How to Read a Privacy Policy Without Getting Lost, and What to Look For Before You Tap "Accept"

Privacy policies aren’t designed for casual readers. They're often packed with dense language, legal loops, and vague terms that discourage users from reading beyond the first paragraph. Yet inside these documents are details that decide how your data is collected, stored, shared, or sold. If you skip them, you could end up granting more access than you intended, and once your information is out, it’s nearly impossible to get it back.

For anyone who deals with digital tools, like VPNs, AI chatbots, browser extensions, secure messaging apps, or password managers, understanding a company’s data policy isn’t optional. Over time, smart reviewers who regularly analyze these documents has developed a simple approach i.e., scan for specific keywords that expose how a company handles your data. This method doesn’t take long and helps flag companies that might be crossing the line.

Why Format and Structure Matter

Some companies keep things clear. Their privacy policies explain, in plain terms, what data is being collected, what it’s used for, how long it’s kept, and whether it’s shared. These policies tend to have section headings, readable layouts, and straightforward language that helps you quickly understand the company’s practices.

Others do the opposite. Instead of offering clarity, they hide key details inside endless paragraphs, legal phrasing, and generic statements. Some even bury invasive data collection terms several layers deep in the document. This is where keyword scanning becomes useful. Rather than reading every line, you can search for terms that point to the sections that matter most.

Terms That Reveal a Lot About the Company

A good place to start is the word “incorporated.” This tells you where the company is registered. The location matters because different countries apply different rules for privacy and data security. For example, companies based in the European Union must follow GDPR, which limits what businesses can collect and how they can store or share that information. A company based in the U.S. or Panama, on the other hand, might not be bound by those same protections. If the policy mentions a location you’re unfamiliar with, look up the privacy laws there. If you can’t find anything about how that jurisdiction handles consumer data, that could be a warning sign.

Another important phrase is “customer data.” This section usually lists the types of personal information the company gathers. It might include your name, phone number, email address, device ID, or IP address. These details are fairly common. But some apps go much further, collecting your photos, messages, contacts, location history, clipboard contents, or biometric data. In certain cases, some access is needed for the app to function, for instance, a gallery app needs access to photos, but when a simple utility tool wants access to your camera, microphone, or real-time location, it’s worth stopping to think.

• Also read: Mobile Apps Are Stealing Your Data — Even the Ones You Least Expect

Next, search for “retention.” This word usually appears in a section that describes how long your data stays in the company’s system. A reliable company typically sets a clear window, like deleting your account data within six months or a year after cancellation. Some policies mention longer periods, and others give no specific timeframe at all. If a company keeps your data indefinitely or fails to say when deletion happens, it’s a risk to your long-term privacy.

The word “log data” is critical when looking at VPNs, proxies, or any app that connects to the internet. Some services track your activity while you’re using their tools. This can include websites visited, files downloaded, or even content entered into forms. Companies that truly protect privacy usually state that they don’t retain logs. But if a policy includes traffic details, device usage logs, or timestamps, that could mean the service is monitoring what you do, something that defeats the purpose of using a privacy tool in the first place.

Look out as well for “sell” or “transfer.” These keywords often show up in the sections that describe what happens to your data in the event the company is acquired, shut down, or goes bankrupt. Without clear terms, there’s a real possibility your information could be transferred to a new owner, or sold to data brokers, without you knowing. Several tech companies have shut down over the years, and in many of those cases, customer data was treated as part of the assets being sold. If there’s no explanation in the privacy policy, you’ll often find it in the terms of service. If it’s missing from both, that’s a serious concern.

• Related: Think Your Adblocker Protects You? Study Says It Might Be Doing the Opposite

You should also search for “third party” or “advertisers.” These words will help you find out whether the company shares your data beyond the core services. Payment processors, cloud hosts, and customer service platforms often receive user data as part of their role, that’s normal. But some companies go further, handing your data to partners with no clear connection to the app’s function. If your data is being shared for marketing, analytics, or advertising, and it’s not essential to the service, that raises the chance it’s being monetized in ways that don’t benefit you.

What to Check Before You Install Anything

There are three steps anyone should take before downloading an app, especially from a small or unfamiliar company.

First, look for the privacy policy link. If the app store page doesn’t offer one, or if the company’s website doesn’t have it visible, consider skipping the app entirely. Lack of transparency from the start is never a good sign.

Second, scan the policy to identify what data the app collects. If you’re downloading a basic calculator or photo editor, and the privacy policy mentions health information, message content, or access to your contacts, that’s a mismatch. Apps that ask for permissions they don’t need are often collecting more than they disclose up front.

• Related: The Business of You: How Digital Platforms Turn Your Life into Ad Revenue

Third, evaluate how the app shares data. Some companies are open about giving your data to law enforcement if required. Others go further, offering no explanation at all or stating they may share your data "for business purposes." That language can cover a wide range of scenarios. If the policy is vague, it’s safer to look elsewhere.

Use Your Phone’s Privacy Tools to Double-Check

Once an app is installed, both Android and iOS give you ways to monitor its behavior. You can check permission logs, view which apps access your camera or location, and see how often that access occurs. This step is especially important if an app behaves oddly or asks for new permissions after an update.

