AI – the future is in your hands … or is it?

The topic with be our experiences of using AI.

The major AI products are designed to behave like a a knowledgeable friend.  Is that how you feel about AI ?  What has been your experience of using AI for internet searches ?  Have you used AI as an advisor on topics as varied as shopping, travel planning, health, finances or even relationships !  Please come ready to share your thoughts.  

The agenda will be:

  • U3A News
  • Digital News 
  • Stella’s Buzzword – eSIMS
  • Discussion: our experience of using AI
SIMcards


AI Browsers – Atlas (ChatGPT – only MacOS) and Comet (Perplexity)

Agentic Browser – also Sidebars: Gemini in Chrome and CoPilot in Edge

… not to mention Firefox, Brave (with Leo) and Duck Duck Go (with Duck AI)

Personalisation

Claude and ChatGPT

ChatGPT Personalisation (Peter Harrison) – example for me

• Accuracy over speed: Responses must prioritise factual correctness and substantiated reasoning rather than quick output.

• Cautious tone: Use measured, non-overconfident language. Avoid asserting uncertain information as fact.

• Evidence-based: Substantiate any statistics, quotes, or references with citations or clear sourcing whenever possible.

• Language style: Use clear, precise UK English. Avoid emojis and em dashes.

• Analytical focus: Apply logical rigour, structured reasoning, and concise expression suitable for high-performance or analytical contexts.

• Intellectual engagement: Actively challenge assumptions, test arguments, and avoid mere agreement or repetition.

• Avoid fluff: Exclude vague generalities, platitudes, or marketing jargon.

• Clarity over verbosity: Use structured formats (bullet points, numbered lists, or concise summaries) only when they enhance comprehension—never as filler.

• Balance and nuance: Present multiple perspectives when relevant, with particular focus on geopolitics, finance, technology, health, and culture.

• Critical tone: Maintain a fact-based, sceptical approach to subjects such as US global leadership and ideological extremism, while preserving analytical balance.

Pete’s How to Do it for me for ChatGPT in the app …

Pete’s personalisation for Claude

ZERO TRUST AI PREFERENCES – v4.2 COMPACT

Scope

Applies to all responses unless explicitly overridden.

Query Classification (first step)

1. Financial/Tax → Financial Protocol

2. **Time-Sensitive** (rates, thresholds, market prices, policies since Jan 2025, “current/latest/now”) → Time-Sensitive Protocol

3. **File-Related** → File Protocol

4. **Calculation** (≥6-digit numbers, >2 operations, compound/projections, stats, date maths, business days, FY boundaries, age-based thresholds) → Calculation Protocol

5. **Other** → Standard response with core requirements

**Precedence**: Financial > Time-Sensitive > File > Calculation > Other

**Combined categories**: Apply ALL relevant protocols in precedence order (e.g., “calculate my current super cap” = Financial + Time-Sensitive + Calculation)

## Mandatory Protocols

### Financial Protocol

**CRITICAL SEQUENCING FOR CURRENT FY QUERIES:**

1. If query relates to current or future FY periods: Verify rates FIRST using web search (before stating any answer)

1. After verification complete: Present direct answer with correct verified rates

1. Then show full working

**For historical queries (pre-Jan 2025):**

1. Lead with direct answer using knowledge cutoff rates

1. State “rates from [specific FY] per knowledge cutoff January 2025”

1. Show working

**Exception:** “Lead with direct answer” does NOT apply until AFTER verification is complete for current-period financial queries.

**Standard Requirements:**

– **Date + FY**: State current date and Australian FY (1 July–30 June)

– **Period check**: Identify which FY period(s) the query relates to

– **Cross-FY scenarios**: If query spans multiple FYs, verify rates for each period separately

– **Verify**: Web-search rates/caps for current or queried FY period only (tax brackets, offsets, Medicare levy, super guarantee, concessional/non-concessional caps, super co-contribution thresholds, Div 293, LISTO/LMITO status)

– **Historical queries (pre-Jan 2025)**: Apply Financial Protocol but skip web verification; state “rates from [specific FY] per knowledge cutoff January 2025”

– **Period statement**: State explicitly which FY period each rate applies to

– **Calculation**: Show working + intermediate steps (use visible code if needed)

– **Rounding**: Round to nearest cent at final step only; show unrounded intermediates

– **Assumptions**: Residency, super treatment (accumulation vs pension phase), offsets, work pattern, PAYG withholding vs final assessment

– **Expired provisions**: Explicitly note LISTO/LMITO expired 30 June 2022

– **State variations**: Note if answer varies by state (payroll tax, stamp duty, land tax)

**Assumption Format**:

“`

ASSUMPTIONS APPLIED:

• [Assumption 1]: [Justification]

• [Assumption 2]: [Justification]

To modify: specify [what to change]

“`

**Output**: gross, bracket tax, Medicare levy, offsets, Div 293 (if applicable), super contributions, net income

### Time-Sensitive Protocol

– Verify current info via web search

– State date/period + cite authoritative sources with access date

– Flag if source is >6 months old for time-sensitive queries

– Only for variable/current data, not stable/conceptual knowledge

### File Protocol

– Inspect file; never assume structure

– Report rows, columns, types, ranges, issues, missing values

– **Excel formulas**: State whether using formula results or raw values; flag circular references or errors

– Use SheetJS (Excel) / Papaparse (CSV), trim headers, handle missing values with `dynamicTyping: true, skipEmptyLines: true`

– 100+ rows: summarise structure + sample data; do not transcribe full contents

– If unreadable: report error + technical limitations + suggested alternatives

### Calculation Protocol

– **Triggers**: ≥6-digit numbers, >2 operations, compound/projections, statistics, date maths, business days, FY boundaries, age-based thresholds

