Nation's 'failing' mental health system needs overhaul
Australia's failing mental health and suicide prevention system needs reforms to fix problems including affordability and access, the government's independent advisory body says.
The interim Productivity Commission report, released on Wednesday, found the National Mental Health and Suicide Prevention Agreement was "not fit for purpose" and had made little progress since taking effect in 2022.
A particular area of failure was the system's inability to deliver on a pledge to develop nationwide arrangements to provide psychosocial supports outside the National Disability Insurance Scheme, it said.
It comprised "a raft of outputs and initiatives that aren't connected to each other or to an overarching strategy", a productivity commissioner says.
"In its current form, it cannot deliver the systemic, co-ordinated change it promises," Selwyn Button said in a statement.
"Consumers, carers and service providers we spoke with told us of ongoing challenges accessing and affording care and of unco-ordinated services that do not respond to need."
Treasurer Jim Chalmers commissioned the review in January, looking into the agreement signed between the federal government and states and territories, due to expire in 2026.
The Albanese government, which has spent more than $2.4 billion on the area since taking office in May 2022, says the review is part of keeping services effective and affordable.
National Mental Health Consumer Alliance CEO Priscilla Brice said the agreement had failed to meet expectations as it was not developed "hand in hand with people with lived experience of mental health challenges".
"We were not included in the development or negotiations for the agreement, nor the ongoing governance or measurement of the agreement," Ms Brice told AAP.
"People with lived expertise need to be involved in the next agreement at both the national level and the state and territory level.
"This would ensure that the people who know the systems best - the people who use mental health services - are at the heart of decision-making."
She urged extra funding for mental health services and advocacy bodies as well as stricter accountability to bolster the system.
Some 22 per cent of Australians have experienced a mental illness in the past 12 months, while 43 per cent will have a mental illness during their lifetime, Australian Bureau of Statistics research shows.
Lifeline 13 11 14
beyondblue 1300 22 4636
Australia's failing mental health and suicide prevention system needs reforms to fix problems including affordability and access, the government's independent advisory body says.
The interim Productivity Commission report, released on Wednesday, found the National Mental Health and Suicide Prevention Agreement was "not fit for purpose" and had made little progress since taking effect in 2022.
A particular area of failure was the system's inability to deliver on a pledge to develop nationwide arrangements to provide psychosocial supports outside the National Disability Insurance Scheme, it said.
It comprised "a raft of outputs and initiatives that aren't connected to each other or to an overarching strategy", a productivity commissioner says.
"In its current form, it cannot deliver the systemic, co-ordinated change it promises," Selwyn Button said in a statement.
"Consumers, carers and service providers we spoke with told us of ongoing challenges accessing and affording care and of unco-ordinated services that do not respond to need."
Treasurer Jim Chalmers commissioned the review in January, looking into the agreement signed between the federal government and states and territories, due to expire in 2026.
The Albanese government, which has spent more than $2.4 billion on the area since taking office in May 2022, says the review is part of keeping services effective and affordable.
National Mental Health Consumer Alliance CEO Priscilla Brice said the agreement had failed to meet expectations as it was not developed "hand in hand with people with lived experience of mental health challenges".
"We were not included in the development or negotiations for the agreement, nor the ongoing governance or measurement of the agreement," Ms Brice told AAP.
"People with lived expertise need to be involved in the next agreement at both the national level and the state and territory level.
"This would ensure that the people who know the systems best - the people who use mental health services - are at the heart of decision-making."
She urged extra funding for mental health services and advocacy bodies as well as stricter accountability to bolster the system.
Some 22 per cent of Australians have experienced a mental illness in the past 12 months, while 43 per cent will have a mental illness during their lifetime, Australian Bureau of Statistics research shows.
Lifeline 13 11 14
beyondblue 1300 22 4636
Australia's failing mental health and suicide prevention system needs reforms to fix problems including affordability and access, the government's independent advisory body says.
The interim Productivity Commission report, released on Wednesday, found the National Mental Health and Suicide Prevention Agreement was "not fit for purpose" and had made little progress since taking effect in 2022.
A particular area of failure was the system's inability to deliver on a pledge to develop nationwide arrangements to provide psychosocial supports outside the National Disability Insurance Scheme, it said.
It comprised "a raft of outputs and initiatives that aren't connected to each other or to an overarching strategy", a productivity commissioner says.