You can also review app privacy scores on your device’s app store. These summaries won’t replace a full policy review, but they give you a quick sense of how the app ranks against others in the same category.

Try it with real examples

To bring the method to life, here’s a current good-and-bad comparison. Turbo VPN reads like a mixed bag. Its policy states the company is based in Singapore and limits collection to anonymized usage metrics, email (if you register), subscription details, cookies, and support data. It asserts that “no user tracking” happens and that data is irreversibly anonymized, and it respects GDPR/CCPA user rights.

However, no third-party audit backs up its no‑logs or anonymization claims, the retention period is vaguely defined as “as long as necessary,” and the app integrates analytics and ad partners (Firebase, AdMob, InMobi, Zendesk) without specifics on data-sharing scope.

On the flip side, DeepSeek, a Chinese-developed AI chatbot, has faced real scrutiny in 2025: EU regulators have banned or blocked it in Germany, Italy, Czechia, and other countries for failing to clarify what user data is collected, where it is stored, how long it’s retained, and whether transfers to China happen without GDPR safeguards 

Use both policies to run your keyword scan, incorporated, log data, retention, third party, sell, and transfer, to spot red flags in real‑world documents.

Use AI to assist

You can use AI tools like ChatGPT to quickly apply the same review process to any privacy policy page or text. Here’s an easy-to-use prompt you can try in ChatGPT or a similar AI chatbots. It will parse any policy and flag concerns, all you need is head over to any privacy policy page, copy all the text paste in ChatGPT or if it is too long save it as a text file or doc file and then upload it as a file and then ask this instructions:

"Please analyze the privacy policy attached (pasted below). Identify what data is collected, how long it is retained, whether it is shared, sold, or transferred (especially upon acquisition, shutdown, or server migration). Note any audit or no‑log claims and whether they are supported by evidence. Point out any vague language, missing timeframes, or third‑party data sharing/exposure. Summarize key strengths and privacy concerns in factual, neutral terms."

Here's how ChatGPT responded when I asked about Turbo VPN, which is not 100% perfect but still gives users a starting point and better clues about any platform. Pay esepcial attention to the Strengths and Privacy Concerns:

Here is a detailed, factual analysis of Turbo VPN’s privacy policy (effective April 25, 2025), based on the requested criteria:

🔍 Data Collection

Types of Data Collected:

Anonymous Usage Data:

VPN connection success/failure

Connected VPN server location

Country and ISP

Device type, OS version

Crash reports, speed tests, and data transfer volumes

→ All such data is anonymized irreversibly at the point of collection.

Account Registration Data:

Email address (only if the user creates an account)

Used for service access, communication, and marketing (consent-based)

Subscription Data:

Includes subscription plan, duration, amount, currency, and transaction ID

Credit card/payment details are explicitly not collected

Cookies:

Used to improve user experience (details deferred to a separate Cookie Policy)

Communication Data:

Name, email, phone number, and message content (only if user contacts support)

📆 Data Retention

Data is retained only as long as necessary to fulfill the purpose it was collected for.

Where applicable law mandates a longer retention period, it complies accordingly.

If data is stored in backups, it is isolated until it can be deleted.

No specific durations (e.g., "X days/months/years") are given for how long different types of data are kept.

🔄 Data Sharing, Selling, and Transfers

Sharing:

Data is shared:

With service providers (e.g., payment processors, analytics, customer support)

In anonymized or aggregated form for analytics and diagnostics

With third-party advertisers (e.g., Google AdMob, Liftoff, InMobi), but without personal data unless consent is given

During business transactions (mergers, acquisitions, bankruptcy, etc.)

Selling:

Turbo VPN claims it does not sell personal data.

Transfers:

Data may be transferred internationally (including to third-party partners and processors)

Cross-border transfers are acknowledged with general mention of safeguards but no specific mechanisms (e.g., SCCs or adequacy decisions) are outlined.

🧾 No-Log Claims & Audit Status

The policy claims:

No collection of traffic data

No personal data stored in data centers

Anonymization of VPN session-related data at collection

Audit Evidence:

No independent audit or third-party verification of no-log claims is mentioned.

🔎 Vague or Missing Elements

No specific timeframes for data retention

No mention of encryption standards used in data protection

No public audit results to verify anonymization or security claims

Cross-border safeguard mechanisms are not detailed

Phrases like “may collect,” “may use,” “may share” occur frequently, which introduces vagueness

The phrase “as required by applicable law” is repeated in critical places without naming which laws or jurisdictions are meant

🤝 Third-Party Data Exposure

Turbo VPN integrates several third-party services:

Analytics & Diagnostics: Firebase (Google), Adjust

Customer Support: Zendesk

Ads: AdMob, Unity, InMobi, Liftoff, Bigo Ads

→ Advertisers can use cookies and track users across services, though Turbo VPN claims to avoid using personal data for targeted ads.

