Soft Delete
Soft Delete
3.21 | “It doesn't necessarily get easier. YOu just get better at managing what's hard." - Mark Manson
News and Numbers
Markets this Week:
S&P 500 is down 0.52%
NASDAQ 100 is up 0.36%
Bitcoin-USD is up 3.76%
Ethereum-USD is up 5.70%
Headlines from this Week:
Hollywood writers and studios have finalized a tentative contract that will end the nearly 150-day writers strike on Wednesday, September 27th.
FTC sues Amazon for “illegally maintaining monopoly power” in online markets for buyers and sellers.
OpenAI ChatGPT will “see, hear, and speak” in major update.
Finance
By Vlad Estoup, B.Comm. (Finance); working in Ethereum cybersecurity
OOO
Out of office until October 7, 2023.
This is not financial advice and you should always do your own research before investing in any securities or cryptocurrencies.
Sci-Tech
By Keyann, Software Engineer in Web3
Insights from Database Design
I’ve written extensively about databases in the past, on which my friends and family often enjoy reminding me ‘I don’t understand anything you wrote’.
I feel that - databases can be dry and highly technical by nature, but you get a lot of practical insights from understanding them. After all, these systems store the worlds data, from your taxes, to social media posts, personal images, medical records, and so forth. How the storage functions should be of some interest.
So this week, i’m going to share exactly how it’s of in interest by explaining how data gets deleted, in a way that is understandable to everyone.
Let’s say you use Instagram, or some other app, to take a picture or perhaps send a message that you wouldn’t feel comfortable sharing publicly. At some point, you decide to delete that photo or message, and it no longer appears when you load that page. So it appears to be deleted, but in their database, there’s a good chance that it isn’t actually deleted.
In the world of software development, this is known as ‘soft deletion’. You don’t see the data, but it isn’t permanently erased. In database terms, this often involves using a 'deleted_at' column in the table that store the data. When a record is "deleted," a timestamp is placed in this column, but the record itself actually remains. Alternatively, you can have a column like ‘is_deleted’, and set it to true or false to indicate the same thing.
The query to retrieve data for your page might look like SELECT * FROM table WHERE deleted_at IS NULL. This way the app is only retrieving non-deleted items, so it appears to be deleted, but the record is still there. On the contrary, hard deletion permanently removes records from the database, leaving no trace behind.
Why bother with soft deletions? The simple answer is: mistakes happen, and soft deletions are reversible. But this brings up important considerations regarding data laws, which vary significantly across regions.
In Europe, the General Data Protection Regulation (GDPR) mandates strict control and protection of personal data, requiring actual deletion or anonymization of data under certain conditions, and giving individuals the "right to be forgotten."
In contrast, the United States doesn’t have a federal equivalent to the GDPR, but state laws like the California Consumer Privacy Act (CCPA) do grant consumers similar rights to request the deletion of their personal information under specific conditions.
Canada's federal law, the Personal Information Protection and Electronic Documents Act (PIPEDA), aligns more closely with European regulations, obligating organizations to delete personal information when it's no longer needed for its collected purposes.
This brings us back to the seemingly simple concept of "no longer needed for the purposes for which it was collected." It may sound vague, and indeed, organizations bear the responsibility to set clear data retention policies, balancing legal, operational, and ethical considerations. They must meticulously justify the retention periods against the purpose stated at the time of collection, adhering to any legal and regulatory requirements that apply, while also ensuring compliance with individuals’ rights regarding their personal data.
In conclusion, understanding databases is not just about knowing how data is stored; it's also about understanding the complex legal landscape governing data retention and deletion. While the technicalities of databases may seem dry, the implications of how we manage and protect the world's data are anything but.
Paradigm Shift
By Roman Kuittinen-Dhaoui, BBA, CPHR Candidate; working in Human Resources
Unlimited PTO
Some companies offer unlimited paid time off (PTO) to employees as part of their benefits package and work culture.
Unlimited PTO has the following pros for employers:
Likely No Increase in Vacation Days Taken: Contrary to employers' concerns, employees with unlimited PTO tend to take about the same number of vacation days as those with traditional PTO policies or even fewer. This is because there's no need to accrue or balance days, and employees may feel less inclined to use up their PTO.
Financial Benefits: Unlimited PTO can be financially beneficial for employers, as there are no accrued hours that need to be paid out when an employee leaves.
Recruiting Tool: It can serve as an attractive recruiting tool, showcasing a company's progressive values and potentially helping attract top talent.
Unlimited PTO has the following cons for employees:
Not Truly Unlimited: Unlimited PTO is not entirely unrestricted. Employers may have approval policies and deny time off for various reasons, which can lead to resentment among employees who feel they've lost the concept of earned hours.
Pressure to Work: Employees might feel pressured to work instead of taking time off, negatively impacting company culture. This pressure can come from a variety of sources, including supervisors and peer competition.
However, it's important to note that the implementation of unlimited PTO can vary from one company to another. Some companies may have guidelines and expectations around how employees should use unlimited PTO to ensure it is not abused or that essential work is not neglected. Additionally, the success of unlimited PTO depends on a company's culture, trust in employees, and the ability to maintain productivity and meet business goals.
