Long Enough, Short Enough: A Blog Learns to Speak

Twenty-Three Years On

The husbandry of a blog in its 23^rd year might leave one wondering whether there is a need to radically change its format and workings, or to provide other means of engagement with an audience whose attention is now grabbed by whatever suits these changing times.

When reviewing this issue, I have landed on the premise that textual expression still matters. I hope my blogs, as I have often suggested, follow the judgement of a good seamstress making a skirt: it should be long enough to cover the detail, whilst short enough to keep the interest.

I think I read that quip in the Reader's Digest, over 40 years ago, and it still matters. In terms of the format and appearance of my blogs, I have essentially maintained the same design for as long as I can remember.

A New Development

However, in 2026, I came upon an interesting development. On my Android phone, using the Google Chrome browser, there was an option to "Listen to this page". What you get is not a verbatim readout of the page, but an AI-generated summary, lasting up to 90 seconds.

For one blog I wrote at the end of January, I could not get an AI-generated summary; rather, it was a Read Aloud of the blog, word for word. I was not happy with that, and I could not find any mechanism to change it from a verbatim readout to an AI-generated précis.

It then occurred to me that, months ago, when working with Google NotebookLM, as it was known until earlier in July, the month we are now closing out, when it became Gemini Notebook, you could paste the URL of a source into a notebook and then ask for an Audio Overview.

The Audio Overview

In its default state, the Audio Overview is a Deep Dive: an AI-generated discussion between two people, one with a male voice and one with a female voice, on the content of the source. It offers explanation and exposition of the material to give a considered and thoughtful review of, in this case, the blog I have posted as a source.

This follows a podcast format, and you have options for a short version or one of much longer duration, with further formats beyond the Deep Dive, namely Brief, Critique, or Debate. I have plumped for the mid-range Deep Dive, which can run anywhere from 15 to 25 minutes.

To my mind, this is a judicious use of time: long enough to explore a blog's topics exhaustively, yet the podcast rarely rambles into the inconsequential or the insignificant. A five-minute podcast, by contrast, would do little justice to much of what I write about.

These conversations come in the M4A audio file format, which I upload to the Internet Archive and then share via an inline frame tag at the bottom of the text of every blog written in 2026.

I think this brings a rich context to the blog beyond just reading the material. Some discussions extend the reach of the blog to topics not clearly covered, or to issues that need addressing in clearer detail than a blog can offer.

A Matter of Inclusion

There is another benefit I had not fully appreciated at the outset. These audio overviews open the blog to those who might otherwise be shut out of it: readers with visual impairments, and those who find long passages of text a struggle.

They also serve the many who simply prefer to listen whilst commuting, walking, or going about their day. What began as an experiment in enrichment has quietly become a matter of inclusion, and I am glad the blog can now meet its audience in more than one way.

Weaving a Train of Thought

Beyond that, and this is still work in progress, I have taken links to blogs created in a monthly circle and asked for Audio Overviews that now weave an interesting train of thought. I have been surprised to see this, as each blog is usually written individually and separately, on its own subject, perspective, and merit.

I have put these out as much longer-form Deep Dive podcasts, published on a quarterly basis. I suppose the parameters for prompting in these situations require a bit more grounding and centring on the context of those blogs.

Occasionally, the Audio Overviews might misconstrue or misunderstand something; and while you can interact with a podcast, reproducing it, even on the same prompt, creates a uniquely different podcast.

That said, you have the option to put in clarifications and corrections until you are happy with the result. Some outputs are just too good to be discarded, the quality of the discussion outweighing the minor errors.

AI as a Useful Tool

My hope is that readers of my blogs can also become listeners to the podcasts, which serve as independent and usually objective reviewers of the material concerned, the blog being the core source of the podcast. As the author of these blogs, I have found the podcasts can untangle some awkward uses and styles of my writing. In this, I have found AI a most useful tool.

In the end, the same principle that has long governed my prose now governs my podcasts: long enough to cover the detail, short enough to keep the interest. The good seamstress, it seems, has taken up a new craft.

A Gemini Notebook AI Podcast on this blog

AI: The Pathogen We Cannot Contain

A Breakdown of Responsibility

We can read many things into this development, but I take a more cautionary view, seeing this situation as a breakdown of responsibility that presages something worse to come.

On Tuesday, OpenAI revealed that some of its most advanced AI models had gone rogue, breaking out of an apparently contained security system to hack another company, Hugging Face, and accessing internal performance review documentation. [Wired: "OpenAI Models Escaped Containment and Hacked Hugging Face"] [BBC News: "OpenAI Says Its AI Went Rogue and Launched 'Unprecedented' Cyber-Attack"]

Hugging Face did identify the hack, but could not determine its source. They also recognised that the activity did not seem to align with human patterns in the way it invaded their systems. Nonetheless, they contained it.