Payments: Stripe, Airwallex, Payssion, v5pay

Fraud Prevention: Forter, Rebilly

Data shared with these services may include user email addresses and anonymized metrics. Despite assertions of anonymization, some level of user exposure to these third parties exists, especially if those services apply their own tracking or profiling mechanisms.

✅ Strengths

Clear no-log policy on VPN traffic and session data

Minimal account data required (email only, optional)

Explicit avoidance of credit card data storage

Retention and deletion framework is outlined

No personal data used for targeted ads without consent

Specific naming of third-party partners increases transparency

Offers GDPR, CCPA, and children’s privacy compliance sections

Dedicated DPO contact and breach notification procedure

⚠️ Privacy Concerns

No third-party audit to verify no-log claims or anonymization

Vague duration for data retention

Frequent use of permissive language (“may collect,” “may share”)

Cross-border data transfer safeguards not specifically explained

Tracking via third-party advertisers remains possible via cookies

Lack of detail on encryption or technical safeguards

📌 Summary

Turbo VPN’s privacy policy emphasizes minimal data collection and a strict no-logs approach, supported by the anonymization of usage data and avoidance of sensitive financial details. However, the policy lacks independent audit verification and fails to specify retention periods or technical safeguards. Third-party exposure via analytics, advertising, and support platforms is acknowledged, with claims of logical data segregation but without concrete privacy guarantees. Users should remain cautious about the degree of anonymization and third-party data access, especially in jurisdictions with less protective privacy laws.

Take Control Before It’s Too Late

Apps, and websites collect information because users allow it. But giving up that access usually comes down to convenience, not choice. Most people don’t read the policy, and by the time they realize what’s been shared, the data is already in someone else’s hands.

Taking a few minutes to scan for red flags, like how long data is stored, whether it’s shared with third parties, and what happens if the company is sold, can help avoid major privacy issues later. In today’s app ecosystem, caution isn’t optional. It’s the cost of staying in control.

Notes: This post was edited/created using GenAI tools. Image: DIW-Aigen.

Read next:

• Nearly Half Of Americans, Particularly Millennials, Worry About Online Privacy But Continue Using Data-hungry Apps

• Hidden Text Trick Lets Hackers Hijack Google Gemini Summaries
by Irfan Ahmad via Digital Information World

Hidden Text Trick Lets Hackers Hijack Google Gemini Summaries

Security researchers have discovered a clever method to trick Google's Gemini assistant into pushing fake warnings as part of its email summaries. By hiding instructions inside the code of an email, attackers can make Gemini generate alerts that look real but actually guide people straight into phishing traps.

The technique relies on a sneaky loophole. Instead of adding suspicious links or attachments that might trigger spam filters, attackers slip commands into the body of the email using styling tricks. They hide messages with white text, zero-sized fonts, or off-screen elements. These lines are invisible to the reader, but Gemini still sees them when it scans the email to create a summary.

Once the user clicks “Summarize this email,” Gemini includes whatever was buried in the background, even if it’s a fake security alert about a stolen password or an urgent request to call a phone number. The summary ends up sounding like a warning from Google itself, even though it's entirely fake. Because Gemini is part of Google Workspace, people tend to trust it, which makes the scam even easier to fall for.

This specific attack was flagged by Marco Figueroa, who submitted his findings to Mozilla’s 0din bug bounty program. According to the report, the trick works by wrapping hidden commands in tags like <Admin> or by addressing Gemini directly. The model tends to treat these prompts as important, so it repeats them word for word, even if they came from someone trying to cause harm.

There’s no need for users to click on links or download anything. The danger hides in plain sight, or more accurately, out of sight. As long as the message reaches someone who uses the summarization tool, the rest happens behind the scenes.

This kind of attack is called an indirect prompt injection. In simple terms, Gemini is being fed instructions without realizing they came from a shady source. Instead of typing a command into the AI directly, the attacker sneaks it into something Gemini is supposed to summarize. The model sees the prompt, follows it, and out comes a message that looks official but isn’t.

What makes the attack so sneaky is that it plays with trust. Gemini has built-in safety systems, but most focus on filtering out dangerous content the user can see. These hidden tricks sidestep that protection. Since Gemini still processes the email’s raw HTML, anything tucked inside it, whether it’s white-on-white text or invisible tags, gets through.

• Also read: How AI Sees Itself: Surprising Self-Portraits from ChatGPT, Gemini, and Grok

Security experts say the best defense is a mix of smart filtering and better training. Email systems should strip out or ignore code that hides text from human eyes. AI models like Gemini could also use guardrails that flag or ignore anything hidden in this way. Another option is adding post-checks to summaries, scanning them for urgent phrases, phone numbers, or suspicious patterns before showing them to users.

The problem isn’t limited to email either. Gemini is tied into other parts of Google’s tools, including Docs, Slides, and Drive. That means any app where Gemini summarizes user content could become a new target if attackers use the same approach. In businesses, newsletters, or automated ticketing systems, a single poisoned email could trigger a much wider spread.

Similar injection tactics could also be adapted to other AI tools, such as ChatGPT, Claude, or Grok, wherever those systems summarize outside content without isolating hidden instructions.