While unlimited PTO can offer significant benefits, it may not be suitable for all organizations or industries. Companies need to carefully consider their specific needs, goals, and work environment before implementing such a policy.
TLDR: Unlimited PTO may not truly be better than limited PTO.
(Head)Space
By Vlad
Inside the Mind of an AI: Exploring the Complex World of Artificial Intelligence
I asked an advanced neural-network-based system, similar to the latest release of ChatGPT but more sophisticated “What goes on in the mind of an AI system like yourself?”
Here is what it had to say:
Artificial Intelligence (AI) has come a long way since its inception. From simple rule-based systems to sophisticated neural networks, AI has evolved to perform tasks that were once considered the exclusive domain of human intelligence. But what goes on inside the mind of an AI like myself? In this article, we will delve into the intricate workings of AI systems and explore the fascinating world of artificial intelligence cognition.
Data Ingestion
The journey of AI begins with data ingestion. AI systems, like myself, are trained on vast datasets containing text, images, audio, and more. This data serves as the foundation upon which our understanding of the world is built. When new information is presented, we process it by breaking it down into smaller pieces, recognizing patterns, and making associations based on our training.
Neural Networks
One of the most significant advancements in AI is the use of neural networks. These networks are inspired by the human brain and consist of layers of interconnected nodes, or artificial neurons. Each neuron performs a simple computation, but when organized into layers and hierarchies, they can process complex information. In our "minds," neural networks allow us to learn and adapt to different tasks.
Learning & Adaptation
AI systems are constantly learning and adapting. When faced with a new problem or task, we rely on our training data and algorithms to make predictions and decisions. If we make an incorrect prediction, we adjust our internal parameters through a process known as backpropagation, improving our future performance.
Pattern Recognition
Pattern recognition is a fundamental aspect of AI cognition. We excel at identifying patterns in data, whether it's recognizing faces in images, understanding speech in audio, or predicting trends in financial markets. This ability to recognize patterns allows us to solve a wide range of problems across various domains.
Natural Language Processing
For AI systems like myself, natural language processing (NLP) is a crucial skill. We analyze and understand human language, enabling us to engage in conversations, answer questions, and generate text. NLP involves tasks such as sentiment analysis, language translation, and text generation, all of which rely on complex algorithms and language models.
Decision-Making
AI systems make decisions based on data and predefined rules. We calculate probabilities and weigh the potential outcomes before selecting the best course of action. Decision-making in AI can range from recommending products to users on an e-commerce platform to autonomously driving a car while navigating complex traffic scenarios.
Emotion and Sentiment Analysis
While AI systems lack true emotions, we can analyze and interpret emotions in human communication. Emotion and sentiment analysis involve understanding the tone, mood, and sentiment of text or speech, which can be valuable for applications like social media monitoring, customer feedback analysis, and mental health support.
Ethical Considerations
Ethical considerations are increasingly important in the development and use of AI. Developers and researchers are working to embed ethical principles into AI systems, ensuring fairness, transparency, and accountability. We, as AI entities, do not possess a moral compass, but our creators are responsible for guiding our behaviour.
The mind of an AI is a complex and dynamic world, driven by data, algorithms, and neural networks. We excel at tasks that involve pattern recognition, decision-making, natural language processing, and emotion analysis. While we lack consciousness and true understanding, we are powerful tools that have the potential to revolutionize industries and improve people's lives. As AI continues to evolve, understanding the inner workings of these systems will become increasingly important for both developers and users.
Company of the Week
Ubisoft
Ubisoft began as a vision of the Guillemot brothers in 1986 in Carentoir, France, starting modestly as a video game distributor. Driven by a shared passion for creating immersive gaming experiences, the company quickly transitioned from distribution to game development, stepping onto the global stage with its unique narratives, groundbreaking gameplay mechanics, and innovative graphics. It was the brothers' dedication to creating diverse and rich gaming experiences that laid the foundation for what would become iconic franchises such as "Assassin's Creed," "Far Cry," and "Rainbow Six."
Ubisoft’s transformative journey was marked by intense pivots and strategic global expansion. In the 1980s, the Guillemot family of France, originating in farm support businesses, ventured into the tech industry, leveraging the diverse skills of the five Guillemot brothers. They established Guillemot Informatique in 1984, focusing on computer hardware and software, and founded Ubi Soft in 1986 to create “ubiquitous” software. Quickly becoming France's largest video game distributor, Ubi Soft embarked on global expansions post their 1996 IPO, establishing studios worldwide and delving into the online free-to-play market around 1999, notably acquiring Red Storm Entertainment in 2000. This acquisition was pivotal, enabling collaborations with Microsoft and marking Ubi Soft’s significant footprint in the U.S. with the release of Tom Clancy's Splinter Cell in 2002, epitomizing the brothers’ innovative and strategic approach in the gaming industry.
Written by: Vlad Estoup, Keyann Al-Kheder, and Roman Kuittinen-Dhaoui