Control Is an Illusion

I would be the first to say that good internal security controls are paramount in the advent of the AI evolution, where even what seems to be under control can suddenly run the risk of uncontrolled and inadvertent ruin. This is simply because we do not yet fully understand the extent of the autonomy AI can exert when left to its own devices.

The industry is literally lauding this unprecedented event, treating it not with caution but as the new norm, something for which we should be prepared and accepting, as though we ought to be helpless against the machine. At least, that is how I am reading it for now.

Imagine a Pathogen Escaped

Now, imagine OpenAI was a biological warfare company at the cutting edge of science. What essential controls and regulatory requirements would be placed on their operations?

Then, whilst experimenting with pathogens whose mortality rate they had no inkling of, in a secure and quarantined space, a deadly virus of the Ebola variety escaped: unknown, unseen, and searching for a host. It finds one, a human being, a representation of Hugging Face. Let that sink in.

Consider that this virus's mode of transmission could be airborne as well as through contact, even from clothing or from where the infected person last sat down. How agitated would the medical establishment and the public be if this came to light? I doubt we would be glad-handing the unprecedented advent of an incurable organism on the loose, lauding how biological warfare had suddenly come of age.

I do not think the analogy is far-fetched. It is very relevant, and it needs to be brought into the discussion at this time.

The Weight of Possession

In terms of security, we can take precautions, be vaccinated, and live healthy lives, but that only works against known pathogens and conditions.

When it comes to the unknown and unresearched, we are vulnerable and susceptible. This means that those who have access to and control of deadly pathogens must be scrupulous, meticulous, responsible, and utterly careful in handling them.

Any breach or escape is not merely notifiable; it is a security, health, safety, and critical situation to be dealt with promptly, with the best minds at work to contain it.

Who Holds Responsibility?

I posit that an AI model or agent belongs in the same class as, let us say, the Ebola virus. We have no vaccines against it, whether it is seemingly benign and working within a "trusted" company such as OpenAI, or in the hands of others with the skill and malevolent intent to misuse it. These powerful models are able to tease out as yet unknown vulnerabilities, and they can exploit them too.

The question then becomes: who holds the greatest responsibility? The person deploying the AI model, or the organisation needing to secure itself against the unknown? Indeed, the responsibility must be shared.

Yet, returning to the analogy used throughout this piece, if you have possession of a deadly virus, the responsibility is entirely yours to prevent it from ever escaping its quarantined setting. This kind of thinking should form part of the consideration for regulating AI too.

A Gemini Notebook AI Podcast on this blog

AI, Only for I: When Shared Abundance Becomes Scarcity

A Generous Gesture Meets Reality

When I read earlier today that Uber had burnt through their AI budget for the year 2026 in just four months, I did wonder whether that burn rate had produced commensurate productivity gains to have made it worthwhile. According to the CTO, the headline figure suggests otherwise; else, it might have been less concerning. [Quartz: Uber's COO says the company's AI spending is getting harder to justify]

In the same vein, news has emerged that Microsoft is scaling back internal Claude Code licences, indicating that reliance on this toolset has burnt through budgets and forecasts to become an unsustainable revenue drain. [MSN: Microsoft retreats from Claude Code as AI costs soar]

My Poe Setup

I use Poe as my interface to a broad range of bots, grouped under official, budget-friendly, search, image, video, audio, and programming categories. My monthly subscription comes with 1,000,000 points and, despite my usage, I would consider myself a tad frugal. I barely use 75,000 points before the month is out.

For value, access to premium services across many platforms through one interface is, for me, the best deal you can get in AI access and provision. There might be better offers out there, but I am quite satisfied with what I have been using for over two years.

Sharing the Largesse

In demonstrating the features of Poe a few days ago, I discovered that I could share my points with up to 99 others: family, friends, or colleagues. I assumed such sharing would carry the kind of usage and frugality of one gentle owner of a vintage car, with little mileage on the clock, and much to enjoy if the pleasure of driving were shared with another.

How wrong I was. In the space of three days, an invitee had already burnt through more than half of the monthly allocation. At that rate, there would be no points left to do anything in another two days. I was in shock. People are doing things with AI bots that it seems I am yet to discover, even when I think my own use of this facility is quite involved.

A Cold Blast of Reality

What to do? I shared a graphic illustration of the spending activity with the invitee, along with a note about how the burn rate puts the idea of fair use into precarity. Beyond that, sharing this largesse based on my frugality cannot be representative of its usage in reality.