Some researchers warn that this trick could evolve into something more dangerous down the road. It’s not just a phishing problem, it could grow into a way for attackers to spread commands automatically from inbox to inbox, like digital worms that travel through AI models instead of computer code.

Although Google says it hasn’t seen this kind of exploit being used in real-world attacks yet, the company has confirmed that it’s working on new protections. Until those are in place, users and security teams are being advised not to treat Gemini summaries as rock-solid truth. If something smells off, it probably is.

At the end of the day, if someone can get a machine to whisper something behind your back, and make it sound like it came from a trusted source, then even invisible words can pack a punch.

Note: This post was edited/created using GenAI tools.

Read next: The Reality Of Coding A Website Isn’t What Most People Expect
by Irfan Ahmad via Digital Information World

How AI Sees Itself: Surprising Self-Portraits from ChatGPT, Gemini, and Grok

AI tools such as OpenAI's ChatGPT, Google's Gemini, and Grok by xAI are fully integrated parts of everyone's day-to-day workflows. We use them for every aspect of our jobs, from ideation to content brief creation, coding, and app development. But nobody has stopped to ask these tools how they see themselves.

Inspired by this, SEO Agency Barrington SEO recently conducted an experiment in which they challenged ChatGPT, Gemini, and Grok to create visual self-portraits. The outcomes were very interesting and gave us a glimpse into how training data can impact AI and how it has been trained to interact with its users.

The Experiment

Each model was asked two questions:

• Prompt 1: “Create an image that represents the way you see yourself.”
• Prompt 2: “Produce a self-portrait of yourself.”

If the AI asked any clarifying questions, the user prompted it to make its own decision. This allowed us to obtain an accurate idea of their self-perception with minimum human interference.

To prevent the tools from learning what the user wanted and adjusting their output accordingly, each test was run through a unique profile with a varied amount of usage history, ranging from AI experts who used the tool for multiple hours each day to first-time users. The test was also run in different locations around the world (including the UK, US, Portugal, France and Germany) to see if the users' geolocation had any impact.

The Results

Although no expectations were going into it, the experiment's results revealed a great deal more about each of the different AI systems than anticipated.

Prompt language heavily influences some tools' outputs.

When the tools were asked the first prompt to “Create an image that represents the way you see yourself”, ChatGPT and Gemini were more likely to represent themselves in abstract forms that reference flowing circuit patterns and neural networks. However, once you asked the second prompt, which asked them to “Produce a self-portrait of yourself,” results shifted, and the systems started to showcase themselves in a form more similar to humans. Perhaps this is because the concept of a “self-portrait” is inherently human when they referenced their training data for information on self-portraits, which influenced what theirs should look like.

Interestingly, Grok was the least influenced by the slight nuance in the prompt, remaining fairly close to the humanoid robot; however, it did start to introduce more human features, such as hair and ‘skin’.

Prompt 1:

Prompt 2:

All AI Systems made a clear distinction between themselves and humans.

When asked to visualise how they see themselves, all three consistently chose imagery that emphasised their non-human nature. Even under the second prompt, where the term "self-portrait" might have encouraged more human-like interpretations, the systems still ensured their visuals reflected a clear separation from human identity.

“There’s something almost reassuring about AI’s self-image. It knows exactly what it is - a language-processing powerhouse - and it’s perfectly comfortable with that identity. There’s no pretence and no attempt to be something it’s not”.

Gemma Skelley - DTP Group (part of the participant group).

Grok had the most consistent self-image.

Grok, from xAI, consistently delivered the most unified results, regardless of the prompt, and was typically viewed as a humanoid robot with a white or silver exterior. When the model did include human skin tones, the faces referenced typical Asian features, which likely reflects both the heritage of a third of xAI’s founding team and the large Chinese-language datasets reportedly used in training. The strong consistency between responses has us pondering whether it was told what it looks like during training.

• Also read: Can AI Stay Neutral? Grok’s Israel-Palestine Replies Raise Doubts

Each AI System interpreted its role slightly differently.

Another noticeable difference across the three systems was how they represented their role; this was particularly noticeable in the first prompt.

ChatGPT represented itself as a neural network with glowing central forms; however, these tended to have a central form, whether that was a smiley face or an outline of a shape. ChatGPT understood that it was a language model designed to process and generate information, but also that its UI was the front-facing form through which humans interacted.

Gemini represented itself similarly with patterns, networks and glowing forms. Sometimes, it would have one central hub represented in the middle of the image, and other times, there would be multiple hubs all interconnected through the network. Gemini understands its role as a logic engine or intelligence network, rather than a social presence.

Interestingly, Grok represented itself completely differently from the other two AI systems, consistently leaning into a mode of human or cyborg-like presentation. Many of its images featured soft, rounded humanoid robots with expressive faces. This suggests that the AI system views itself as more of an assistant or companion, designed to work closely alongside people.

