagazine.com — 21 January 2023 (LINK)

— Research shows that in many European countries and the U.S., the growth of information and computerized technologies was accompanied by a significant expansion of professional and managerial occupations and a decline of low-skilled jobs.

Not ChatGPT: Cheating Thai professors who research everything — thethaiger — 21 January 2023 (LINK)

6 scary things ChatGPT has been used for already — mashable.com — 20 January 2023 (LINK)

Professors say adapting coursework to AI writing tools can keep student use in check — thestar — 20 January 2023 (LINK)

— Students who use ChatGPT can further refine their paper by using other programs like Grammarly, which corrects spelling and grammar mistakes and assesses style and tone. And of course, students can also rewrite passages in their own voice. "Change some words, run it through another checking system," says a professor. "There's really no way to win this fight right now."

Another says there are ethical ways for educators to use the technology in class — for example, by comparing the AI's writing to a student's and analyzing the strengths and weaknesses of using the tool.

She says a class could use ChatGPT to write an essay on the plot of "Hamlet" and then analyze the quality of what it spits out. They could also question the references used and whether the analysis was accurate. She says that would allow students to think critically on the effectiveness of the tool.

She also notes that ChatGPT does not produce a bibliography to go with the essays it writes — a red flag for professors trying to determine if a bot was involved. However she notes that there are online tools that can generate footnotes and sourcing for an existing paper.

Le Monde: ChatGPT: 'The risk of mass manipulation will intensify the PR battle between Big Tech companies' — lemonde.fr ● — 22 January 2023 (LINK)

— "Back in 2014, the Cambridge Analytica scandal showed that it was possible to influence citizens' votes by presenting them with fabricated information. Since then, the game Candy Crush has shown that it is possible to create enough of an addiction to then charge for continued playing. Meta has indicated that it has the ability to modify its algorithms to improve the wellbeing of its users. And the voluntary spreading of misinformation has convinced 1 in 10 French people that the Earth is flat."

7 Future-Proof Technical Skills That AI Can't Automate — makeuseof.com — 20 January 2023 (LINK)

CEOs at Davos are using ChatGPT to write work emails — CNN — 19 January 2023 (LINK)

ChatGPT is the talk of Davos — axios — 20 January 2023 (LINK)

The 4 Best AI Generator Tools For Writing Essays, Blogs & More: HiveMind, JasperAI, Ryter AI, ChatGZP — hive.com — 18 January 2023 (LINK)

— ChatGPT Pros: Open source platform. It can be used to build complex conversational applications. Easy-to-use APIs. ChatGPT Cons: Lacks the advanced features of other popular AI tools on the market.Limited support for languages other than English.

Four Techniques AI can be used for Crypto trading: Crypto and AI — cryptopolitans — 18 January 2023 (LINK)

ChatGPT listed as author on research papers: many scientists disapprove — nature — 18 January 2023 (LINK)

College Student Caught Writing Paper Using ChatGPT — futurism.com — 18 January 2023 (LINK)

— The paper was way too coherent and well-structured. "I had [the student] rewrite the paper," the Northern Michigan philosophy professor told Futurism. "That's what I almost always do in plagiarism cases. I want the students to actually learn the material, and the only way they can do that is by actually completing the assignment," he said. "I fail students for an assignment or a class only if they are repeat offenders."

ChatGPT: three steps to master this AI tool — uk.finance.yahoo.com — 17 January 2023 (LINK)

I asked ChatGPT how to start a business and it gave me 8 steps that weren't that helpful — Business Insider — 17 January 2023 (LINK)

ChatGPT 101 for HR Pros — shrm.org — 17 January 2023 (LINK)

— Test it out and see if you can write a better job description faster than ChatGPT can. I bet you can't, because ChatGPT will give it to you in under two seconds.

This 22-year-old is trying to save us from ChatGPT before it changes writing forever with GitHub Co-Pilot — whyy.org — 17 January 2023 (LINK)

Princeton student Creates GPTZero App to Detect Essays Written by AI — smithsonianmag.com — 17 January 2023 (LINK)

— Within the first week of its launch, more than 30,000 people used the tool, per NPR's Emma Bowman. On Twitter, it has garnered more than 7 million views.

AI-generated content? This browser extension will spot it for $0.01 for 100 words — whatsnewinpublishing.com — 17 January 2023 (LINK)

A tech news site issued a string of corrections after an article quietly written by ChatGPT got key facts wrong — Business Insider — 19 January 2023 (LINK)

Getty Images is suing the creators of AI art tool Stable Diffusion for scraping its content — theverge — 17 January 2023 (LINK)

How to Identify an AI-Generated Image: 4 Ways — makeuseof.com — 17 January 2023 (LINK)

Davos 2023: Coursera set to integrate ChatGPT into courses says CEO Jeff Maggioncalda — source — 17 January 2023 (LINK)

7 Ways to Get the Best Results From ChatGPT — makeuseof.com — 16 January 2023 (LINK)

ChatGPT could be used for good, but like many other AI models, it's rife with racist and discriminatory bias — insider.com — 16 January 2023 (LINK)

— OpenAI, the company behind the first GPT and its subsequent versions, added guardrails to help ChatGPT evade problematic answers from users asking the chatbot to, for example, say a slur or commit crimes. Users, however, found it extremely easy to get around this by rephrasing their questions or simply asking the program to ignore its guardrails, which prompted responses with questionable — and sometimes outright discriminatory — language.

I Used ChatGPT Every Day for a Month, Here's What I've Learned — medium ● — 9 January 2023 (LINK)

— Among other things, ChatGPT can build websites and apps for you. You can even ask for code in a specific language. It can also solve errors, explain the code and even explain the test cases. It literally can explain each and every line of code. And that's what makes you more productive.

What is generative AI? — /cointelegraph.com — 26 June 2023 (LINK)

32 ChatGPT tips for beginners (video) — www.geeky-gadgets.com — (LINK)

100 ChatGPT terms explained from NLP to Entity Extraction — www.geeky-gadgets.com — (LINK)

How to use ChatGPT for research and essays — www.makeuseof.com — (LINK)

6 ways to use ChatGPT as a data analyst — www.makeuseof.com — (LINK)

How to leverage your skills in the post-knowledge AI economy — weforum — (LINK)

Want To Try OpenAI's GPT-4? Here's A Step-By-Step Guide On How To Try This Internet-Breaking AI Tool — benzinga — (LINK)

ChatGPT cheat sheet: Complete guide for 2023 — techrepublic — (LINK)

What Are Reasonable AI Fears? — source — (LINK)

Who Owns the Copyright to AI Creations? How Does AI Copyright Work? — makeuseof — (LINK)

Can we rely on AI cybersecurity — costs & disadvantages (exclusive report) — cryptopolitan — 22 September 2023 (LINK)

— Its conclustion: it brings many compelling benefits, including long-term.