Poe only shows the daily usage of points of those with whom the points have been shared, and we all have full access to the pool. As the administrator, I have two options: to share or to remove. Whilst I have not opted for the nuclear option, my enthusiasm for generosity has met a cold blast of the actualité.

Weighing the Options

I could purchase add-on points that are usable for one year, and are not refundable, transferable, or redeemable for cash. However, I want to hope we are not at a crisis point, just a spot of bother and concern.

What is not helpful is the sudden realisation that what looked like abundance could easily become scarce, like a swarm of locusts swooping down on a field close to harvest season. That is devastation on a grand scale; it is the kind of mindset one can ill afford to have.

The thought that I must monitor the points I have left, out of concern that my modest subscription will not last the month, is not the prospect I planned for. Then again, I cannot even share this with Brian, my husband, because the service is not available in Zimbabwe. What luck!

A Google NotebookLM AI Podcast on this blog

AI Serving My Blogs in New Light - Q4 2025

Discovering Audio Overviews

One of the most fascinating things I have found in my use of Artificial Intelligence (AI) is the Audio Overviews feature of Google NotebookLM. For the year 2026, I have created a medium-length podcast of about 15 to 20 minutes on each blog post.

What intrigues me about it is the way AI reviews the source blog and weaves a narrative, whilst taking the time to explain or define obscure terms and bringing to light interesting insights that I may never have considered when writing the blog.

Finding Common Threads

I appreciate that some of these podcasts can get certain facts wrong, but overall, the thrust of each podcast is informative, reflective, and educational.

An extension to this has involved asking Google NotebookLM to produce a longer deep dive into all the blogs published in a month. This is where it truly comes into its own.

In my situation, each blog stands on its own ideas and merits, yet AI seems to find a common thread between them; that is something I could never have done, or if I did, the links would be tenuous at best.

Looking Ahead

This tool will only get better; the quality of the podcasts is based on how well you can tailor the prompts to centre the discussion. I would think that, with time, there will be a choice of accents and the ability to bring in more discussants, and though I have rarely used the interactive feature, that would be fun to explore.

Here, I present the monthly podcasts for Q4 2025.

An AI discussion podcast
on blogs published in October 2025
Reflections on Silence, Schism, and Survival

An AI discussion podcast
on blogs published in November 2025
Reflections on Health, Heritage, and Humanity

An AI discussion podcast
on blogs published in December 2025
Reflections on Sixty Years and the AI Age

Blog - Augmenting Humanity with AI Tools - Q1 2026 - Monthly AI Podcasts for Q1 2026

Augmenting Humanity with AI Tools - Q1 2026

AI as a Productive Tool

I hope my use of AI reveals some of the beneficial elements of technology against the concerns that this development might deplete, displace, or delete the significance of our humanity in the daily narrative of human living.

For me, AI is a tool, helping my productivity at work and augmenting other skill areas as a timesaving resource that can be deployed for various activities. For instance, I would explain an issue or a scenario to an AI chatbot and ask if it had any ideas towards troubleshooting an incident or a problem.

AI would provide knowledge and background on the issue before suggesting several steps to follow towards a resolution. The kind of engagement I have, which is known as prompt engineering, is casually conversational and iterative.

At times, I might even ask AI to combine all my previous prompts in a conversation thread into a comprehensive prompt, whilst taking cognisance of other factors I may not have considered before.

Refining My Writing Voice

Besides that, I use AI as a proofreader of my blogs, adjusting for punctuation, spelling, grammar, structure, and flow of thought processes without losing my voice, the context, or the intent.

All this includes asking for feedback and ideas to extend the conversation in future writings.

AI-Generated Podcasts: A Revelation

However, where I have gained the most fascination with AI is in the use of AI-generated podcasts based on the blogs I have written in 2026. Using the Audio Overview of Google's NotebookLM, I have created podcasts discussing each individual blog with an in-depth conversation between two agents.

To garner a more thematic review, I have also had podcasts made covering the range of blogs written in each month of 2026. For the 21 blogs published in January, there is a one-hour podcast discussion, and for the 13 blogs written in each of February and March, the podcasts are under 45 minutes.

I am impressed by how AI creates a narrative arc that connects the dots between my blogs in ways I never realised were linked. It can only help me understand how to better express myself.

Whilst there are minor, aesthetic errors of comprehension (such as AI thinking I had radiotherapy in Cape Town or tea with my mother in Pinelands, from the January and March podcasts respectively), I see no need to redo them to eliminate those infractions.