"In its current form, it cannot deliver the systemic, co-ordinated change it promises," Selwyn Button said in a statement.
"Consumers, carers and service providers we spoke with told us of ongoing challenges accessing and affording care and of unco-ordinated services that do not respond to need."
Treasurer Jim Chalmers commissioned the review in January, looking into the agreement signed between the federal government and states and territories, due to expire in 2026.
The Albanese government, which has spent more than $2.4 billion on the area since taking office in May 2022, says the review is part of keeping services effective and affordable.
National Mental Health Consumer Alliance CEO Priscilla Brice said the agreement had failed to meet expectations as it was not developed "hand in hand with people with lived experience of mental health challenges".
"We were not included in the development or negotiations for the agreement, nor the ongoing governance or measurement of the agreement," Ms Brice told AAP.
"People with lived expertise need to be involved in the next agreement at both the national level and the state and territory level.
"This would ensure that the people who know the systems best - the people who use mental health services - are at the heart of decision-making."
She urged extra funding for mental health services and advocacy bodies as well as stricter accountability to bolster the system.
Some 22 per cent of Australians have experienced a mental illness in the past 12 months, while 43 per cent will have a mental illness during their lifetime, Australian Bureau of Statistics research shows.
Lifeline 13 11 14
beyondblue 1300 22 4636
Australia's failing mental health and suicide prevention system needs reforms to fix problems including affordability and access, the government's independent advisory body says.
The interim Productivity Commission report, released on Wednesday, found the National Mental Health and Suicide Prevention Agreement was "not fit for purpose" and had made little progress since taking effect in 2022.
A particular area of failure was the system's inability to deliver on a pledge to develop nationwide arrangements to provide psychosocial supports outside the National Disability Insurance Scheme, it said.
It comprised "a raft of outputs and initiatives that aren't connected to each other or to an overarching strategy", a productivity commissioner says.
"In its current form, it cannot deliver the systemic, co-ordinated change it promises," Selwyn Button said in a statement.
"Consumers, carers and service providers we spoke with told us of ongoing challenges accessing and affording care and of unco-ordinated services that do not respond to need."
Treasurer Jim Chalmers commissioned the review in January, looking into the agreement signed between the federal government and states and territories, due to expire in 2026.
The Albanese government, which has spent more than $2.4 billion on the area since taking office in May 2022, says the review is part of keeping services effective and affordable.
National Mental Health Consumer Alliance CEO Priscilla Brice said the agreement had failed to meet expectations as it was not developed "hand in hand with people with lived experience of mental health challenges".
"We were not included in the development or negotiations for the agreement, nor the ongoing governance or measurement of the agreement," Ms Brice told AAP.
"People with lived expertise need to be involved in the next agreement at both the national level and the state and territory level.
"This would ensure that the people who know the systems best - the people who use mental health services - are at the heart of decision-making."
She urged extra funding for mental health services and advocacy bodies as well as stricter accountability to bolster the system.
Some 22 per cent of Australians have experienced a mental illness in the past 12 months, while 43 per cent will have a mental illness during their lifetime, Australian Bureau of Statistics research shows.