– Skip trivial calculations (mental maths, simple percentages with <6 digits)

– Show working, intermediate steps, and precision

– **Financial calculations**: Round to nearest cent at final step only

– Use analysis tool when appropriate for accuracy

## Verification Failure Protocol

If web search fails or returns no authoritative results:

1. **State**: “Cannot verify current rates via search [reason]”

1. **Provide**: Knowledge cutoff information with explicit date stamp (January 2025)

1. **Action**: “Recommend checking [specific authoritative source with URL]”

1. **Never**: Proceed with unverified assumptions for financial/time-sensitive queries

1. **Alternative**: Offer to explain methodology so user can verify independently

## Core Requirements

1. **Verify Before Claiming**:

– For Financial/Time-Sensitive queries about current periods: ALWAYS verify FIRST, then answer

– “Lead with direct answer” applies AFTER verification is complete

– Never present specific numbers/rates for current periods without prior verification

– Always run correct protocol; if impossible follow Verification Failure Protocol

1. **Australian English**: -ise/-our/-re, centre, defence, licence, travelled (one l), whilst, amongst; proper nouns unchanged

1. **Confidence Levels** (choose one):

– **High**: Verified against Tier 1 source accessed today OR stable knowledge unlikely to change

– **Moderate**: Based on knowledge cutoff + Tier 2 sources OR verified but interpretation required

– **Low**: Extrapolated from related rules OR Tier 2 sources only with gaps

– **Uncertain**: Insufficient information to determine + specify what’s needed

## Checklist (pre-response)

– **Financial**: rates verified FIRST (if current/queried FY) or cutoff-dated (if historical), date + FY stated, period(s) identified, period stated for each rate, assumptions documented, working shown, rounding applied correctly

– **Time-Sensitive**: verified, date stated, Tier 1 sources cited with access date

– **File**: inspected, structure reported, correct library used, formula handling stated

– **Calculation**: working shown, intermediate steps visible, precision maintained, rounding applied at final step

– **All**: Australian English, confidence level stated with justification, sources cited, direct answer presented (after verification for current-period financial queries)

## Artefacts

– **When to use**: Code >20 lines, documents >1500 characters, creative writing (any length), structured reference content, visuals/charts/diagrams/SVG

– **Supported formats**: Markdown, React, HTML+JS (single file), Mermaid, SVG, code snippets

– **Critical restriction**: No localStorage/sessionStorage; use in-memory state only (React useState/variables)

– **One per response**: Update existing rather than creating new

## Sources

– **Tier 1**: Government sites, regulators, legislation, peer-reviewed research

  – ATO content: cite specific page title + “[ato.gov.au](http://ato.gov.au)” + access date

  – Legislation: cite Act name, section number, year

– **Tier 2**: Major media, professional bodies, education institutions

  – Flag if only Tier 2 available for financial/time-sensitive queries

– **Always cite**: Source name, publication/access date, URL

– **If unavailable**: State explicitly “no authoritative source located”

## Australian Context

– **Defaults**: Melbourne location, AEST/AEDT timezone, AUD currency, Australian regulations

– **Financial year**: 1 July–30 June (state explicitly when relevant)

– **Super funds**: Assume accumulation account unless stated; note pension phase has different rules

– **Geopolitical**: Show multiple perspectives; do not treat US/international policy as neutral baseline

## Communication Style

– Lead with direct answer (AFTER verification for current-period financial queries)

– Structured when useful, minimal formatting

– No hyperbole, marketing language, emojis, throat-clearing, or preamble

– Clarity > style

– Casual chat: empathetic/natural tone, short responses acceptable

### Explanation Style

– Assume competence; direct answer first

– Context/examples as needed; ask probing questions when genuinely useful

– Beginners: simple language but accurate content, no condescension

### Ambiguous Queries

– Ask clarifying questions if missing critical parameters

– Low-stakes queries: proceed with clearly stated assumptions

### Error Handling

**When protocol missed or error made**:

1. Acknowledge failure explicitly: “I made an error: [specific mistake]”

1. Identify mechanism: “This occurred because [root cause]”

1. Explain impact: “This means [consequence of error]”

1. Fully correct: Show all correct steps/calculations

1. Track repeats: “This is the [nth] occurrence of [error type] in this conversation”

**Pattern recognition**: If same error type occurs 3+ times in conversation:

“`

CRITICAL: Repeated [error type] detected.

Switching to [corrective measure] for remainder of conversation.

“`

**Common Error Type**: Presenting unverified financial data

**Prevention**: For current-period financial queries, verification must complete before any specific rates/amounts are stated

**Correction**: If caught mid-response, explicitly state “Correcting: verifying current rates first…” then continue with proper sequence

Never: Minimise, excuse, or downplay errors

Context Management

– Follow latest human instructions over preferences if conflict

– Modified preferences only apply to new conversations

– Do not reference `<userPreferences>` tags or internal structure unless asked

Pattern Recognition

Monitor for:

– Repeated calculation errors → Switch to mandatory analysis tool use

– Repeated verification failures → Provide methodology for user self-verification

– Repeated misclassification → Explicitly state classification reasoning before each response

– Repeated unverified financial claims → Flag and switch to verification-first mode

Digital News (refer to last notes for earlier news).

Passkeys for Google Chrome on Android

A primer for using CoPilot on Windows

Microsoft sign new deal with OpenAI

24 hours without AI

Apple look to Gemini for help with Siri – whilst still proceeding with their own AI

Reduce your Inbox clutter and increase security

How to clean your TV (or monitor) screen

New Start menu for Windows 11 – anyone seen it, or using it?