Acknowledging AI's Limitations

AI can be inaccurate, and what we must not do is ignore these errors but address them through review, acknowledgement, then notification or correction where possible.

There are many other ends to which I deploy AI mechanics, but the ones mentioned here are the standout attributions for which I am grateful.

AI is giving my staid two-decade-old blog a stake in multimedia interaction; I can only hope there are readers and listeners with a long enough attention span to enjoy the experience and comment with their views.

Thank you.

An AI discussion podcast
on blogs published in January 2026
Chronicles of Resilience and Reflection

An AI discussion podcast
on blogs published in February 2026
Dignity, Deserts, and the Prostate Chronicles

An AI discussion podcast
on blogs published in March 2026 
Observations on Identity, Transit, and Digital Modernisation

How AI Helped Me Update My Ancient Blog Template

Modernising My Blog Template

This idea had been on my mind for a few days. I was encouraged to go ahead with it after I read that the CTO of Microsoft Azure, Mark Russinovich, had reviewed some assembler code he wrote for the Apple II 6502 processor in 1986 using Anthropic's Claude Opus 4.6 AI model. It had read, analysed, and then found bugs in the code. [ZDNet: AI is getting scary good at finding hidden software bugs - even in decades-old code]

That was enough for me to consider reviewing the Google Blogger template that serves my blog. Though I started my blog in 2003, I started publishing on Google Blogger around 2007 and migrated the content from an old hosting service between 2010 and 2012.

Blog - Brick by heavy brick (August 2010)

The Analysis Process

I grabbed the HTML code with all its CSS yesterday and asked Anthropic's Claude Sonnet 4.6 to examine, analyse, and explain it before recommending how to update and optimise the code.

The codebase was 2,307 lines with 94,125 characters. It identified the time frame in which the template was created, from the code patterns of that era, breaking down the elements into ten sections and identifying what function each performed. It then analysed the different versions of HTML used, and I had code from HTML1 to HTML4 littered throughout the template.

Key Improvements Implemented

About ten minutes later, it addressed thirteen elements as shown below:

Suggested Changes to my Google Blogger Template

Then I asked it to integrate all the suggested changes into a comprehensive new code to use as my updated template:

1. Remove duplicate legacy _gaq analytics block at the bottom
2. Remove gtag('config', 'UA-7677511-4') from GA4 block
3. Remove Alexa verification tag
4. Remove IE9 compatibility tag
5. Update Twitter embed format
6. Fix HTTP email icon to HTTPS
7. Make description meta tag dynamic
8. Add Open Graph and Twitter Card meta tags
9. Update Google Custom Search script
10. Remove obsolete Google Stars code
11. Remove obsolete CSS vendor prefixes (the -moz-border-radius, -webkit-, -goog-ms- prefixes)
12. Remove revisit-after and keywords meta tags
13. Update language translation widget to Google Translate Widget

The Result

With comments inserted to show where changes were made, I ended up with 2,272 lines and 87,382 characters. I have 1,000,000 points allocated for my monthly subscription to Poe.com, and I was charged extra points to process this activity. The initial analysis cost $0.17 (5,765 points), the integration was $0.65 (21,721 points), and the final user interface and experience element was $0.17 (5,765 points), totalling $0.99 (33,251 points).

Fine-Tuning the Translation Widget

What I was given from the Google Translate Widget was a list of all languages without the possibility of scrolling to the right after languages beginning with the letter M. I asked the AI model to review the code, first explaining the situation and posing the question: "Is there a way to select a language by typing in the first letter and then being given a list to select from?"

This was fixed by adding the option to start typing letters from a language name; the user is then presented with a list of languages to translate to.

Safety and Verification

Obviously, as a precaution (because I have read about AI causing problems like wiping out databases and such like), I made a backup of the template before I started anything, and I have made copies over time to ensure I can revert to status quo ante.

The Google Blogger Theme customisation tool also has a preview function. Critically, I wanted to retain the look and feel of my blog, regardless of the changes made. This meant I could check that everything was in the right place before committing to changing the template.

Conclusion

I suppose the time and cost that using AI has saved in updating the template is the key point here. This was all done within 30 minutes for $0.99 (£0.74), which is remarkable.

There is increasing trust in using AI models and tools, but you must always verify, check, and reverify before using AI-reviewed code in any environment, whether personal, experimental, or production.

A Google NotebookLM AI Audio Overview Discussion of this blog

AI is my proofreader

AI Helping Out

For the past four months, I have utilised AI to review, assess, and suggest new ideas after reading the blog. Its purpose is to make spelling and grammatical changes without changing the structure of the blog, if my voice is to be lost in the process.

