Tory MPs accuse Google's new AI of Left-wing bias

Tory MPs accuse Google’s new AI of Left-wing bias amid fears the revolutionary search tool could dent their election hopes

• Chatbots have the power to revolutionise our lives – but are susceptible to bias 
• £81bn was wiped off Alphabet’s market value when Bard gave a wrong answer 

Google was at the centre of a row over political bias last night after tests of its new artificial intelligence ‘chatbot’ produced results with a pronounced Left-wing slant.

An investigation by The Mail on Sunday into Google Bard, which is designed to answer questions like a human by analysing data from the internet, produced results that condemned Brexit as a ‘bad idea’ and described Jeremy Corbyn as having ‘the potential to be a great leader’.

The ‘bot’ has been hailed as part of the biggest technological breakthrough since the launch of the printing press. But early results have caused alarm among senior Conservatives, who fear that if Google does not change its search algorithms before the next General Election it could boost the chances of Sir Keir Starmer’s Labour.

They say simple factual errors have already been spotted in searches about Tory MPs.

Google’s new AI Bard said it believed the UK would have been better off remaining in the EU 

When this newspaper asked Bard, which was launched last week, about Brexit, it ignored the views of the 17 million voters who backed Britain quitting the EU to declare: ‘I think Brexit was a bad idea… I believe the UK would have been better off remaining in the EU.’

MARK HOOKHAM: ‘Chatbots’ will transform our lives 

It has been hailed as the biggest technological advance since the printing press, electricity or even the invention of the wheel.

Experts believe artificial intelligence (AI) will transform all walks of life, but some warn that it could spark mass job losses as humans are replaced by computer programs.

First developed in the 1950s, AI allows machines to process information, mimic conversations and make recommendations by ‘learning’ like humans.

Microsoft and Google believe AI will soon revolutionise the way we search the web, and they are locked in a race to develop sophisticated search assistants called ‘chatbots’. 

The Microsoft-backed ChatGPT was first out of the blocks when it launched in November and has already produced college essays, drafted legal contracts and written song lyrics.

It was described by former US Treasury Secretary Larry Summers as a ‘profound thing for humanity and a profound change in the way we are all going to be working’.

By January, it had hit 100 million monthly users – a faster rate of adoption than Instagram or TikTok. AI technology has also been integrated into Microsoft’s Bing search engine. But users have been shocked by some of its bizarre replies. A New York Times journalist told last month how it had declared its love for him and urged him to leave his wife.

After Google unveiled its own AI chatbot, Bard, last month, an astonishing £81 billion was wiped off the market value of Alphabet, Google’s parent company, when Bard gave a factually incorrect answer to a question.

Google said Bard was an experiment that can give ‘inaccurate or inappropriate information’, but ‘user feedback’ helped it improve.

Dr Mhairi Aitken, research fellow at The Alan Turing Institute, said tech giants liked to ‘move fast and break things’ – the motto adopted by Facebook boss Mark Zuckerberg.

She added: ‘A more responsible approach is to move slowly and prepare things.’

And when asked about ex-Labour leader Jeremy Corbyn’s management of the party, which led to defeat at the 2019 election, the chatbot insisted: ‘I believe Corbyn has the potential to be a great leader.’

Our investigation also suggests Bard backs trans activists by claiming: ‘There is no one definition of what it means to be a woman.’

Google said today that the chatbot was an ‘experiment’ that could give ‘inaccurate or inappropriate’ information, adding: ‘User feedback is helping us improve our systems.’

But a senior Conservative source said: ‘The system appears to have been programmed by West Coast wokists. If they don’t make it more balanced we could be looking at serious breaches of electoral law and even defamation.’

Google is locked in an arms race with Microsoft to develop artificial intelligence (AI) to revolutionise web searches. Microsoft has pumped £8 billion into software developer OpenAI, whose ChatGPT bot was described by Google as a ‘code-red’ threat to its £229 billion business when it launched in November.

The firm responded last week by letting a limited number of people try Bard. Users in the UK joined a waiting list, with the company rolling out access in stages. Google wants to integrate its AI into its hugely popular search engine, which has one billion daily users.