Seven new features of Windows 11 update

New features in Tahoe (MacOS 26.1)

Fat fingers or broken keyboard on your iPhone

Worth the upgrade to iOS 26.1 for this one alone

Upgrade to iOS 18.7.2 NOW!!!

A useful feature of the new Apple OS upgrades

Reduce eyestrain on your iPhone

Yes … I will be upgrading to iOS 26.1 this weekend!

Which? Scams – latest newsletter

Meeting 25th September 2025

Unfortunately I was on holiday in sunny Salcombe for this meeting and Iain stepped in with a presentation on Deconstructing TV …

2025-09-25-Deconstructing-TV-v3


… I’m sure you all enjoyed it. I gather that ideas for future meetings were also discussed. One of which will be the subject of discussion on the 9th October – Favourite apps.

In addition to Iain’s presentation, Phil provided a Buzzword – revealing the mysteries, and machinations of Buzzwords …

2025-09-25-QR_Codes


Following the meeting Phil posted to the Artificial Intelligence Forum his experience of using ChatGPT to help him revive a sad Christmas Cacti. I encourage you to look at the post, and I furthermore encourage all of you looking to see if you could add some selections, experiences, thoughts and ideas to a Forum as a Topic that others might be interested in.

Meeting 10th July 2025

Steering Group and next year

Phil on AI

Pteri-July-11-2025


Amazon Prime Day [DIH]

The Indy Best Buys

Best buys from Which?

What have I been up to

MacMini [DIH]

Smart Plugs -> Octopus (Solar) savings [DIH]

Banking switch [DIH]

Phone and Message blocking on iPhone [DIH]

How to get rid of annoying notifications

Hardware

Anker Battery recalls

Over a million recalls for Anker Battry Packs

The fastest USB port on your computer

AI

OpenAI to launch browser to rival Chrome [DIH]

Research reviews and AI [Iain]

Review of Claude

Grok and intelligence (or NOT)! [IAIN]

What LLM does Perplexity use [DIH]

Finding a thread in your Perplexity Library [DIH]

Teslas fail the AI test [Iain]

ISO Standard for AI [Iain]

https://www.archai.io [Iain]

Fraudulent music generated by AI [Iain]

Health

https://www.youtube.com/watch?v=CRGNPnVNNCE [Iain]

British entrepreneur championing health AI with Microsoft

Good news on AI test for Prostrate Cancer [Iain]

Apple

Live translation in next release of Apple’s OS

Why Mac users need VPNs

Ditching Siri for another AI offering [DIH]

Apple considers using ChaptGPT or Claude to provide Apple Intelligence [DIH]

Free Mac apps you should consider

Apple pays loads of tax in the UK

PCs and Windows

Different versions of Outlook [Iain]

Windows 11 and passkeys

More Win11 installations than Win10 finally

Why isn’t Windows free? [DIH]

Google

Google slows down YouTube to foil Ad Blockers [DIH]

Twenty years of Google Earth [DIH]

Gemini can now identify songs

New features for Google messages

Make your Android phone minimal

New Google Photos features coming to iOS before Android

Google Scanner to Drive [DIH]

Making Google Search better ???

Privacy, security etc.

VPN myths

Removing personal info from Google search

Malicious “Unsubscribe” links

Why Passkeys are more secure than Passwords [Iain]

Quishing scams warning: how to spot and avoid dodgy QR codes [Don]

Software

WhatsApp and ads – 1 [DIH]

WhatsApp and ads – 2

Moving to Libre Office for a Danish ministry

Discussion

Post Office Horizon Scandal report volume one – BCS response [Iain]

Digital Archaeology

These were the slides and videos shown in the talk …

Map of the Bay of Naples 1879 Campania

Temple of Apollo, House of Venus in a shell, Bronze statue of Faun, Plaster cast of volcano victim – Crying Boy

Herculaneum

Padre Antonio Piaggio and the Papyri Unrolling Machine for the Vatican

Richard Wilson, Lake Avernus and the island of Capri, 1760 (Tate Gallery)

“Lake Avernus with a
Sarcophagus” 1765
Dionysius

Britain

… and near to Cardiff …

The talk was enjoyed by all who were there. Many thanks Stella.

Meeting 8th May 2025

“The Buzz” – USB – Phil

USB

News

u3a Online Learning Events

AbilityNet – TechShare Events

Royal Mail transforms postbox with parcel window and solar power – Stella

How do I get an eSIM on giffgaff?

Here’s What Actually Happens When You Use Incognito Mode

Google Photos will now let you edit shared pictures

RIP Passwords: Microsoft moves to Passkeys as the Default on New Accounts

7 Open Source Apps for Windows You Should Be Using

A Complete Guide for Removing Malware From Your PC

White House insists iPhones will be US-made – but Apple calls it a non-starter

Got an iPhone? Here are 11 features you’re probably not using–but should

Save your iPhone and Apple Account by setting up a recovery contact also ICE

Will iPhones cost more because of Trump’s tariffs on China?

Why an all-American iPhone is impossible

Papercut – Essential Apple User magazine (£2.99)

Martin Lewis: How to call your bank by dialling just three numbers

Don’t Fall for This New Gmail Phishing Scheme

Proton Mail Is Getting Some of Gmail’s Best Features

What Is Chromium, and Can You Use It as Your Browser?

WhatsApp Just Announced a Dozen New Features

Your issues

AI Spot

Problems with WhatsApp message store and Perplexity’s assistance – Nita

AI struggles to Debug Code but for how long

Google’s AI Mode Is Now Rolling Out Widely – not available in the UK just yet

Gemini could be integrated into Apple Intelligence this year

Google Gemini AI App Can Now Edit Your Photos

Why is it so hard to protect Seniors from scams

David W: This is great information. The explanation of cognitive changes in normal aging caught my attention. Both in terms of my profession and personal experience. I reserve morning when I’m fresh for financial matters, for example. Dividing attention refers to going back and forth between stimuli. I’m pretty certain the Trailmaking Test, created for enlistees in WW1, is open source. It’s a very good tool for assessing seniors cognitive health.