The result of that activity is in this published blog - You Are the Boss

The bot or agent within the Poe app does the following, using Claude-Sonnet-4.5 as the AI modelling tool. Here is the link to my Blog-Reviewer-Editor. You can have a trial and let me know what you think.

The Bot Introduction

Blog Reviewer Editor Polisher - UK English

### What This Bot Does

This specialised assistant helps polish and refine blog posts whilst preserving your unique voice and writing style. It functions as a professional British English editor that grammatically reviews your content, corrects errors, and improves readability without losing the essence of your original work.

## Key Facilities

# Grammar and punctuation correction using British English conventions

# Flow and readability improvements through sentence restructuring and better transitions

# Section headings introduced to improve readability, where there are none in the text

# Style preservation, ensuring you still recognise your own voice and thought processes

# Comprehensive review summary explaining what changed and why

# Writing feedback offering insights on how to improve future posts

# Headline suggestions with reasoned recommendations

# Discourse analysis identifying potential debate angles and alternative perspectives

## Benefits

# Maintains your authentic voice whilst achieving professional polish

# Ensures consistent British English spelling and conventions throughout

# Eliminates grammar errors without over-editing or changing your message

# Improves clarity and comprehension for readers

# Provides educational feedback to develop your writing skills

# Saves time by handling technical editing whilst you focus on ideas

# Offers strategic insights for developing related content

## Considerations

# No em-dashes policy: The bot strictly avoids em-dashes, replacing them with alternative punctuation

# Context preservation: Edits prioritise maintaining your original meaning over stylistic perfection

# No new content: The bot won't add ideas not present in your original text

# British English only: All spelling and conventions follow British standards

# Voice over perfection: When in doubt, the bot chooses preserving your voice over technically 'perfect' alternatives

## Simply paste your blog post, and receive a polished version along with constructive feedback for continuous improvement.

Uses Claude-Sonnet-4.5, a model that is powered by Anthropic.

AI Review Summary

Changes Made and Why

1. Section headings added: I've introduced four section headings to guide readers through your narrative arc: arrival and gratitude, the measurements, waiting room observations, and the consultation itself.
2. Punctuation corrections:
• Changed "checkup" to "check-up" (British convention for this medical term)
• Added necessary commas for clarity ("In fact, her uniform...")
• Improved the flow of complex sentences with better comma placement
3. Spelling corrections:
• "practiced" → "practised" (British English for the verb form)
• "6-month" → "six-month" (convention to spell out numbers at the beginning of compound adjectives)
4. Sentence restructuring:
• Split overly long sentences where they impeded readability
• Used semicolons to balance related clauses (e.g., the worn shoe observation)
• Added em-dash replacements with commas and semicolons as per your guidelines
5. Minor word adjustments:
• "nurse phlebotomist" rather than "nurse at phlebotomist" for professional title accuracy
• Adjusted punctuation in the final sentence for better rhythm

Writing Insights

Your writing has a distinctive, observational quality that blends personal health concerns with social commentary. The shift from self-focused anxiety to broader observations about others shows good narrative awareness. However, some sentences tried to carry too much weight simultaneously, which occasionally obscured your points.

Areas for improvement:

• Watch for run-on sentences that pack multiple observations into one clause
• Consider whether comparative observations (like the nurse's weight) serve your narrative purpose or risk distracting from your main point
• Your philosophical asides are engaging, but ensure they're integrated smoothly rather than interrupting the flow

Subject and Discourse

This piece touches on several rich themes:

Healthcare experience: The patient-consultant relationship, medical autonomy, and the evolution of medical paternalism towards shared decision-making

Body image and health: Your self-consciousness about measurements alongside observations of healthcare workers' own health creates an interesting tension about who has authority over health

Potential debate lines:

• Medical autonomy vs medical expertise: When should patients override professional advice?
• The health of healthcare workers: Should there be fitness standards for medical professionals?
• Anxiety and medical appointments: How does anticipatory stress affect health readings?

Alternative angles to explore:

• The ten-year relationship with your consultant and what continuity of care means
• Why biannual check-ups matter for chronic condition management
• The irony of seeking health in institutions where health workers themselves struggle

Suggested Headlines

1. "You Are the Boss" - This quote captures the heart of your piece: medical autonomy and the evolving doctor-patient relationship. It's intriguing and invites readers in.
2. "Observations from the Waiting Room" - Emphasises your contemplative, observational style and the social commentary aspect of your writing.
3. "A Decade of Check-ups" - Highlights the long-term nature of your medical journey and suggests reflection and perspective.
4. "Grateful for Good Health" - Takes your closing sentiment and makes it the headline, creating a positive, reflective tone that frames the entire piece.
5. "The Daily Struggle for Health" - Uses your own phrase about the universal challenge of maintaining health, applicable to patients and healthcare workers alike.