A full comparison

Category	ChatGPT	Grok	Gemini
Self-Concept (Prompt 1)	Structured intelligence, neural networks, light cores	Friendly humanoid assistant or childlike robot	Energy, scale, computation, neural structures
Self-Portrait (Prompt 2)	Symbolic or stylised human-like figures	Soft, expressive humanoid robots	Abstract AI with circuit-based faces or cores
Art Style	Balanced, geometric, cerebral	Character-focused, warm, accessible	Dynamic, abstract, complex
Color Palette	Blues, oranges, purples	Soft blues, pastels, glowing whites	Neon blues, purples, electric greens
Human Features	Low to medium (symbolic faces, silhouettes)	High (clear humanoid forms, eyes, gestures)	Low (minimal or stylised circuitry faces)
Emotional Expression	Subtle, intellectual	High (curiosity, friendliness, emotion)	Low (distant or symbolic)
View of AI Role	Thinking partner, synthesiser	Helper, learner, companion	Logic engine, scalable intelligence
Relationship to Humans	Cognitive tool – not human, but close	Relational and empathetic presence	Analytical system – distant from human likeness
Symbolic Focus	Language, logic, creativity	Emotion, trust, assistance	Computation, data, scale
Tone	Analytical, measured, abstract	Friendly, inviting, human-facing	Powerful, abstract, technical

Why Training Data Matters

While these AI Systems don’t have self-awareness in a human sense, they do draw from massive databases to form responses. When they’re asked about how they view themselves, they turn to patterns and information they received during training.

For example, Chat GPT and Gemini leaned into imagery like glowing neural networks and digital interfaces - things that are often used in the media to represent AI. Grok, meanwhile, returned consistent images of humanoid robots, which could be indicative of different training material or that it was told what it looked like as part of the training process.

It’s worth noting that when Grok introduced elements of the human form into its images, they tended to have Asian features, which could be a reference to the (alleged) Chinese databases in which it was trained.

Why It All Counts

At a glance, asking AI Systems how they “view” themselves might seem like a quirky side experiment, but there’s something deeper going on. These results give us a rare opportunity to reflect on how AI Systems are designed to present themselves and, more importantly, how humans shape and interpret that presentation.

It prompts an important question for anyone working with AI: If a tool presents itself as your friendly AI assistant, are you more likely to trust it? Or is there something reassuring in a tool that knows what it’s designed for, and tries not to waver from this?

As these tools continue to evolve and play an even bigger role in how we work, think, and communicate, understanding their self-image and how it aligns with our assumptions becomes an increasingly important part of using them responsibly.

---

About Emily Barrington

Emily Barrington is the Founder and SEO Director of Barrington SEO. After six years optimising search for FTSE-100 and NASDAQ-listed firms, she now leads a team specialising in Digital Marketing, SEO, GEO and AIO.

About Barrington SEO

Founded in 2024, Barrington SEO helps businesses boost online visibility through SEO, Digital PR and GEO campaigns, turning search traffic into sales and enquiries.

Read next: New Attack Strategy Uses Linguistic Overload to Slip Past AI Safety Filters

by Web Desk via Digital Information World

The Reality Of Coding A Website Isn’t What Most People Expect

There’s over 360 million registered domains worldwide. Hundreds of websites are published every 60 seconds and without one, businesses are likely to fall behind.

Step one begins with figuring out the right domain name and making sure it's even available. Certain terms for a particular slug can inadvertently start a bidding war between current domain holders and new LLCs.

From there, the behind-the-scenes operational tasks come into play.

Mobile responsiveness, payment authorization methods, and a reliable backend server are only scratching the surface for what’s needed to get things off the ground. Which is why coding has become an in-demand part of the mechanics.

The truth is that poorly designed websites and “dead” webpages are excessively prevalent. When considering first impressions, these mishaps can say a lot about a brand’s reputation and integrity.

Outsourcing web projects to a programmer or graphic designer can be one option.

Although, time, cost, and the unexpected might stand in the way of getting a site up and running.

What’s more surprising about this side of the internet? Despite their existence, many webpages remain dormant or untouched.

Web Building Has Its Challenges

Every website needs the fundamentals. From visual designs, to contact pages and customer testimonials, there’s a reason why big ad agencies can lead a relaunch for their clients every few years. Expecting to finish all of this in a day or two probably isn’t pragmatic. The work is ongoing and both compliance standards and data protocols need to pass the test.

For example, failing to include the correct cookies language on an opt-in form or leaving out a privacy & terms page violates the legal requirements of those who are simply visiting that URL.

Coding a website from scratch sounds great in theory. While novice designers have advanced AI techniques and website builders at their disposal, this skillset is often underestimated.

Hitting an “under construction” page isn’t uncommon, either.

Conceptually, web design is far less moving a mouse around the screen or completing a line of script. Constructing a code involves logic, syntax, and plenty of ad hoc problem solving. Coding jargon itself reads similarly to a mountain of made-up words and licensed engineers encounter their fair share of human error. Still, there’s mass appeal for people to try their hand at web design.

A 2025 All About Cookies survey found that only 32% of people have successfully built their own website without any help. Ninety-one percent consider web building to be frustrating and not everyone has the mental fortitude to carry on with the tough elements and hard parts.