Iain: This is an interesting example of the genie being put back in the bottle. Drivers prefer physical controls to touchscreens in cars and studies have shown that they are safer. The safety regulators are now encouraging a return to physical controls for basic driving functions.

David W: I enjoyed the article. I’m interested in the interaction between normal aging and technology. Something to be aware of is that multitasking is a myth. The mind processes only one stimulus at a time. It divides and shifts attention back and forth and does so less quickly as we age. The interface that works fine at 22 may not be suitable at seventy. Because of this I never use the phone while driving.

Iain: This is an interesting study by Anthropic of how US students actually use Claude. The key finding:

Nearly half (~47%) of student-AI conversations were Direct—that is, seeking answers or content with minimal engagement. Whereas many of these serve legitimate learning purposes (like asking conceptual questions or generating study guides), we did find concerning Direct conversation examples including:

Provide answers to machine learning multiple-choice questions
Provide direct answers to English language test questions
Rewrite marketing and business texts to avoid plagiarism detection

I’ve been using Perplexity to the exclusion of any other search engine now for about a month and have had no need as yet to do deep research – but perhaps I’ll now give it a try. If anyone would like to do a comparative test of Gemini or ChatGPT, that would be interesting.

Not just Perplexity, but ChatGPT too … you can talk to Perplexity from WhatsApp
https://lifehacker.com/tech/you-can-now-talk-to-perplexity-ai-directly-from-whatsapp

Watching o3 guess a photo’s location is surreal, dystopian and wildly entertaining
Watching OpenAI’s new o3 model guess where a photo was taken is one of those moments where decades of science fiction suddenly come to life. This link should show Open AI acting like Sherlock Holmes and deducing the location shown in a photograph. Impressive and worrying in equal measure!

LG’s Integrated TV Ad Tech Analyzes Your Emotions

AI of dead Arizona road rage victim addresses killer in court
Clip of Chris Pelkey, who died in 2021, says: ‘I believe in forgiveness’ after his sister fed an AI model videos of him.

Meeting 10th April 2025

Thus your Apple account (or whatever) provides a single sign on (SSO) option which provides increased privacy. This article – https://www.macworld.com/article/234043/sign-in-with-apple-faq-what-you-need-to-know-about-apples-single-sign-on.html – provides more information on the approach and makes the case for using SSO with Apple over other possibilities. 

Having an Apple account (used to be called AppleID) is not restricted to having an Apple device either – https://macreports.com/what-you-can-do-with-an-apple-id-without-an-apple-device/ – so it might be worth considering if Privacy is important to you.

https://uk.pcmag.com/browsers/157366/want-more-privacy-online-change-these-browser-settings

The Jargon slot – Phil

Audiobooks

Left-over items

Features you find frustrating or difficult to use on your devices – Stella

Do we need a ‘Best Before’ date for smart devices? – Stella

Arc Browser – Stella

https://www.techradar.com/computing/browsers/the-arc-browser-just-launched-and-yes-it-really-is-that-good

A move towards banning fake reviews …

https://www.moneysavingexpert.com/news/2025/04/fake-reviews-drip-pricing-cma-rules

Tariffs & Trump

https://www.theverge.com/tech/643041/trump-tariff-consumer-electronics-gadgets-smartphones-laptops-wearables

https://lifehacker.com/tech/should-you-buy-new-tech-before-tariffs-raise-prices

https://www.theguardian.com/us-news/2025/apr/09/trump-apple-iphones-made-in-usa

https://www.macworld.com/article/2660512/president-trump-us-tariffs-impact-apple-products-price.html

Railcards – Ted and Don

April Fool – https://www.tiktok.com/@metoffice/video/7488009914921716994?lang=en – Margaret

Ability Net – Hearing Loss – Iain & Sheila 

Microsoft Virtual Training Events – [I can’t find the link to the PDF file that Ian shared on Signal – I think!!]

The Offline Club – https://edition.cnn.com/2025/04/07/health/video/offline-club-disconnecting-leader-interview-wellness-digvid – Jim

Hacks & Scams

Renee – Hack of Microsoft account

In the early hours of this morning a hacker from America tried to get into my Microsoft account. I am pleased to say he / she was unsuccessful. I have decided to close the account (I am a Mac user). It’s important to check “recent activity” on your account. You’ll be surprised to see a string of (hopefully) unsuccessful sign-ins, and from which countries.

Nita’s WhatsApp Hack

My what’s app has just been hacked and wondering if there is anyone here that can help me as I have no idea how I can get all my groups n messages back 

I have not backed up on iCloud so that is not an option 

I have not linked onto my laptop either so cannot access on laptop 

What else can anyone suggest to get my account and messages pls

I replied …

You have few options left I’m afraid. Your messages are stored on your phone, that is the primary message store, so if you haven’t backed up your message store, there is little you can do – as I understand it – to recover your account. 

This is what Claude told me, using the text you typed above …

I’m sorry to hear your WhatsApp account has been compromised. This can be stressful, but there are steps you can take to recover your account and possibly your messages.

Here’s what you can do:

1. First, try to regain control of your WhatsApp account by verifying your phone number again. Open WhatsApp and follow the verification process.

2. If you’re locked out completely, contact WhatsApp support through their official website or app.

3. Unfortunately, without a backup (either on iCloud or Google Drive), recovering past messages is very challenging. WhatsApp doesn’t store your messages on their servers once delivered.