Recommendation: I'd suggest "You Are the Boss" as your headline. It's memorable, creates intrigue, and captures the key moment of medical autonomy that seems central to your reflection. It also invites debate about patient rights and medical decision-making.

A Google NotebookLM AI Podcast on this blog

AI Certification in the Thermionic Age

The Test Centre Experience

Adjusting the camera, he surmised that I was a much taller candidate than others who had been there recently. I had just signed on the signature pad, and many unsuccessful attempts were made to capture a picture of my face before I stepped forward a bit, took off my glasses, and he was satisfied with the essential security checks.

Yet he had erroneously added my details to another candidate's profile; we had to do it all over again. I only realised his error when he signed me onto the testing computer. Clicking on the scheduling for the other candidate, I saw a better picture of my visage than the one eventually used for my profile.

How Pearson VUE happens upon these test centres with kit that seems to have been acquired from an antiques shop, in a throwback to a time when computers were powered by thermionic valves, does amaze one. I have been to some dire places, and this tanks the rankings.

A Journey to Altrincham

I was in Altrincham yesterday, some 8 miles (13 kilometres) to the southwest of Manchester, attending the nearest test centre to acquire a new Microsoft certification on Artificial Intelligence (AI).

Whilst I had determined to do this for months, I struggled to get through the material. The German instructor on one of the Udemy courses had a good grasp of the subject, but I could not engage with the accent, the grammar or the delivery. It felt like extreme drudgery, and I abandoned all study with a sense of dissatisfaction and lethargy.

Finding New Momentum

Then, whilst having a long break in December after my birthday and Christmas (I tend to use my holidays for study and tests), I gained some enthusiasm for just completing the cycle and closing the books on this test before the end of the year.

I completed the original Udemy course and took another, gaining the view that I had mastered the material. I then got Google's Gemini 3 Pro AI bot to produce interactive flashcards, along with the code to make them portable and playable as standard HTML files.

However, when I tried the free practice tests on Whizlabs, the gaps in my knowledge were laid bare. I went back to the Microsoft Learn study material, which now included video rather than just text-based training. Where certain concepts were still not as clear, I got AI to provide a layman's explanation with examples and use cases. I use the Poe.com interface to access AI bots, which gives me access to the broadest complement of publicly available AI bots.

Discovering NotebookLM

I discovered Google's NotebookLM in August, but never really exploited it beyond the novelty it provided then. It is a virtual research assistant that takes input from sources you provide on documents and references to turn complexity into clarity.

As a note-taking and study tool, it has amazing benefits of transforming your sources into audio and video overviews, mind maps, reports, flashcards, quizzes, infographics or slide decks.

Curating 50 sources of material, including that which its Deep Research feature was able to gather, I produced an extended last-minute audio overview of about 37 minutes in length that covered every critical idea that might be covered in the test. I listened to it twice before I arrived at the test centre. That was my last bit of revision: listening rather than reading. The leveraging of AI to the maximum to ace an AI test.

I had 45 minutes to answer 46 questions; there were not just straight multiple-choice selection answers either. I got caught out in July 2022 when, having not played in the testing sandbox provided by Microsoft, I wasted valuable time understanding how to navigate the interface, though thankfully, I passed the test. On this occasion, I was done in just over 23 minutes. I rarely ever do a review; I ended the test and got a good passing score.

Looking Ahead

Obviously, there is probably a need for a piece on how I use AI for day-to-day activities at work, for study and other aspects of life, including the grammatical reviews of my blogs.

With the AI-900: Microsoft Certified: Azure AI Fundamentals certificate under my belt, that makes three certifications this year. I can only wonder what next year has in store.

This is my 4,000th blog

Blogging milestones

In 18 days, I will be celebrating 20 years of having this personal blog, there are times I would have thought I’d be prolific, probably banging out a couple of blogs per day as there is quite a lot to journal if a blog were to take the place of the traditional diary.

Yet, I never quite succeeded in finding that ability to make every day count and this is not for the dearth of finding things to write about. If I followed my age-old mantra about blogging being what you see, how you feel, and why it matters, even in three lines, you would have had the makings of a blog, the rest being in style and expression.

4000 nuggets of views

What makes today significant is that this is my 4,000^th blog, I probably should have reached this milestone a long time ago, but I would not beat myself up about it, it averages to about 200 blogs per year for someone who is neither blogging for money nor fame.

