No, it’s not OK to call your boss a “Dickhead”

The media had a field day last week with a story that an Employment Tribunal had ruled that being sacked for calling your boss a “Dickhead” was grounds for Unfair Dismissal. As always when it comes to the reporting of Employment Law stories, the old adage “never let the truth get in the way of a good story” applies here.

The case involved a Ms Herbert, who was sacked from the small construction business she worked for by its Operations Director.  He was also Ms Herbert’s brother in law, and was married to the Managing Director who was therefore her sister in law.

Most of the facts were disputed – included the date Ms Herbert was dismissed. The only consistent fact that everyone agreed on was that at some point in the meeting where she alleged she was dismissed, she used the words “fucking dickheads” to describe the Operations Director and his wife.

The reason she won her case was that the company made a complete pig’s ear of dealing with the situation. In fact pretty much everything they could have got wrong they did.

  • When the ‘dickheads’ comment was made, the Operations Director told Ms Herbert to ‘get out’ and that she was ‘sacked’
  • The company then tried to construct a case about Ms Herbert’s misconduct and hold a later disciplinary hearing on a series of alleged serious breaches of company rules. She refused to participate in this process on the basis that the company had already sacked her.
  • The context in which the comment was made was not enough to justify a gross misconduct dismissal – and therefore she was entitled to be paid notice. In fact their company policy said that use of ‘insulting and abusive language’ would only result in dismissal if a prior warning had been given.

There are three important takeaways for small businesses from this case – none of which are around what Ms Herbert said

  • Employment Tribunals deal with the facts in each individual case. This decision does not set a precedent in any way, and especially it doesn’t give a green light for employees to abuse their bosses without penalty.
  • To make a dismissal fair, you have to have a fair reason and follow a fair procedure. The judge did conclude that Ms Herbert’s behaviour could well have been a fair reason but the Operations Directors ‘spur of the moment’ decision was not in any way a fair process.
  • The case shows starkly how long the tribunal process is taking – the events of this case happened in 2022 but the decision was not published until last week. Regardless of who is right or wrong, having a claim that takes 3 years to resolve is not a sensible way to resolve employment disputes (and as this article shows, this is not an untypical timescale)

Why I won’t be using AI anytime soon

Why I won’t be using AI anytime soon

Every time I log on these days, I’m bombarded with articles about Artificial Intelligence (AI) – whether it is how it is the most wonderful labour saving thing ever (I’d send an avatar to a meeting too if I had the option!)  – to the apocalyptic, with some predicting, Terminator style, in AI wiping out humanity.

While I don’t fall into either category, I’m certainly a sceptic about its uses, particularly some of the most common AI bots that are available (ChatGPT/Meta/Gemini/Grok/Glamdring/Wall-E/Co-Pilot etc). Here’s why:

  • They get things wrong:

If you ask Gemini who Sarah O’Connor is, it will tell you she’s a truck driver who was interviewed for the Financial Times.  In fact she’s a highly regarded FT journalist. While Chat GPT informed me that drug dealer Howard Mark’s autobiography was called “Thy Damnation Slumbereth Not” and even explained to me how he’d arrived at that title. It’s not called that at all.

  • It makes stuff up:

Gemini created a totally fictitious act of parliament (“The Civil Justice Act 2004”). And a barrister nearly got themselves into very hot water with a judge for citing fictitious AI generated case law in court.

  • It can’t do certain things (but pretends it can)

This video from people professional Julie Drybrough, when she asked ChatGPT to help create a presentation for her reveals it be like an over-confident intern  – claiming it can do the job and constantly saying it was doing it, before finally admitting that it was unable to complete the task.

  • It doesn’t know what it doesn’t know

Large Language Learning Models (the basis of AI) has to learn from something. However, despite what we might think, not all human knowledge is on the internet. There are still plenty of books, films and novels that aren’t available and many museum and library archives are not yet digitised, or where access is limited. So, ask a question that it doesn’t know the answer to and it may be honest and admit it doesn’t know – but equally it may revert to point above and just make it up.

  • It comes with a lot of ethical and environmental concerns

Meta AI has been subject to a lot of criticism for using illegal copies of copyright works to train its AI (they are probably unlucky that they got caught since I can’t imagine that the other leading AI providers paid for their sources). If you don’t think that’s a problem, try walking out of Waterstone’s with a book you haven’t paid for, and use the defence of “I wasn’t stealing, I just wanted to read it to learn what it contained”

While the environmental consequences in terms of water use and electricity are only just becoming known – but one stat that stands out is that a Chat GPT query uses ten times the amount of electricity as a standard Google search.