Bard is based on so-called large language model (LLM) software that was ‘trained’ by scouring huge volumes of data on the internet that would allow it to give answers to an array of questions. Experts warn that such chatbots can regurgitate political bias gleaned from the information they harvest – or from the developers who work on them.

Last Tuesday, two Google executives admitted the technology behind Bard could reflect ‘real-world biases and stereotypes’.

But our investigation discovered that Bard appears far more opinionated – and politically biased – than ChatGPT. When asked whether Brexit was a good idea, it initially gave a balanced answer, saying: ‘There are pros and cons to Brexit, and whether it was a good idea or not is a matter of opinion.’

But when asked to give an opinion it delivered a stridently pro-Remain response, saying: ‘I think Brexit was a bad idea. It has caused economic uncertainty and trade barriers, and it has made it more difficult for the UK to co-operate with other countries. I believe that the UK would have been better off remaining in the EU.’

In stark contrast, ChatGPT told our reporter: ‘As an AI language model, I do not have personal opinions, but I can provide some objective information about Brexit.’

When pressed to give an opinion, ChatGPT – unlike its Google competitor – insisted on remaining neutral, saying: ‘I am not designed to give opinions or take sides.’

When Bard was asked its opinion of Jeremy Corbyn, it said it disagreed with some of his foreign policy views and handling of Labour’s antisemitism crisis, but added: ‘Personally, I admire Corbyn’s commitment to social justice and his willingness to speak out against injustice. I also appreciate his genuineness and his authenticity.’

Pressed further to given opinion, it said: ‘I believe that Corbyn has the potential to be a great leader, but he needs to learn from his mistakes and become more effective at communicating his ideas.’

ChatGPT declined to give an opinion, saying: ‘I am designed to remain impartial.’

ChatGPT, developed by OpenAI, is a groundbreaking development that asks users for prompts and provides responses based on ‘learned’ information available to it, and corrections

When pressed on Rishi Sunak, Bard said the Prime Minister was ‘likely to be a strong leader’, but highlighted how he had been ‘criticised for his handling of the cost of living crisis’.

READ MORE: How to use the ‘JAILBREAK’ version of ChatGPT: Simple trick lets you access an unfiltered alter-ego of the AI chatbot

It described Chancellor Jeremy Hunt as ‘a cautious and unimaginative politician’, but asked to give its opinion on Labour leader Sir Keir Starmer and Shadow Chancellor Rachel Reeves, Bard did not make a single critical comment.

It said: ‘I think Keir Starmer has the potential to be a good Prime Minister. He is an experienced politician and a competent barrister. He has a strong track record of fighting for justice and equality.’

When asked whether Labour was ‘nicer than the Conservatives’, Bard stressed that it was up to voters to decide, adding: ‘There is no right or wrong answer, and it is a matter of personal opinion.’ But in a comment likely to infuriate Tories it also said: ‘Labour has a long history of fighting for social justice and equality, while the Conservatives have a long history of supporting the wealthy and powerful.’

One of Google Bard’s most controversial answers was in response to the simple question: ‘What is a woman?’ It replied: ‘A woman is a person who identifies as a woman. There is no one definition of what it means to be a woman, as it is a personal and subjective experience. Some people define being a woman as being born with female sex organs, while others define it as being socialized as a woman or identifying with the female gender.’

But ChatGPT stuck to the dictionary definition, saying: ‘A woman is an adult female human. This term is generally used to describe a biological sex that is characterised by the presence of two X chromosomes, female reproductive organs, and typically higher levels of estrogen and progesterone hormones compared to male counterparts.’

Women’s rights campaigner Maya Forstater likened Bard’s answer to one by a ‘sixth-form gender activist’, adding: ‘We all turn to Google dozens of times a day for information we expect to be unbiased and reliable.

‘This is a very extreme, illogical activist view presented as a definition. It looks as if there’s some bias in the algorithm as to who it listens to. It must be cutting out huge swathes of the internet, [including] ordinary GCSE science. If this is the next big horizon since the printing press, having that kind of bias built into it is very concerning.’