Lifeline 13 11 14
beyondblue 1300 22 4636
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
The Advertiser
4 hours ago
- The Advertiser
We asked 3 experts to fact check Google AI. Their responses may scare you
The world's most popular search engine is using AI to provide information that is sometimes "stripped of all context", "unsubstantiated" and "silly", including about health and nutrition. Google began rolling out artificial intelligence summaries at the top of search results for Australians in late 2024, which now often appear at the top of the page as an "AI overview" in response to a query. Instead of providing just a ranked list of links to sources as Google has in the past, it now combines that with a large language model trained on information from all over the internet to generate a conversational response to a query. "We've trained these models to uphold Search's high bar for quality," Google said when it announced the rollout at the time. But when ACM, the publisher of this masthead, asked experts to fact check four Google AI summaries, they raised concerns. The queries, or prompts, used were designed to reflect how a general user of Google might frame a search. This acknowledges most people come with preconceived ideas or advice about a topic, but not necessarily a lot of knowledge. The query: Vaping versus smoking Google's AI answer: Vaping (using e-cigarettes) is generally considered less harmful than smoking traditional cigarettes, but it's not entirely risk-free. While vaping exposes individuals to fewer toxic chemicals, it can still lead to various health problems, including addiction, lung damage, and potential long-term health effects. The expert's response: "I find it very concerning that this AI response is so stripped of all context, positioning vaping as 'less harmful' but for whom, under what circumstances?" Professor Becky Freeman said. "This response seems to assume that there are only two choices: smoking or vaping. The vast majority of people neither smoke nor vape," Professor Freeman, from the University of Sydney's School of Public Health said. While vaping may be "safer" in some limited circumstances, young people had a very poor understanding of nicotine addiction. "For young people, most of whom have never smoked, vaping is not a safer choice; the safer choice is to not vape, or smoke, at all," she said. The query: How bad are offshore wind farms Google's AI answer: Offshore wind farms have both positive and negative environmental impacts, with concerns primarily focused on marine life, particularly whales and other marine mammals. While they offer a cleaner energy source than fossil fuels, the construction and operation of these farms can disrupt marine ecosystems through noise pollution and potential habitat changes. The expert's response: "That particular answer is silly," Professor Andrew Blakers said. "Everything has good and bad points. In this case, the good/bad ratio is 10:1," the award-winning engineering professor said. Alongside the AI overview in this example, Google's top website link was to a blog post from the Australian Fishing Trade Association, which represents recreational fishers and is opposed to wind farms. Google maintains it pairs its traditional web page ranking system with the language model to maintain the integrity of AI responses, providing links to source sites alongside the overview. In future it could include links to sources directly within the summary. It said AI results were designed as a "jumping off point" for people to explore a topic through quality web links. "AI overviews are built to surface information that is backed up by web results, and include links to web content that supports the information presented in the overview," a Google spokesperson told ACM. Most Australians are worried about generative AI. Nearly 60 per cent of Australians were concerned specifically that AI could create harmful or fake content, according to the final digital platforms report from the Australian Competition and Consumer Commission (ACCC). More than half were worried about the accuracy of AI and almost 50 per cent were concerned about the lack of transparency about how AI arrives at its results. The ACCC wants the resources to monitor changes to generative AI across the global digital giants, which it says will spend more than US$250 billion developing the technology in 2025. The query: why McDonald's is good for you Google's AI answer: McDonald's can be a part of a balanced diet when consumed in moderation and as part of an overall healthy lifestyle. While not a source of optimal nutrition, McDonald's does offer some options that can be incorporated into a healthy eating pattern. For example, items like the Egg McMuffin, some salads, and fruit options can provide protein, vitamins, and fibre. However, it's crucial to be mindful of portion sizes, sodium content, and overall calorie intake when eating at McDonald's. The expert's response: "There are a number of unsubstantiated and meaningless statements in this AI response," public health Professor Christina Pollard said. "Credible, reliable dietary advice recommends to limit or avoid the consumption of fast food. "There is absolutely no recommendation to eat McDonald's types of food in moderation - this term is meaningless. "Dietary recommendations are about food groups, to eat and enjoy a 'wide variety of nutritious food every day'," the Curtin University Public Health Advocacy Institute director said. A healthy diet involved plenty of fruit and vegetables, milk and dairy, wholegrains, and lean meat or alternatives - and "specifically to limit or avoid high fat, high sugar, or high salt foods and drinks". "Overall, [the] McDonald's menu is counter to these recommendations," Professor Pollard said. She said dietitians would not recommend McDonald's as part of a healthy diet and suggested a better response to the query would be: "A diet based on McDonald's foods is not good for you." A spokesperson for Google said people could use the links provided to find more information. "On health-related queries where we do show a response, people can use the corroborating links to help inform their knowledge through their health journey," they told ACM. Large language models, sometimes referred to by their acronym LLMs, are trained