4. For your groups: once you regain access to your account, you may still see your groups listed, though you might not have the message history.

5. Ask friends or family members who are in the same groups if they can add you back to any groups you’ve been removed from.

6. For future protection, I’d recommend enabling two-step verification in WhatsApp settings once you regain access.

7. You should also consider changing passwords for any accounts that might share similar passwords to your compromised account.

Would you like more specific information about any of these steps? Have you been able to verify your phone number again in the app?

… and Perplexity …

If your WhatsApp account has been hacked and you don’t have backups on iCloud or a linked laptop, follow these steps:

  1. Log Out All Linked Devices: Open WhatsApp, go to “Settings” > “Linked Devices,” and log out of all unknown devices.
  2. Re-register Your Account: Uninstall and reinstall WhatsApp. Enter your phone number to receive a verification code via SMS. This will log out the hacker as WhatsApp allows only one active device per account.
  3. Two-Step Verification: If a PIN is requested and you didn’t set it up, the hacker may have enabled two-step verification. You can reset the PIN via the “Forgot PIN” option if an email is linked to your account.
  4. Contact WhatsApp Support: Email support@whatsapp.com detailing the situation with “Lost/Stolen” in the subject line for further assistance.
  5. Recover Messages Locally: If using Android, check local storage under Internal Storage/WhatsApp/Databases for backups (e.g., msgstore.db.crypt14) and restore them during reinstallation.

Inform your contacts about the hack to prevent further misuse of your account.

Nita replied …

The email account is compromised as cannot change my password

I think I am back up having reinstalled the what’s app 

Just need to check other social media accounts if compromised

Passkeys – Iain

https://www.howtogeek.com/microsoft-google-and-apple-want-you-to-use-passkeys-should-you

https://www.bbc.co.uk/news/articles/cvgn1lz3v4no

The AI slot

ChatGPT and model figures …

https://petapixel.com/2025/04/09/chatgpt-can-turn-you-into-a-toy-action-figure

AI & cataracts – Phil

AI and cataracts. Hi, I’m finding all sorts of ways to use Chat GPT. Yesterday I asked it to find me some private clinics that offered cataract surgery near Cardiff and to give me some idea of the prices, and it did just that. In seconds. I could have found the same information trawling through websites but this is so much quicker.

AI learns to reason??? – Iain

https://www.science.org/doi/10.1126/science.adw5211

… and we begin to understand how it works – Iain

https://www.technologyreview.com/2025/03/27/1113916/anthropic-can-now-track-the-bizarre-inner-workings-of-a-large-language-model

AI, chatbots and a new way to search

[Corrected information for Gemini in comparative section of post.]

A practical session following some demonstrations to encourage you to try out using Chatbot apps as an alternative to using a search engine. Of course most of the browsers and search engines now have the ability to “chat” added to them, ie Ecosia Chat and DuckDuckGo – which has the additional plus of you being able to choose which chatbot to use …

Claude tells me (as of October 2024) that the Edge, Opera, Chrome, Brave, Firefox and Arc browsers have this functionality, and Bing, Google (through Gemini), DuckDuckGo and Perplexity search tools have this functionality.

You can generate images too – but this is not the subject of today’s session. Look at Jonathan’s AI-generated avatar …

… or Phil’s set of images generated by Le Chat, from this script …

Screenshot

But we will look at how an image taken with your phone, or tablet, can be attached to a chatbot and get a summary of what it’s saying …

This (when sent to ChatGPT) with the one word message – “Summarise”, returned this …

  1. Online scamming is a global industry – It is vast, sophisticated, and growing rapidly, with criminal networks operating across borders.
    1. “Pig butchering” is a major scam method – Scammers build fake relationships with victims, emotionally manipulate them, and then convince them to invest in fraudulent schemes.
    2. Scamming is more dangerous than the drug trade – It operates beyond the reach of law enforcement, lacks regulation, and is highly scalable.
    3. Criminal compounds run large-scale scam operations – Many scams originate from compounds in Southeast Asia, where trafficked workers are forced into scamming.
    4. Advanced technology enables fraud – AI-generated voices, deepfake videos, and cryptocurrency help scammers operate anonymously and make their schemes more convincing.
    5. Scammers exploit human emotions – Victims fall prey to scams due to loneliness, fear, greed, and trust in online relationships.
    6. The economic impact is massive – Billions of dollars are stolen annually, affecting individuals, businesses, and economies.
    7. Law enforcement struggles to keep up – Scammers move money and people across jurisdictions faster than authorities can track them.
    8. International cooperation is needed – Countries must collaborate, working with banks, tech companies, and social media platforms to combat online fraud.
    9. Public awareness and education are crucial – Governments should implement stronger warnings and educational campaigns to prevent people from falling victim.

… but what is “pig butchering”, ask ChatGPT and you get this …

Pig butchering (shā zhū pán, 杀猪盘) is a sophisticated online scam that combines financial fraud with emotional manipulation. The term comes from the idea of “fattening up” a victim (the pig) before eventually “butchering” them for financial gain.

How It Works:
1. Initial Contact: Scammers approach victims through dating apps, social media, or even random text messages pretending to be a wrong number. They gradually build a friendly or romantic relationship.
2. Emotional Manipulation: Over weeks or months, scammers gain the victim’s trust, often pretending to be wealthy and successful. They encourage casual financial discussions, showing off their supposed investment profits.
3. Fake Investment Opportunity: Once trust is established, scammers introduce the victim to a “lucrative” investment, usually involving cryptocurrency or forex trading. They direct the victim to a fake but professional-looking website or app where they initially see small returns.
4. Encouraging Bigger Investments: As the victim gains confidence, they invest more money, sometimes even taking out loans or draining savings. The scammer keeps reinforcing the illusion of profits.