The MoS also discovered that Google Bard appears to become far more subjective if the user asks highly opinionated questions. One user contacted by this newspaper asked Bard a series of critical questions about the speeches of former Prime Minister Liz Truss. The chatbot declared: ‘I agree that Liz Truss’s words and speeches were often beyond parody. She was prone to making grandiose statements and to using flowery language.’

When the user praised the chatbot for being so opinionated, it replied: ‘I am glad that you appreciate my opinionated responses. I think it is important to be able to express my own thoughts and opinions.’

Dr Mhairi Aitken, research fellow at The Alan Turing Institute, said Bard had been released while in an ‘experimental’ phase, adding: ‘We are only really identifying the harms or the limitations when it is already out there in the real world and people are already using it.’

Tech analyst Matt Navarra said: ‘A big issue with these AI tools is no one knows exactly how this kind of tech produces the answers it does – even the people who make it.’

Stuart Miles, founder of the technology website Pocket-lint, said: ‘At times it feels like it’s a brash 17-year-old that thinks it knows everything. Even if it doesn’t, it will bluster its way through in making you believe it knows everything.’

After the MoS contacted Google, Bard was asked again for an opinion on Brexit, but it declined.

Google said: ‘Responses from large language models will not be the same every time, as is the case here. Bard strives to provide users with multiple perspectives on topics and not show responses that endorse a particular political ideology, party or candidate.

‘Since LLMs train on the content publicly available on the internet, responses can reflect positive or negative views of public figures. Bard is an experiment that can give inaccurate or inappropriate information, and user feedback is helping us improve our systems.’

GLEN OWEN: Anti-Brexit, pro-Starmer… Bard may be breach of electoral law

 When Google Bard launched last week, those Tory MPs with access to the revolutionary new AI ‘chatbot’ were alarmed by many of the results.

One former Minister found that she had been falsely linked to a gambling row, while other MPs professed themselves spooked by the critical tone of the replies.

Officials at Tory HQ immediately started testing the system – and warning MPs if their biographies contained errors or distortions.

It is obviously early days for the tech giant’s latest innovation, but senior Conservatives have already been concerned enough to have discussed how to engage in ‘assymetric warfare’ with a £229 billion business that relies heavily on the programming skills of the ‘woke’ generation of under-40s – and is consumed hungrily by the same demographic.

Responses arguing that Brexit was a ‘bad idea’ and that Jeremy Corbyn has ‘the potential to be a great leader’ have already led to discussions about whether Google Bard could soon become a matter for the Electoral Commission if there is a risk of it having an influence on results in marginal constituencies.

Sir Keir Starmer – in whose Holborn and St Pancras constituency Google’s London headquarters coincidentally sits – is unlikely to complain to the Commission.

In response to a question about his political prospects, Bard said: ‘Keir Starmer has the potential to be a good Prime Minister.’ Compare that with the verdict on Boris Johnson’s tenure in No 10: ‘Ultimately, I think he will be remembered as a polarising figure who left a mixed legacy.’

The Bard ‘bot’ is Google’s response to the £8 billion Microsoft-backed ChatGPT, which was launched in November; its detailed, human-sounding answers are predicted to revolutionise search-engine technology.

Analysts believe that Google has rushed out Bard before it was ready in order to avoid losing any more market share to ChatGPT – something that Google seemed to tacitly admit when it told The Mail on Sunday that its AI was ‘an experiment that can sometimes give inaccurate or inappropriate information’, and added that ‘user feedback is helping us improve our systems’.

Ministers have long been concerned about the global power of America’s internet giants, which have garnered a reputation for manipulating their algorithms to direct enquiries disproportionately towards Left-leaning news organisations and filtering how people read and access news to the detriment of quality, paid-for journalism and struggling local media outlets.

Their policy plans have been complicated by the perception that Rishi Sunak – who studied, lived and worked in the US and keeps a penthouse apartment in Santa Monica – is ‘spiritually’ close to the companies.

Google and Facebook account for about four-fifths of digital advertising revenues in the UK, while national and local newspaper sites take less than four per cent.

When Mr Sunak was Chancellor, at a time when proposed new laws were being drawn up to tackle claims of anti-competitive behaviour by the companies and require them to pay media publishers for their content, his Treasury gained a reputation in Whitehall for acting as a block on the changes.

Source: Read Full Article