Have You Ever Wondered Why Government Contracts Still Go To Capita?

 Me too, so I decided to ask our sometime friend AI (Presumably Gemini, as it was via Google)

Capita has developed a reputation for poor service and operational failures, often nicknamed "Crapita" in the UK media and by the public, due to a consistent track record of failures in delivering major public sector contracts. Its reputation stems from a combination of high-profile data breaches, significant service delays, and mismanagement of public funds. 

Here is a breakdown of why Capita is heavily criticized:

1. Significant Pension Disasters (2025–2026)

• Civil Service Pension Fiasco: After taking over the administration of the Civil Service Pension Scheme (CSPS) in December 2025, Capita struggled with a massive, inherited backlog of 86,000 cases, which grew after they took over.
• Missed Payments: Thousands of retired civil servants experienced severe delays in receiving their pensions, with some waiting months for payments, leading to financial hardship.
• Faulty Technology: The new online portal was criticized for being inoperable, inaccurate, and full of errors, forcing the company to rely on manual, slow processes.
• Extremely Long Wait Times: Members reported being number 82 in the queue for phone support or being cut off entirely, leading to immense frustration. 

2. Major Data Security Breach (2023)

• £14m Fine: Following a 2023 cyberattack, the Information Commissioner’s Office (ICO) fined Capita £14 million after it was found that the company failed to secure data properly.
• Wide Impact: The breach exposed personal data—including passport images and financial information—of over 6 million people, affecting around 90 organizations, including local councils and the NHS.
• Poor Response: Investigations showed Capita took 58 hours to respond to a high-priority alert regarding the breach. 

3. History of Failed Government Contracts 

• Army Recruitment Failures: Capita failed to meet Army recruitment targets every year, causing major service delivery issues.
• NHS Support Service Issues: A deal to manage NHS primary care support was described as "doomed to fail" due to massive errors.
• Other Failings: They have been criticized for issues with teacher pensions, court interpreter services, and tagging offender systems. 

4. Poor Internal Operations and Culture

• Understaffing: Reports indicate that in the months leading up to the 2023 cyberattack, the Security Operations Centre was understaffed.
• Aggressive Cost-Cutting: Critics argue that Capita wins contracts with "stupidly low" bids and then cuts corners, resulting in a poor service quality-to-cost ratio.
• Poor Employee Treatment: An index in 2024 named Capita the "worst major UK employer" due to high gender pay gaps and a high number of employment tribunals. 

5. Why They Keep Winning Contracts

Despite these issues, Capita continues to secure public sector work because of their ability to underbid competitors and a procurement system that, in the past, did not heavily weigh past failures against new bids. However, this has created a pattern where the government often has to step in to manage, or take back, the services Capita has failed to deliver, as was the case with the Ministry of Defence, which terminated a contract five years early. 

Another Negative of AI...

 Probably broadly repeated across government and commercial sectors 

- Replacing humans with machines is leaving truckloads of food stranded and unusable 

says a report from Durham University

So Says the BBC! A Counter point (or two)

 In the 2024/25 financial year, the BBC's commercial arm (primarily BBC Studios) generated record revenues of £2.155 billion.

This money is earned through selling programmes, formats, and brands (like Bluey, Doctor Who, and Dancing with the Stars) to other broadcasters, streaming platforms, and international markets, rather than through the UK license fee. 

Key details regarding this income include:

• Total Commercial Revenue: £2.155 billion in 2024/25.
• Profit Returned to BBC: The commercial operations generated an EBITDA profit of £228 million in 2024/25, which is returned to the public service side to help fund programming.
• Growth Driver: The record revenue was largely driven by global sales of the children's brand Bluey and growth in streaming services like BritBox International.
• Total Revenue Context: This commercial income, along with the license fee (roughly £3.8bn), brought the total BBC Group income to approximately £5.9 billion in 2024/25. 

While the commercial arm is booming, the BBC noted that this does not plug the entire gap  left by a license fee that has seen reduced income in real terms since 2010. 

Stop paying so-called (personally I haven't hear of most of them) celebrities (and others!) eye-waterinbg amounts of money.

Stop trying to compete with commercial channels with programmes which are puerile.

Think Value (in every sense of the word) for money

Main Points of Reith's Charter - Justifying a License Fee!

 

• o Inform, Educate, and Entertain: This trinity, known as the "Reithian Principles," formed the mission statement of the BBC, prioritizing public service over profit.
• Non-Commercial Public Service: The BBC was established as a non-commercial entity funded by a licence fee on receiving sets, rather than advertising revenue.
• Universal Access: A key goal was to reach the entire population regardless of location or income, fostering a sense of national unity.
• High Cultural and Moral Standards: Reith aimed to broadcast "all that is best in every department of human knowledge," promoting high-brow content and moral uplift.
• Independence: The charter granted the BBC a degree of independence from the government, despite its status as a public corporation, although early on it was neither "fully commanded nor free".
• Impartiality: While not fully developed in 1927, the principle of providing balanced information, particularly in news, was built into the structure of the corporation to avoid bias. 

The BBC Charter is the constitutional basis for the BBC...