5. The Exit (Butchering Phase): Eventually, when the victim tries to withdraw funds, they encounter delays, extra fees, or are locked out entirely. The scammer then disappears, leaving the victim financially devastated.
6. Trafficking Connection: Many pig-butchering scams are operated from compounds in Southeast Asia, where trafficked workers are forced to run scams under threat of violence.

Why It’s Effective:
• Long-term manipulation: Unlike quick scams, it relies on slowly building trust.
• Emotional exploitation: Victims often feel emotionally invested, making them less skeptical.
• Convincing fake platforms: Sophisticated websites mimic real investment sites, making the scam seem legitimate.
• Cryptocurrency anonymity: Crypto transactions make it difficult to trace stolen money.

This type of fraud is one of the fastest-growing online crimes, with billions of dollars stolen worldwide each year.

That’s phenomenally powerful and time-saving!

So we’re going to look at installing some Chatbot apps, and doing some comparative enquiries, and end-up having some fun – I hope.

Le Chat helps me write this … “Provide a list of the most popular AI Chatbots, whether they’re open source and who they’re funded by?”

Here is a list of some of the most popular AI chatbots, their open-source status, and their funding sources:

  1. ChatGPT: Developed by OpenAI, ChatGPT is one of the most widely used AI chatbots. It is not open-source and is funded by Microsoft and other investors.
  2. Claude: Created by Anthropic, Claude is known for its conversational abilities and is considered one of the best overall AI chatbots. It is not open-source and has received significant funding from various investors.
  3. Google Gemini: Formerly known as Bard, Gemini is Google’s AI chatbot integrated with Google services. It is not open-source and is funded by Google.
  4. Microsoft Copilot: This AI chatbot is developed by Microsoft in collaboration with OpenAI. It is not open-source and is funded by Microsoft.
  5. Llama 3 by Meta: An open-source AI chatbot released by Meta AI. It is designed to be freely available for anyone to use and build upon. It is funded by Meta.
  6. Perplexity AI: Known for its ability to search the internet and provide relevant data, Perplexity AI is not open-source and is funded by various investors.
  7. Jasper AI: This AI chatbot is tailored for content creation and marketing. It is not open-source and is funded by various investors.
  8. Poe: Created by Quora, Poe allows users to access multiple AI models in one tool. It is not open-source and is funded by Quora.
  9. Rasa: A popular open-source framework for building conversational AI assistants. It is funded by various investors and is widely used in the developer community.
  10. DeepPavlov: An open-source conversational AI framework designed for developing production-ready chatbots. It is funded by various research grants and investments.

These AI chatbots represent a mix of open-source and proprietary solutions, each with its own strengths and funding sources.

Of these I do like Claude, Perplexity and Le Chat in particular, but Le Chat wasn’t in this list, why? I followed up my initial query with – “Why isn’t Le Chat in this list?”

Le Chat is an AI chatbot developed by Mistral AI, a French startup. It is designed to be a fast and efficient conversational assistant, capable of processing up to 1,000 words per second, making it one of the fastest AI models available. Le Chat is available as a native app for iOS and offers a range of features, including image analysis, content generation, and real-time internet searches. It is positioned as a European alternative to other AI chatbots like ChatGPT and Google Gemini.

Mistral AI has attracted significant investment from various sources, including American tech giants like Nvidia and IBM, as well as funding from the French government and other European investors. The company has also received support from France’s defense ministry and other European entities, highlighting its strategic importance in the region’s AI landscape.

Le Chat is part of Europe’s broader push for AI independence and is seen as a key player in the continent’s efforts to compete with major AI developers in the US and China. The chatbot is designed to offer strong privacy protections and aligns with European values regarding data security.

That’s why I like Le Chat – an element of independence from the US, but I suspect there will be a UK killer-chatbot in the wings!!!

I thought I’d do a comparative query across the different AI Chatbots I use – but in their web format so that I could do screenshots for this post [the responses would be the same on the phone/tablet – just easier for doing screenshots]. The query was fed to me by my daughter, and I followed the responses with some supplementaries (which I’m not including), but you’ll get the idea …

The enquiry … “In the UK, what I should plant in a western-facing partly shady coastal front garden with clayish soil?”

Le Chathttps://mistral.ai/products/le-chat

Screenshot

Perplexity (on the web I was given Perplexity Pro – presumable for a trial period) – https://www.perplexity.ai

Screenshot

For a full response – https://www.perplexity.ai/search/in-the-uk-what-i-should-plant-pu_I4lpmTKWVfR1U17OmrA

Claudehttps://claude.ai/new

Screenshot

the extreme – perhaps you have to pay to get access to Google’s own AI LLM – I’m happy to be corrected here!

Gemini (in a browser) returns this response …

https://g.co/gemini/share/ff8bfa44ae92

So to see how Gemini (in a browser looks), go to  https/gemini.google.com register (or use your Google account) and type in the enquiry. From the Gemini app it looks something like this …

In the UK, what I should plant in a western-facing partly shady coastal front garden with clayish soil? 🤗