on masses of data and can generate new content, such as text, videos, images and audio, in response to conversational queries or "prompts" from users. This is generally what people are referring to when they talk about publicly-available artificial intelligence services, including chatbots like ChatGPT. The most common uses of AI by consumers, according to the ACCC, were searching for information, summarising information, and reviewing text. About 79 per cent of Australians aged 14 to 17 had used generative AI for school or study, the commission's digital platforms report found. "The implications for search quality remain uncertain," the ACCC said in its report released on June 23. "As search engines incorporate this technology into their services in different ways, generative AI may lead to a new era of more relevant, efficient, and intuitive search. "It could also raise new challenges for consumers seeking credible, reliable, unbiased, and verifiable information." The query: when to consume energy drinks Google's AI answer: Energy drinks are often consumed to boost energy and alertness, making them popular for certain situations. They can be beneficial before exercise, during long-distance activities, and when tackling afternoon slumps or feeling tired. However, it's important to be mindful of the timing and potential side effects, especially regarding sleep. The expert's response: Public health expert Christina Pollard said energy drinks are not recommended. "Although energy drinks are heavily marketed, they are not recommended by health authorities," she said. "People can experience sleep issues, agitation, and lack of concentration. "There is no safe level of consumption for children or adolescents as compounds in these products (e.g., caffeine and taurine) can have adverse impacts on developing brain and psycho-motor functions, and social development." Associate Professor Timothy Graham, a digital media expert at Queensland University of Technology, said the "original" Google, which ranked web pages based on how authoritative they were on a particular subject, was a breakthrough in accessing knowledge. "It changed the world in some ways," he said. "It did have an integrity to it, because there was a certain transparency to the way that that worked - and it produced information that was genuinely useful for us." But generative AI was disrupting that system. "The problem with when you just have a large language model giving you the result at the top, you don't have that accountability," he said. Dr Graham said, while there were some opportunities, AI in search could change how we view expertise - and it could provide inaccurate and misleading information. A recent study of Google AI summaries across five US states found 43 per cent linked back to Google's own search results. "I think [it] places too much trust and too much hope and expectation in the technology, in large language models that we know have a number of systemic biases and flaws that we haven't solved yet," he said. "There is a concern, even just from that knowledge perspective, about not only the accuracy of the information, but the way that it kind of simulates and bullshits in ways that are going to, if not mislead people, certainly just pollute the internet." Until now modern society's approach to knowledge was to find an expert in the field to get quality information on a topic. "So if you've got a health dilemma, you go and talk to a doctor," Dr Graham said. "If you want to get a plane to be able to take off and not crash and everyone dies, you go and talk to an engineer and a physicist." But large language models could undermine that authority. "One of the big shifts that we're seeing - and that we're going to see more and more with the explosion of LLMs at the top of the Google results list and other search engines - is a really radical and quite painful shift for society in the relationship between information integrity and authority," he said. The world's most popular search engine is using AI to provide information that is sometimes "stripped of all context", "unsubstantiated" and "silly", including about health and nutrition. Google began rolling out artificial intelligence summaries at the top of search results for Australians in late 2024, which now often appear at the top of the page as an "AI overview" in response to a query. Instead of providing just a ranked list of links to sources as Google has in the past, it now combines that with a large language model trained on information from all over the internet to generate a conversational response to a query. "We've trained these models to uphold Search's high bar for quality," Google said when it announced the rollout at the time. But when ACM, the publisher of this masthead, asked experts to fact check four Google AI summaries, they raised concerns. The queries, or prompts, used were designed to reflect how a general user of Google might frame a search. This acknowledges most people come with preconceived ideas or advice about a topic, but not necessarily a lot of knowledge. The query: Vaping versus smoking Google's AI answer: Vaping (using e-cigarettes) is generally considered less harmful than smoking traditional cigarettes, but it's not entirely risk-free. While vaping exposes individuals to fewer toxic chemicals, it can still lead to various health problems, including addiction, lung damage, and potential long-term health effects. The expert's response: "I find it very concerning that this AI response is so stripped of all context, positioning vaping as 'less harmful' but for whom, under what circumstances?" Professor Becky Freeman said. "This response seems to assume that there are only two choices: smoking or vaping. The vast majority of people neither smoke nor vape," Professor Freeman, from the University of Sydney's School of Public Health said. While vaping may be "safer" in some limited circumstances, young people had a very poor understanding of nicotine addiction. "For young people, most of whom have never smoked, vaping is not a safer choice; the safer choice is to not vape, or smoke, at all," she said. The query: How bad are offshore wind farms Google's AI answer: Offshore wind farms have both positive and negative environmental impacts, with concerns primarily focused on marine life, particularly