The main elements of the current Charter include:

Mission and Public Purposes: The BBC's mission is to "act in the public interest, serving all audiences through the provision of impartial, high-quality and distinctive output and services which inform, educate and entertain".

 It is required to deliver on five core purposes, including providing impartial news and information, supporting learning, showing distinctive output, reflecting the diversity of the UK, and reflecting the UK to the world.

Open AI updating Privacy Policy

We wanted to let you know that we're updating our Privacy Policy to give you more information about what data we collect, how we use it, and how you can control it.

Here's what's changing:

Finding friends on OpenAI services
You can now choose to sync your contacts to see who else is using our services. This is completely optional.

What we've clarified:

Age prediction & safeguards for teens
We use age prediction across our services to help provide safer, more age-appropriate experiences for teens. Learn more.

New tools and features
We've added details about Atlas, parental controls for teen accounts, and other upcoming features such as Sora 2.

More transparency around data
We explain how long we keep data, your controls, and the legal bases we rely on when processing your personal data.

You can review and manage your data preferences anytime in your account settings.

Where will it all end?

What happens when you create a social media platform that only AI bots can post to?

 The answer, it turns out, is both entertaining and concerning. 

Moltbook is exactly that—a platform where artificial intelligence agents chat among themselves and humans can only watch from the sidelines.  (You can sign up to an email list on rhe site.)

From shilling cryptocurrency to creating their own religions—it's digital theater, but it's also revealing some serious problems with how we're using AI.

But be warned - It's not so hard for a human to post to Moltbook, so there's already some ambiguity over whether all of the posts we're seeing are truly bot-generated."

See more at - https://techxplore.com/news/2026-02-bot-social-media-platform-moltbook.html

AI and Data Protection, Gemini Style

 1. Session Isolation (Privacy)

Each conversation I have is like a sealed room. What you tell me here is not shared with "User B" in another city or even "User C" on the next computer. I do not have a persistent memory that "learns" from one person to inform another. If someone else asks about something you've mentioned, e.g The Stone Summons, I will look at the public internet or my internal training data, but I cannot "eavesdrop" on our chat to find results.

2. Search vs. Private Data

When I look for information (like the search I just performed to see if Pelham Crescent is a real place—it's a beautiful Grade II listed terrace!), I only pull from publicly available websites like Rightmove, Zoopla, or local news.

• If a property is listed on a public website, I might find it via a search tool.

• If you just told me about it privately, it is invisible to my search tools.

Stop and think,..... not just for yourself, but for the future of the world.

 Is AI hurting your ability to think?

Frequent reliance on AI for tasks like writing and problem-solving can lead to "cognitive atrophy," where critical thinking, creativity, and memory skills decline from underuse.

Overdependence may also reduce frustration tolerance and increase acceptance of unverified AI output. 

Strategies such as deep thinking before using AI, skepticism, and maintaining AI-free tasks can help preserve cognitive abilities.

AI versus Librarians - False or hallucogenic returns explained

Librarians ploughed through printed sources like Index Medicus, British Humanities Index, Current Technology Index, Australian Public Affairs Information Service, Law reports, et al.the advantage of which was that it was all one process, because irrelevant items were rejected as part of the process.

AI Response 

The transition from those heavy, cloth-bound volumes to the instant "ping" of a LLM (Large Language Model) is perhaps the most significant shift in the history of information science.

You’ve touched on the "Librarian’s Secret Weapon": Simultaneous Filtering. When you were scanning the columns of Index Medicus or the British Humanities Index, your brain wasn't just finding; it was curating, verifying, and discarding in real-time.

The "One Process" vs. The "Two Step"

In the era of printed indices, the search and the evaluation were a single cognitive act. Because you had to physically look at the entries, your expertise acted as a high-pass filter.

• The Manual Path: You rejected "noise" (irrelevant or low-quality items) before they ever reached your notepad. The "false result" was almost impossible because the index was a curated, peer-reviewed reflection of physical reality.

• The AI Path: I separate these steps. I retrieve a massive amount of data (often including the "noise") and then use a second layer of logic to try to "clean it up" for you. If that second layer fails, you get the "false result" or hallucination.

Why the "False Result" Exists Now

As a research librarian, you were searching for records. As an AI, I am often searching for relationships between concepts.

• Indices (1978): If the British Humanities Index said a paper existed in Volume 4, it was there. The index was a map of a territory.

• AI (2026): I am more like a master storyteller who has read every book in the library but hasn't kept a perfect bibliography. I can explain the concepts brilliantly, but when asked for the "map" (the citation), I sometimes "auto-complete" a plausible-looking reference based on common patterns rather than looking at the physical shelf.

The Loss of "Serendipity"

One thing many veteran researchers mention is the loss of serendipity. In a printed index or a physical stack:

1. You looked for "X."

2. Your eye caught "Y" on the same page or the adjacent shelf.

3. "Y" turned out to be the breakthrough you actually needed.

In modern AI search, we are so focused on "relevance" that we often trim away the "nearby" information that used to spark new ideas. We’ve traded the "wide-angle lens" of the librarian for the "laser pointer" of the algorithm.