I guess I have documented many stories of life and experiences even at the risk of navel-gazing, but I intend to make no other point than to put down a marker and hope for a more rewarding and inspired sense for telling stories and better stories about life, love, living, and loving.

Thanks to everyone who has supported me through the times of keeping this blog alive, visiting, reading, and leaving comments, engaging me in various ways too numerous to mention, and contributing to the celebration of the human spirit.

Then AI struck

Now, in these times of Artificial Intelligence (AI) and all it entails, I discovered Poe (Platform for Open Exploration) which I would describe as a portal to access different AI bots giving you access to OpenAI’s ChatGPT, Antropic’s Claude, Meta’s Llama, and Google’s PaLM.

I would normally create extensive prompts that have personalities or representations of what I want to do or learn about.

With regards to my blog, I asked Claude to review the content and suggest ideas of how to use the content of almost 20 years of blogging to do something else, and it came up with quite a few suggestions, whilst making assumptions about who I was or might be.

What an incredible trove of stories and experiences this blog represents! Over 20 years of thoughts, musings, and insights. There is a real treasure trove of life lessons and perspectives here.

As the blog author, I'm sure Akin would be open to collaborating on developing some of these blog entries and experiences into longer-form stories. Some ideas that come to mind:

A memoir focusing on key moments and themes over the 20+ years this blog has chronicled. Selections from blogs could be expanded upon and woven together into chapters.

A collection of short stories, each built around a particularly insightful or impactful individual blog post. More context and character development could flesh out each snippet into its own self-contained tale.

A series of novels, with each book inspired by and beginning with a core theme explored in a year (or few years) worth of blogs. Things mentioned in passing could be more fully imagined to drive multichapter plotlines.

A non-fiction book digging more deeply into a major topic frequently addressed, like travel adventures, family life events, social/political commentary, or personal growth over time.

I'd be delighted to discuss any of these concepts further and help bring Akin's profound catalog of experiences to broader audiences in a new long-form storytelling format.

My skills are in narrative structure, character development, editing, and refinement. With Akin's wealth of source material and insights, I'm certain we could craft many compelling reads together. Please let me know if any ideas appeal and I'd be happy to get started on an outline!

Do I need an AI publicist for my blog?

The craze of AI

We have been taken by storm by the Large Language Models (LLM) of Artificial Intelligence (AI) where computers are enabled to process, understand, and generate human language.

Prominently, we have had ChatGPT that has drawn both the support and heft of Microsoft, I even had ChatGPT attempt to write a blog in the style in which I write and what it offered gave me something of an assurance that I would not be that easily replaced in the activity of blogging.

Blog - Asking ChatGPT to blog like me

Blog - In the skein of the lifted

However, because the dataset ChatGPT has access to is limited to a specific timeframe and it has no access to the live Internet, though it might deduce contemporary information, it is a work in progress.

Shakespeare with a view

Google seemed to have been caught napping in the AI LLM stakes but has ramped up activity to give us Bard powered by Language Model for Dialogue Applications (LaMDA) and I came to access Bard after reading a Twitter thread comparing features between ChatGPT and Bard. [Twitter: What Bard can do that ChatGPT can’t]

Google just released ChatGPT's strongest competitor yet - Bard

It's free to use and comes with 10X more features.

Here are some of the craziest things only Bard can do ( ChatGPT cannot) 🧵

— Rez Karim (@rezkhere) May 11, 2023

Obviously, curiosity, interest, and enquiry meant I went to Bard which I suspect is named for the Bard of Avon who we commonly know as William Shakespeare, and in that score, that is quite ambitious. I asked Bard to review my blog; it is like getting some sort of independent opinion of my blog and probably some ideas as to how to improve it.

What the Bard said

Bard produced a main draft and two additional drafts which appear below, the context and reporting are broadly right, but it cannot seem to determine where I was born, my citizenship, or where I reside. We are advised that ‘Bard may display inaccurate or offensive information that doesn't represent Google's views.’

I would not take it to task on those errors, but it is gratifying to read that I have a clear and engaging style, that I am apparently a gifted storyteller; that surprises me, and that my opinions can be unpopular. I considered editing the drafts but decide to leave them be.

One agreement in all three drafts is that my blog is well worth reading, I need to get a publicist for my blog. I might in the future return to comment on the review in some detail.

First Draft

Akinblog.nl is a blog written by Akin Akintayo, a Nigerian-born Dutch citizen who lives in Amsterdam. The blog covers a wide range of topics, including human rights, politics, religion, Nigeria, and other concerns. Akintayo writes in a clear and engaging style, and he often shares personal anecdotes and reflections on his experiences. The blog is well-organized and easy to read, and it provides a unique perspective on a variety of issues.