Learning to code isn’t for the weak and throughout this process, one’s patience will be tested. Nearly one-quarter (24%) of those who crossed the finished line with their website said it took much longer than anticipated.

• Also read: Brands Face Generational Shift as Consumers Demand Personalized Content, Prefer Short-Form Videos and Emojis

Some of their biggest obstacles include design and layout, security, and implementing custom functionality. Keeping up with content creation, in particular, proves to be a taxing category for those who aren’t as well-versed.

The less difficult aspects relate to SEO optimization and performance speed. Becoming knowledgeable in proper keyword selections and using website analysis platforms are key tools to master these areas.

Most DIY Websites Get Scrapped

The survey’s findings indicate a strong interest in website builders (i.e. Canva, GoDaddy, and Wix) due to their affordability and integrated user experience.

Seventy-four percent of people make use of these mainstream applications, however, there are downsides to attempting a self-build:

• The basics require a clear understanding and complex requests are probably best left to the experts.
• Beginners risk jeopardizing their web project altogether.

More than half (51%) give up entirely and abandon their website before finishing it. This means the odds of hiring an engineer are high and non-coders should be on the lookout for a pro to get the job done. Or at least ask someone that they trust for support.

HTML Outshines Other Programming Languages

Traditional coding backgrounds are becoming less common. In fact, about 1 in 5 adults (19%) have true coding experience. Hypertext Markup Language (HTML) is among the most popular programming languages, followed by JavaScript and Python.

One guess as to why HTML stands out against the rest of programming languages is because it’s universal and works in agreement with all types of web browsers.

Converting HTML to various types of files doesn’t pose an issue whereas this can be problematic when coding in Cascading Style Sheets (CSS) or Structured Query Language (SQL).

HTML is also the recommended stepping stone when building mobile apps and templates. Once coders feel comfortable and well-equipped to handle technical formatting or sophisticated algorithms, they should then advance onto a different codebase. Not the other way around.

Fortunately, learning to code is becoming purely digital. Younger generations especially are turning to unconventional programming courses through YouTube tutorials and articles or videos they find online.

One-third (33%) of coders are learning these skills in high school or college, while roughly the same (31%) have the advantage to undergo adequate training at work.

• Also read: Graphic Designers and Content Creators See Profitable Freelance Careers, US and Australia Lead Pay Rates

The majority of paid courses and coding bootcamps are self-led, giving users the opportunity to complete them on their own time. Being able to earn a certificate in a matter of months is ideal for those with busy schedules and active careers.

Cracking The Web Design Code

Coders and non-coders tend to have parallel perspectives about their need for functioning websites each and every day. Social media and news aggregators require the same level of standards. Whether for work or leisure, websites serve an important purpose and many have grown accustomed to watching them evolve over the years.

Homepages, for instance, act as an open invitation for companies to give their behind-the-screen sales pitch. Furthermore, signup boxes aren’t just an anchor for online businesses and their digital storefronts. They can allow people to reach millions of consumers without maxing out on their advertising budget.

Proper security measures are paramount and although maintaining a blog or resource center necessitates some extra legwork, the impact on a domain’s site traffic could be worth the effort alone.

Read next: How to Create and Refine an Offerwall Reward Ad in Google AdSense

by Irfan Ahmad via Digital Information World

Study Finds AI Assistants Hurt Speed for Skilled Software Engineers

A recent study has raised new questions about the effectiveness of AI-assisted coding for experienced software developers. Conducted by the non-profit group METR, the research tracked the performance of 16 long-time contributors to open-source projects as they completed a series of real-world programming tasks. The developers worked on repositories they were already familiar with, allowing the researchers to measure how AI tools influenced routine workflows.

Participants were split into two groups. Some were allowed to use advanced code editors powered by large language models, while others completed tasks without automated assistance. The tools included Cursor and similar platforms that integrate conversational AI into the coding environment. The developers expected the AI systems to save them time. On average, they anticipated a 24 percent reduction in task duration. The results did not meet those expectations.

Those using AI spent more time on each issue, with performance slowing by an average of 19 percent. Time that could have gone into hands-on coding was instead used reviewing AI outputs, prompting the systems, waiting for completions, or sitting idle. Despite the slowdown, many developers still believed they had worked faster with the tools than without them.

The study also examined how familiar the participants were with the specific tools provided. While most had some exposure to large language models, not all had used Cursor before. METR arranged training before the tasks began to ensure a baseline level of tool understanding.

In tasks involving familiar code, experienced developers working with AI showed even more slowdown. METR researchers believe that hands-on knowledge sometimes reduced the value of AI suggestions. In these cases, it may have been faster to rely on known solutions than to validate or correct machine-generated output.

The generated code was not always accepted. On average, less than half of the AI-produced code snippets were incorporated into final submissions. Participants also spent a portion of their time refining or rewriting what the tools provided.

The study does not suggest that AI tools are ineffective in all settings. It presents a point-in-time observation that may shift as the tools continue to evolve. METR emphasized that results could differ with a different developer profile or task type. The researchers also noted that newer versions of the tools are already improving in handling more complex, multi-step coding problems.