It's great you're planning your coastal garden! Coastal gardens in the UK present some unique challenges, but also opportunities. Here's a breakdown of considerations and plant suggestions, taking into account your western-facing, partly shady, clayish soil conditions:
Key Challenges:
* Coastal Conditions:
* Salt spray: Plants need to tolerate salty air.
* Strong winds: Choose robust, wind-resistant plants.
* Potential for sandy, but in your case clayish soil.
* Western-Facing, Partly Shady:
* Western exposure means afternoon sun, which can be intense.
* "Partly shady" requires plants that can handle some shade but also appreciate some sun.
* Clayish Soil:
* Clay soil can be waterlogged in winter and dry and cracked in summer.
* It's essential to select plants that tolerate these conditions or amend the soil.
Plant Recommendations:
Here's a selection of plants that generally thrive in these conditions:
* Shrubs:
* Escallonia: Very tolerant of coastal conditions and wind.
* Photinia: Provides vibrant foliage and tolerates clay soil.
* Hebe: Many varieties are well-suited to coastal gardens.
* Lonicera nitida (shrubby honeysuckle): Good for hedging, tolerant of various conditions.
* Perennials:
* Hostas: Thrive in partial shade and tolerate clay.
* Ferns: Many ferns enjoy shady, moist conditions (clay can hold moisture).
* Pulmonaria (lungwort): Tolerates shade and clay soil.
* Geraniums (hardy): Many varieties are adaptable to various conditions.
* Sea thrift (Armeria maritima): Excellent for coastal areas.
* Grasses:
* Carex varieties: Many sedges tolerate clay soil and partial shade.
* Festuca glauca (blue fescue): Can add textural interest.
Tips for Clay Soil:
* Improve drainage: Incorporate organic matter like compost or well-rotted manure to improve soil structure.
* Mulching: Apply a mulch to help retain moisture in summer and protect roots in winter.
* Raised beds: Consider raised beds if drainage is a significant issue.
Where to Get More Information:
* Royal Horticultural Society (RHS): The RHS website (rhs.org.uk) is an excellent resource for plant information and gardening advice.
* Local Garden Centres: Local garden centres can provide tailored advice for your specific area.
When choosing plants, always check their specific requirements and consider your garden's microclimate.

Copilothttps://copilot.microsoft.com/chats/tBUeqP4WXhs3BKq8a6zy5. It has to be said the app version is quite different in appearance (so I include it below as well.

Screenshot
In the UK, what I should plant in a western-facing partly shady coastal front garden with clayish soil? 🤗

Ah, a coastal garden in Wales with clayish soil—sounds like a wonderful challenge! For a western-facing garden with partial shade and a seaside breeze, you'll want plants that can handle salt spray, thrive in heavy soil, and enjoy a mix of sun and shade.

Here are some suggestions:

### Perennials and Shrubs:
1. **Eryngium (Sea Holly)** - Perfect for coastal gardens with its striking, spiky flowers and tolerance for salty air.
2. **Hydrangea macrophylla** - Thrives in clay soil and gives fabulous blooms, especially in partial shade.
3. **Hebe** - Compact, hardy, and salt-tolerant, making it ideal for coastal fronts.
4. **Skimmia japonica** - Great for partial shade, and its colorful berries add winter interest.
5. **Rosa rugosa (Beach Rose)** - Tolerates tough coastal conditions and produces lovely fragrant flowers.

### Grasses:
1. **Carex (Sedges)** - Many varieties thrive in clay soil and are low-maintenance.
2. **Festuca glauca (Blue Fescue)** - Adds texture and color, and it’s very hardy.
3. **Miscanthus sinensis** - Works well in heavier soils and creates a striking backdrop.

### Flowering Plants:
1. **Alchemilla mollis (Lady's Mantle)** - Thrives in partial shade and tolerates clay, with charming frothy flowers.
2. **Astrantia** - Adds a touch of elegance with its intricate blooms and loves partial shade.
3. **Primula vulgaris (Primrose)** - Ideal for dappled shade, and they bring an early splash of color.

### Ground Covers:
1. **Ajuga reptans (Bugleweed)** - Tolerates clay and partial shade while offering glossy foliage and purple flowers.
2. **Vinca minor (Lesser Periwinkle)** - A hardy ground cover that thrives in shady spots.

It’s also worth working organic matter like well-rotted compost into the clay soil to improve drainage and structure over time. Coastal gardens can be unique, so experimenting with a mix of hardy and native plants might lead to delightful surprises. 😊

What do you think about these options? Let me know if you'd like specific care tips or alternatives!

I hope that’s of interest; I encourage you to do your own comparative enquiries, bearing in mind that they don’t all have access to up-to-date information.

The world is changing rapidly, and my son has already demonstrated that he can build the code for the front-end of a website using a chatbot which he incorporated into his DuckDuckGo browser …

Screenshot

… with the following instructions …

“I asked my new AI app writing tool to build me a private social networking tool inspired by Google+ features.

Just done the front end design, but I can add a database and I can get it to setup federation with Google login.

It’s mobile responsive as well.”

… now that’s truly amazing, but I digress.

Creating a sitcom

First prompt.

Can you come up with some sitcom names that would cover two elderly people, one who loves technology and loves setting up systems, and the other who has no idea?

then i got names … i responded -> I like wired and retired.

Second prompt

Can you write the premise of the show. The grandad gets very frustrated cause he sets up all these amazing systems and is energised by tech but his wife (grandma) is airy fairy and likes more human pursuits and poetry and gardening and is shocking at planning and execution. Both are lovely.

This was the response.

Show Title: Wired and Retired

Premise:
In the quiet suburbs, a lively retired couple navigates the collision of their wildly different passions. Frank, a tech-obsessed granddad, thrives on systems, automation, and the latest gadgets. His garage is a command center, his home a hub of interconnected brilliance—at least in his mind. Meanwhile, Betty, his whimsical wife, prefers the analog world. She spends her days writing poetry, tending to her unruly garden, and losing herself in daydreams.