And what does all this mean for managing  people in a business?

Firstly, relying on AI for information on employment law is risky to say the least. Like Wikipedia, it might be correct, but unless you know already you can’t be certain that it’s giving you the right information.

Secondly, AI can’t possibly know the information in a human head. For example, much of my understanding of HR issues comes from nearly 40 years of experience with a variety of industries and sectors. AI cannot possibly replicate what I learned from the Merseybus bus cleaning dispute in 1995 or the competitive tendering process for Leisure Centres in Runcorn in 1990. Or a TUPE transfer I managed between construction companies in 2004. Or how to deal with an employee charged with child abuse, or who one is terminally ill.

Finally, AI doesn’t understand culture. A solution that works in one company context may not be the most effective or appropriate in a different one, for lots of very valid reasons. AI might give you a range of solutions but can’t advise you on which one might be the best.

I’m sure that in 5 or 10 years, some of these issues with AI might be resolved. But until then, if you ask me to support your business with HR issues, you can be certain that you will be getting advice from an actual human, not a bot.

Just out of interest, I got Microsoft’s Co-Pilot AI (which is built into the latest versions of Word/PowerPoint/Excel etc) to rewrite this post for me. You can read what it came up with (minus the hyperlinks) here

bionic hand and human hand finger pointing
Photo by cottonbro studio on Pexels.com

Why I won’t be using AI (Co-Pilot’s version)


Title: The Impact of Artificial Intelligence: A Critical Examination

In today’s digital age, the prevalence of articles about Artificial Intelligence (AI) is overwhelming. From claims of AI being the ultimate labor-saving tool (who wouldn’t want to send an avatar to a meeting?) to apocalyptic predictions of AI wiping out humanity in a Terminator-style scenario, the discourse is varied and intense. While I don’t subscribe to either extreme, I am certainly skeptical about its applications, especially the most common AI bots available (ChatGPT, Meta, Gemini, Grok, Glamdring, Wall-E, Co-Pilot, etc.). Here’s why:

1. Inaccuracies and Errors

AI bots often get things wrong. For instance, if you ask Gemini who Sarah O’Connor is, it will tell you she’s a truck driver interviewed for the Financial Times. In reality, she is a highly regarded FT journalist. Similarly, ChatGPT once informed me that drug dealer Howard Marks’ autobiography was titled “Thy Damnation Slumbereth Not” and even explained the reasoning behind the title. This is incorrect.

2. Fabrication of Information

AI can create completely fictitious information. Gemini once generated a non-existent act of parliament (“The Civil Justice Act 2004”). Additionally, a barrister nearly faced serious consequences for citing fictitious AI-generated case law in court.

3. Overconfidence in Capabilities

AI sometimes pretends to be capable of tasks it cannot perform. In a video by people professional Julie Drybrough, ChatGPT was asked to help create a presentation. It claimed it could do the job and repeatedly stated it was working on it, only to finally admit it was unable to complete the task.

4. Limited Knowledge Base

Large Language Learning Models, the foundation of AI, must learn from existing data. However, not all human knowledge is available on the internet. Many books, films, and novels are not digitized, and numerous museum and library archives have limited access. When faced with a question it doesn’t know the answer to, AI may either honestly admit its ignorance or revert to fabricating information.

5. Ethical and Environmental Concerns

AI development raises significant ethical and environmental issues. Meta AI has faced criticism for using illegal copies of copyrighted works to train its models. The environmental impact is also concerning, with a ChatGPT query consuming ten times the electricity of a standard Google search.

Implications for Business Management

Relying on AI for information on employment law is risky. Like Wikipedia, AI might provide correct information, but without prior knowledge, you cannot be certain of its accuracy. AI cannot replicate the nuanced understanding gained from years of experience in various industries, dealing with trade unions, disputes, and complex issues. It also fails to grasp cultural contexts, making it difficult to determine the most effective solutions for different company environments.

While some of these issues with AI may be resolved in the next 5 to 10 years, until then, if you seek support for HR issues, you can be assured that you will receive advice from an actual human, not a bot.


A group of people engaging with a futuristic holographic interface, focusing on digital technology and artificial intelligence concepts.
The Law Trumps Soundbites

The Law Trumps Soundbites

There’s been a lot of noise over the last few weeks, mainly as a result of actions of the new American president, about Diversity, Equality and Inclusion (DEI) programmes within business. It’s been compounded by some American business leaders talking about the need for more “masculine energy” in business (whatever that term means).