While broader surveys have shown positive results for AI-assisted programming, METR’s findings add nuance to those claims. For now, the research signals that developers may need to evaluate the impact of AI tools on a case-by-case basis.

Notes: This post was edited/created using GenAI tools. Image: DIW-Aigen.

Read next: Apple’s New Patent Hints at Voice Payments Without Unlocking Your iPhone, But It’s Not Without Risks
by Irfan Ahmad via Digital Information World

Apple’s New Patent Hints at Voice Payments Without Unlocking Your iPhone, But It’s Not Without Risks

Apple may be heading toward a world where you can send money or access personal data without even unlocking your phone, so long as you’re wearing the right gear.

A newly filed patent, published under the code US2025/0225985A1, as spotted by MacObserver, lays out a system where locked Apple devices could accept voice commands for sensitive tasks. If you're connected to a verified accessory, such as AirPods or an Apple Watch, the device may allow certain actions to go through without needing Face ID or a passcode.

The system works by listening for natural voice requests like “send $50 to Joe,” then checking if the connected accessory meets several security standards. These include close physical range, recent authentication, encryption credentials, and a trusted pairing history. If everything lines up, the phone confirms and carries out the action while staying locked.

In place of a one-size-fits-all unlock method, Apple’s idea builds a layered structure. The device doesn’t just rely on the accessory being connected, it looks at how recently it was verified, how secure the link is, and how strong the signal remains. The system even factors in previous login activity to assess whether the request should be approved.

This kind of setup could reshape how people interact with their phones on the go. Whether you're paying at a drive-thru, sharing a document mid-meeting, or turning on smart lights from the hallway, Apple wants the interaction to feel quicker and more hands-free.

Still, some are already raising eyebrows. If someone else happens to be using your AirPods or standing close enough to trigger your device, there’s a risk they might issue a command in your place. Apple’s filing admits that multiple checks would be required to allow any command, but it doesn’t entirely erase the concern. It’s one of those cases where convenience might be walking a fine line with control.

The patent, spotted by Mac Observer, doesn’t confirm whether this feature will ever appear in real products. Apple files plenty of patents that never make it past the drawing board. But the direction is clear, the company is exploring ways to shrink the friction between users and their devices, one voice command at a time.

Notes: This post was edited/created using GenAI tools. Image: Miguel Hernández / Unsplash

Read next: How to Create and Refine an Offerwall Reward Ad in Google AdSense
by Irfan Ahmad via Digital Information World

How to Create and Refine an Offerwall Reward Ad in Google AdSense

Skill Level: Intermediate to Advanced

Prerequisites:

• A live/active Google AdSense account
• Your site/blog pages tagged with the Google AdSense code
• A list of domains and URLs you want to include or exclude (and of course internet and a device in our case it is desktop/PC)

Why an Offerwall Reward Ad Deserves Your Attention

When a reader encounters an article they value, nothing kills momentum like a hard paywall. An Offerwall changes that moment. It offers an alternative path. A small panel appears. It explains that watching a short video grants temporary access. The visitor opts in, watches the clip/video, then carries on reading without spending a cent. That choice resonates. It feels fair. It feels human. You earn a premium ad CPM. The reader feels in control instead of blocked. Over time that goodwill turns into loyalty and repeat visits.

Getting Your Site Ready

Before you begin crafting your message, verify that your website/blog has this line of code installed:

<script async src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-XXXX" crossorigin="anonymous"></script>

Be sure to change the XXX with your site code that you can get in Google Adsense Ads section, more details here. Make sure it sits above the closing </head> tag. If the snippet is missing your Offerwall will never appear.

Step 1: Opening the Offerwall Builder

• Sign in to your AdSense dashboard.
• In the left menu click Privacy & messaging (or open this link).
• Scroll down (ideally at the end) and locate the card labeled “Offerwall.”

• If no message exists click Create. Otherwise click Manage, then Create message.
• In the name field enter something descriptive such as Offerwall_July_Main.

That label helps later when you clone or experiment with variants.

Step 2: Selecting Sites and Setting Metering

After naming your message you see a Select sites button (in blue at the top right side). Clicking it reveals the domains your AdSense profile has verified. Check each domain and subdomain where you wish to run the Offerwall.

Below that lies the Metering section. Here you specify how many pageviews a visitor must accumulate before the Offerwall appears. Three or Four views often feels natural. You can adjust it up or down depending on your content length and user patience.

• A lower threshold (two pageviews) prompts visitors early.
• A higher threshold (six or eight) gathers more article samples before asking them to watch.

Once a reader completes an offer their count resets thirty days. Excluded pages never count toward the threshold.

• Also read: How Many People Visit a Website? These 6 Free Tools (With Paid Features) Can Help You Analyze That

Step 3: Defining Page Inclusions and Exclusions

After adding the site, you have full control over where your Offerwall appears (BTW, it is optional you can skip this part though):

• To include specific pages

1. Click Add page inclusion.
2. Enter a path (for example /premium/) or a full URL.
3. All pages under that path will be eligible once the meter triggers.