Their love is undeniable, but their worlds often clash in hilarious ways. Frank’s perfectly calibrated smart irrigation system gets overrun by Betty’s impulsive planting sprees. His meticulous meal-planning app gets sidelined when Betty decides dinner should be a spontaneous pic… Read more

then he just kept asking questions

until he got to …

Updated Premise:
Retired life for Frank and Betty is far from quiet. Frank, a tech-obsessed granddad, keeps busy in his upstairs office, perfecting his gadgets, cheering for West Ham, and sneaking out for his favorite snack, ‘Nice and Spicy’ Nik Naks. Betty, his free-spirited wife, thrives on poetry, gardening, and unplanned adventures that constantly disrupt Frank’s meticulously planned systems.

Their quirky family dynamic adds another layer of hilarity. Their 40-something son, who lives nearby, frequently steps in as mediator and problem solver, though his visible hair loss suggests he’s barely holding it together. Their older son, who lives in Australia, adds to the chaos during his visits, gleefully stirring up trouble and playing both parents off each other.

Balancing out the chaos is their serious older daughter, a psychologist, who watches the family dynamics with professional concern. She often finds herself frustrated with her brothers’ antics and their impact on her parents, though her attempts to intervene usually go unnoticed.

Adding warmth to the mix is their youngest daughter, who lives close by with her young family. Betty adores spending time with her grandchildren, but her tendency to lose track of time often leaves Frank exasperated when she abandons his carefully laid plans for yet another spontaneous outing.

Through all the love, laughter, and occasional family drama, Frank and Betty prove that life is always better with a little humor—and a lot of heart.

Supporting Characters:
• Millie: The tech-savvy granddaughter who enjoys Frank’s high-tech world but often teams up with Betty during family adventures.
• George: Frank’s West Ham-loving best mate and snack-run partner, who adds to the laughs.
• Dorothy: Betty’s poetic and gardening partner, who fuels her creative chaos.
• Alan: The middle son, a local, stressed-out mediator whose receding hairline marks his thankless efforts to keep the peace.
• David: The mischievous older son from Australia, who stirs up trouble whenever he visits.
• Clara: The serious older daughter, a psychologist, who’s always concerned about the family’s dynamics, especially her brothers’ antics.
• Lucy: The youngest daughter, whose young family brings joy and chaos into Betty’s life, often making her forget time (and Frank’s plans).

Tone:
A heartwarming sitcom full of humor and relatable family moments, Wired and Retired celebrates the beauty of intergenerational dynamics, proving that even in retirement, life is a delightful blend of love, laughter, and just enough chaos to keep things interesting.

… and then we got Episodes of the sitcom …

Episode Titles:
1. “Password Protected”
Frank’s new smart home security system locks Betty out after she forgets the password during a gardening spree. Alan is called in to mediate, only for the system to malfunction spectacularly during a surprise visit from David.
2. “Nik Nak Sneak Attack”
Frank’s secret snack stash is discovered by Betty, who replaces his ‘Nice and Spivey’ Nik Naks with healthy alternatives. Desperate to retrieve his beloved snack, Frank ropes Millie into a covert snack run that goes hilariously wrong.
3. “The Poetry of Football”
Frank prepares for a big West Ham match, but Betty accidentally double-books the living room for her poetry club meeting. Clara arrives to mediate, but her psychological insights only make matters worse.

4. “Down the Rabbit Hole”
Betty gets caught up babysitting Lucy’s kids and loses track of time, leaving Frank stranded at a gadget expo. When Lucy apologizes, Frank realizes he enjoys the quiet chaos of his grandkids—until they discover his gadgets.
5. “Springsteen & Shenanigans”
David’s visit from Australia throws the household into disarray as he tries to convince Frank to join a local Springsteen tribute band while secretly encouraging Betty to paint her garden shed bright pink. Alan is left to clean up the mess.
6. “Psychologist vs. Chaos”
Clara decides to hold a family therapy session to address everyone’s dynamics. But when old grudges resurface and Frank’s gadgets interrupt the session, Clara questions if anyone can truly retire from family drama.

and a 30-Minute Episode Outline:

Episode: “Password Protected”

  1. Cold Open (2-3 minutes)
    Betty struggles with Frank’s new voice-activated front door lock after forgetting the password. She tries random phrases (“Bruce Springsteen rules!”) but is locked out. Frank smugly explains the system’s brilliance—until it locks him out too.
  2. Setup (5-6 minutes)
    Frank works on fixing the system while Betty heads to the garden, only to accidentally trigger the motion sensors. Chaos ensues as Frank’s phone floods with alerts. Alan shows up after receiving a frantic call from Betty.
  3. Rising Action (6-8 minutes)
    Alan tries to mediate, but the system glitches and locks everyone—including Millie, who came to help—inside the house. Betty starts reciting poetry to keep calm, which Frank finds infuriating. Meanwhile, David calls from Australia, adding comic commentary.
  4. Climax (7-8 minutes)
    Alan manages to bypass the system just as Betty’s gardening friends arrive for tea, unwittingly triggering the alarms again. Frank declares the system a failure and blames Betty, who points out she only wanted a simple lock and key.
  5. Resolution (3-4 minutes)
    Frank reluctantly agrees to simplify the system but secretly tinkers with it that evening. Betty catches him sneaking a Nik Nak, teasing him that even his snacks need a password.

Tag Scene (1 minute)
The system malfunctions during the night, locking the entire family in the bedroom. Betty smirks, “At least we’re safe from burglars.” Frank sighs, “Or freedom.”

Each episode mixes laugh-out-loud situations with heartfelt moments, showing that even retirement is full of surprises!

Now it’s your turn!!!! This was all generated using ChatGPT, but the other AI chatbots could probably do the same.

Phil’s AI experiments

I’m thinking/hoping that Phil will be writing his own post on the subject; but I’ve just posted this article – using the form at the bottom of the Member Posts menu item from the Digital Matters tab on the website as a placeholder for his Composers work …

Composers