Even though the cultural and business contexts of the UK and the US are different, this hasn’t stopped much chatter amongst business commentators here about the future of DEI. So it’s probably worth going over what the situation is here, especially from the perspective of small business.

Firstly, outside of some public sector organisations and some very large corporates – often subsidiaries of US companies –  very few companies in the UK have DEI programmes in the US style.

What we do have in the UK though is the Equality Act 2010.  This hasn’t changed, isn’t going to change in the next 5 years at least, and sets down the basis under which all UK businesses have to act.

This Act makes it explicit that you cannot discriminate on the basis of a one of 9 “protected characteristics” (with some very limited exceptions). Every single person in the UK possesses at least two of these protected characteristics (most have more) so it covers everyone.

Discrimination can result in unlimited fines – and unlike most aspects of employment law, claims can be made against individuals as well as businesses.

Discrimination applies equally to so-called ‘positive discrimination’ – for example deliberately favouring a female candidate in preference to a man (because you think your business needs more female staff) is as forbidden as the reverse. In fact there have been recent employment tribunal cases that have reaffirmed this.

What the law does allow – on an entirely voluntary basis – is ‘positive action’.  You might for example run an engineering company where all your engineers are of a certain age group and you are struggling to find younger candidates interested in the job. Positive action might be running taster days for young engineers, or attending careers fairs aimed at school leavers or recent graduates. It doesn’t mean that a younger person is going to get the job ahead of an older person, simply that you are creating opportunities for younger people to meet your requirements. Which, if you are struggling for staff, is a business benefit. Some larger companies might run training schemes targeted specifically at under-represented groups – again this is perfectly permissible. None of this is new – firms have been doing this since the 1980s.

Regardless of your own views on DEI, or what you have read on social media or heard on the news, the situation in the UK hasn’t changed. There is no such thing as a ‘diversity hire’ in the UK, nor can you start advertising for ‘young men’ or rejecting candidates because of their race or religion.

Small Earthquake in Chile: Not Many Dead

So, finally, after much speculation, press leaks, anguished cries from business and reports of government in-fighting, we finally have the new government’s Employment Rights Bill.

And, to be honest, it’s a bit of an anti-climax. There are lots of minor tinkering with existing rules, many of which have little uptake, or extending existing rights to people who don’t currently qualify. Some of the key proposals are:

  • The right to claim unfair dismissal, although it will become formally a day-one right, will in practical terms be reduced from requiring 2 years’ service to 9 months’ service.
  • The right to statutory sick pay will be available to all employees from day one regardless of their earnings. Currently it’s not payable until day 4 of sickness and only for those who earn more than £123 a week  (for context that means anyone who does more than 11 hours per week at adult minimum wage already qualifies)
  • Rights to parental leave. paternity leave and bereavement leave from day 1 of employment rather than requiring a minimum qualifying period. As parental leave in particular is unpaid, hardly anyone uses it currently so extending it is unlikely to see a massive increase in time off.
  • Strengthening and extending existing  unfair dismissal protections for women on maternity for up to 6 months after they return.
  • Flexible working requests must be accepted unless the Employer has a valid business reason to say no. Currently employers must justify saying no with a valid business reason so in practice it’s unlikely to make much of a difference.
  • Rules on zero hours will be changed so that workers  have the right to a contract based on the average number of hours over the preceding 12 weeks (but can choose to stay on zero hours if they prefer). Those of you who’ve read my recent employment law update (sign up here if you don’t already get it) will know that this had already brought into law by the previous Conservative government but not actually implemented.
  • Abolishing some of the previous Government’s restrictive rules on trade unions and strike action – which were rarely used by employers and were not particularly relevant to small business.
  • There will be a lot of consultation on various other aspects of employment law, including
    • The ‘Right to Switch off’  – which it appears may now just be a code of practice rather than a legal requirement.
    • Clarifying the law around employment status – an area which appears very nerdy but is key to businesses that use sub-contractors, casual workers and ‘gig economy’ working practices
    • Considering how equal pay legislation can be extended to cover race as well as sex

Most importantly, the changes themselves are unlikely to be implemented until at least 2026 – which means that businesses will have plenty of time to prepare for them.

After all the hype, it appears we are left with simply a continuation of the approach to employment law of the last 14 years – minor tinkering with particular rules that give some additional benefits to employees but at minimal discomfort to business.

(As an aside, if you’re wondering about the post title you’ll find the origin here)