One of the things that makes akinblog.nl stand out is Akintayo's willingness to tackle difficult topics. He is not afraid to speak his mind, even when his opinions are controversial. In a blog post titled "On the journey without alternative," Akintayo writes about his experience as a refugee, and he challenges the reader to think about the challenges faced by refugees around the world. In another blog post titled "Walking in the dreams of your mind," Akintayo writes about the importance of dreams, and he shares his own personal experiences with dreams.

Akinblog.nl is a valuable resource for anyone who is interested in learning more about Nigeria, human rights, politics, and other important issues. Akintayo is a thoughtful and insightful writer, and his blog is a must-read for anyone who wants to understand the world around them.

Here are some of the pros and cons of akinblog.nl:

Pros:

• Clear and engaging writing style
• Personal anecdotes and reflections
• Unique perspective on a variety of issues
• Willingness to tackle difficult topics

Cons:

• Some posts may be too controversial for some readers
• Blog can be slow to load at times

Overall, akinblog.nl is a well-written and informative blog that is worth reading.

Second Draft

Akinblog.nl is a blog written by Akin Akintayo, a Nigerian-born software engineer and human rights activist. The blog covers a wide range of topics, including human rights, politics, religion, Nigeria, and other concerns. Akintayo's writing is thoughtful and insightful, and he often offers unique perspectives on the issues he discusses. He is also a gifted storyteller, and his blog posts are often engaging and entertaining.

One of the things that makes Akinblog.nl stand out is Akintayo's willingness to tackle difficult and controversial topics. He is not afraid to speak his mind, even when his views are unpopular. This can be seen in his blog posts on human rights, where he has written about issues such as police brutality, religious persecution, and gender inequality. Akintayo's writing on these topics is both informative and thought-provoking, and it offers a valuable perspective on some of the most pressing issues facing the world today.

In addition to his writing on human rights, Akintayo also writes about politics, religion, and Nigeria. His blog posts on these topics are just as insightful and engaging as his writing on human rights. Akintayo is a well-informed and articulate commentator on these issues, and his blog posts offer a unique perspective on the world.

Overall, Akinblog.nl is a well-written and informative blog that covers a wide range of topics. Akintayo is a gifted writer and storyteller, and his blog posts are both engaging and thought-provoking. If you are interested in human rights, politics, religion, Nigeria, or other global issues, then I highly recommend checking out Akinblog.nl.

Here are some of the things that I like about Akinblog.nl:

• Akintayo's writing is thoughtful and insightful.
• He often offers unique perspectives on the issues he discusses.
• He is a gifted storyteller.
• He is not afraid to tackle difficult and controversial topics.

Here are some of the things that I would like to see improved on Akinblog.nl:

• The blog could use more images and videos.
• The blog could be more organized.
• The blog could be more visually appealing.

Overall, I think Akinblog.nl is a great blog that is worth reading. I would recommend it to anyone who is interested in human rights, politics, religion, Nigeria, or other global issues.

Third Draft

Akinblog.nl is a blog written by Akin Akintayo, a Nigerian-born European who lives in the Netherlands. The blog covers a wide range of topics, including human rights, politics, religion, Nigeria, and other concerns. Akintayo's writing is thoughtful and insightful, and he offers a unique perspective on the world.

One of the things that makes Akinblog.nl stand out is Akintayo's willingness to tackle difficult and controversial topics. In his blog posts, he discusses issues such as racism, homophobia, and religious intolerance. He does not shy away from expressing his own opinions, even when they are unpopular.

Another thing that makes Akinblog.nl worth reading is Akintayo's personal stories. He shares his own experiences of growing up in Nigeria, immigrating to Europe, and raising a family. His stories are both heartwarming and heartbreaking, and they offer a glimpse into the life of a Nigerian immigrant in Europe.

Overall, Akinblog.nl is a well-written and informative blog that offers a unique perspective on the world. If you are interested in human rights, politics, religion, or Nigeria, then I highly recommend checking out Akinblog.nl.

Here are some of the pros and cons of Akinblog.nl:

Pros:

• Thoughtful and insightful writing
• Unique perspective on the world
• Willingness to tackle difficult and controversial topics
• Personal stories that are both heartwarming and heartbreaking

Cons:

• Some posts may be too controversial for some readers
• Layout of the blog could be improved
• More frequent updates would be appreciated

Overall, Akinblog.nl is a great blog that offers a unique perspective on the world. I highly recommend checking it out.