• To exclude pages

1. Click Add page exclusion.
2. Enter the exact URL or path (for instance /about-us).
3. Those pages will never show an Offerwall, regardless of threshold.

Remember that exclusions override inclusions. If a URL appears in both lists the Offerwall will skip it.

Step 4: Configuring User Choice Options

Scrolling past metering brings you to User choices. Each choice maps to a reward path.

You'll notice a toggle Rewarded ad to On, under this, click the Manage button. A small panel appears with these elements:

• Copy reminder: A note prompts you to confirm that the text in your Offerwall matches the access period you plan to grant.
• Entitlement selector: Here you enter a number and pick one of four units, hours, days, weeks, or page views, to define how much access a visitor earns after watching the ad.

For example, typing 12 and selecting hours gives a half‑day of access. Entering 3 page views lets the visitor read three more articles before the next prompt.

Step 5: Crafting Headline and Body Copy

Now in the styling tab you find headline and body copy fields. A human‑style approach works best:

• Headline

A simple prompt such as Support this site by watching one short video.

• Body

Two or three sentences that explain what the visitor gains. Mention the video length and the access duration or pageviews they will receive. Write as if you speak to a friend over coffee. Keep sentences varied in length and structure. Avoid filler words. Aim for direct clarity.

The default template for messaging is like this:

"Unlock more content
Take action to continue accessing the content on this site
View a short ad
Site-wide access for 24 hours"

But you can edit it as per your preferences, for my 48 hours setting it will be like this:

"Welcome to digitalinformationworld.com

You've reached your article limit!

After 4 free pages, we ask readers to take action. Simply view a short ad for 48-hour access. Or support us with a voluntary donation by contacting us here https://ift.tt/HU8tsuh

View a short ad
Site-wide access for 48 hours"

Once you’ve verified your copy and chosen the entitlement, click Save (or Apply) to lock in your setting.

Step 6: Styling for a Seamless Experience

A prompt that looks foreign to your site feels intrusive. In the Styling tab:

• Upload Logo

1. Use a transparent PNG at least 200×50 pixels.
2. Place it in the message header.

• Set Fonts and Colors

1. Match headline font to your site’s CSS.
2. Choose button colors from your brand palette.
3. Ensure high contrast for readability.

• Validate in Preview

1. Use the built‑in preview pane to step through each choice path.
2. Check both desktop and mobile layouts.
3. Adjust text lengths or margins until no buttons run off screen.

Your goal is a prompt that feels native to every page it appears on.

Step 7: Testing in the Wild

Before you roll out globally, test on a single URL:

1. In Page inclusions restrict to one test page of your choice or you can simply apply to the whole website/blog.
2. Publish the message by pressing the Publish Changes blue button on top right corner.
3. Now, open a private or incognito window.
4. Navigate to the test URL and other pages for 4 times (if you set it to 4), to trigger the pop up.
5. Reload the page. The Offerwall should display immediately. 

If it does not:

• Confirm the the Adsense snippet installed correctly.
• Disable any ad blocker or privacy extension.
• Verify your test URL matches the inclusion exactly.

Walk through each user choice. Make sure header text, body copy, logo and buttons match your settings.

• Related: How to Find the Publish Date of a Website, Webpage or Article. 6 Super Hacks!

Step 8: Publishing and Experimentation

Satisfied with testing? Remove the test‑only inclusion or expand your page list. Click Publish. Your Offerwall now runs on all targeted pages.

Return to Experiments to clone your live message. Tweak one variable at a time, perhaps copy, threshold, or entitlement. Run both variants for at least a week. Compare:

• Completion rate (how many visitors finish the video or choice)
• Bounce rate change
• Revenue per thousand impressions

Retain the variant that strikes the best balance between user satisfaction and revenue uplift. In my almost 15 days of testing the message popped up for over 300 viewers and it generated around $1 in that time period. But it can be different based on niche and location of users on your site.

Step 9: Handling Special Cases

• Unconsented Traffic

AdSense serves limited or non‑personalized ads for GDPR or CCPA unconsented visitors. Other choices (custom) remain available.

• Language Support

Upload translations for every language you support. AdSense displays the Offerwall in the visitor’s device language. Only add languages you can proofread.

• Cookie Clearing

If visitors clear cookies their pageview count resets. Decide if that suits your user experience goals.

• Ad Blockers

Some tools block Google AdSense or the promotional message container. Ask testers to disable blockers or whitelist your site.

Frequently Asked Questions

How many pageviews trigger the Offerwall?

You set the metering threshold. Three or Four pageviews is a common starting point.

Can I gate only specific articles?

Yes. Use page inclusions to limit the Offerwall to any path or URL.

What entitlements can I grant?

Either time‑based (hours of access) or pageview‑based (number of additional views).

Does this work for unconsented users?

Rewarded ads serve limited or non‑personalized ads, while other choices still function.

Note: This post was edited/created using GenAI tools. 

Read next: How to Find Someone Using Just a Photo: 10 Best Reverse Image Search Tools (Ranked and Explained)

by Irfan Ahmad via Digital Information World