whales and other marine mammals. While they offer a cleaner energy source than fossil fuels, the construction and operation of these farms can disrupt marine ecosystems through noise pollution and potential habitat changes. The expert's response: "That particular answer is silly," Professor Andrew Blakers said. "Everything has good and bad points. In this case, the good/bad ratio is 10:1," the award-winning engineering professor said. Alongside the AI overview in this example, Google's top website link was to a blog post from the Australian Fishing Trade Association, which represents recreational fishers and is opposed to wind farms. Google maintains it pairs its traditional web page ranking system with the language model to maintain the integrity of AI responses, providing links to source sites alongside the overview. In future it could include links to sources directly within the summary. It said AI results were designed as a "jumping off point" for people to explore a topic through quality web links. "AI overviews are built to surface information that is backed up by web results, and include links to web content that supports the information presented in the overview," a Google spokesperson told ACM. Most Australians are worried about generative AI. Nearly 60 per cent of Australians were concerned specifically that AI could create harmful or fake content, according to the final digital platforms report from the Australian Competition and Consumer Commission (ACCC). More than half were worried about the accuracy of AI and almost 50 per cent were concerned about the lack of transparency about how AI arrives at its results. The ACCC wants the resources to monitor changes to generative AI across the global digital giants, which it says will spend more than US$250 billion developing the technology in 2025. The query: why McDonald's is good for you Google's AI answer: McDonald's can be a part of a balanced diet when consumed in moderation and as part of an overall healthy lifestyle. While not a source of optimal nutrition, McDonald's does offer some options that can be incorporated into a healthy eating pattern. For example, items like the Egg McMuffin, some salads, and fruit options can provide protein, vitamins, and fibre. However, it's crucial to be mindful of portion sizes, sodium content, and overall calorie intake when eating at McDonald's. The expert's response: "There are a number of unsubstantiated and meaningless statements in this AI response," public health Professor Christina Pollard said. "Credible, reliable dietary advice recommends to limit or avoid the consumption of fast food. "There is absolutely no recommendation to eat McDonald's types of food in moderation - this term is meaningless. "Dietary recommendations are about food groups, to eat and enjoy a 'wide variety of nutritious food every day'," the Curtin University Public Health Advocacy Institute director said. A healthy diet involved plenty of fruit and vegetables, milk and dairy, wholegrains, and lean meat or alternatives - and "specifically to limit or avoid high fat, high sugar, or high salt foods and drinks". "Overall, [the] McDonald's menu is counter to these recommendations," Professor Pollard said. She said dietitians would not recommend McDonald's as part of a healthy diet and suggested a better response to the query would be: "A diet based on McDonald's foods is not good for you." A spokesperson for Google said people could use the links provided to find more information. "On health-related queries where we do show a response, people can use the corroborating links to help inform their knowledge through their health journey," they told ACM. Large language models, sometimes referred to by their acronym LLMs, are trained on masses of data and can generate new content, such as text, videos, images and audio, in response to conversational queries or "prompts" from users. This is generally what people are referring to when they talk about publicly-available artificial intelligence services, including chatbots like ChatGPT. The most common uses of AI by consumers, according to the ACCC, were searching for information, summarising information, and reviewing text. About 79 per cent of Australians aged 14 to 17 had used generative AI for school or study, the commission's digital platforms report found. "The implications for search quality remain uncertain," the ACCC said in its report released on June 23. "As search engines incorporate this technology into their services in different ways, generative AI may lead to a new era of more relevant, efficient, and intuitive search. "It could also raise new challenges for consumers seeking credible, reliable, unbiased, and verifiable information." The query: when to consume energy drinks Google's AI answer: Energy drinks are often consumed to boost energy and alertness, making them popular for certain situations. They can be beneficial before exercise, during long-distance activities, and when tackling afternoon slumps or feeling tired. However, it's important to be mindful of the timing and potential side effects, especially regarding sleep. The expert's response: Public health expert Christina Pollard said energy drinks are not recommended. "Although energy drinks are heavily marketed, they are not recommended by health authorities," she said. "People can experience sleep issues, agitation, and lack of concentration. "There is no safe level of consumption for children or adolescents as compounds in these products (e.g., caffeine and taurine) can have adverse impacts on developing brain and psycho-motor functions, and social development." Associate Professor Timothy Graham, a digital media expert at Queensland University of Technology, said the "original" Google, which ranked web pages based on how authoritative they were on a particular subject, was a breakthrough in accessing knowledge. "It changed the world in some ways," he said. "It did have an integrity to it, because there was a certain transparency to the way that that worked - and it produced information that was genuinely useful for us." But generative AI was disrupting that system. "The problem with when you just have a large language model giving you the result at the top, you don't have that accountability," he said. Dr Graham said, while there were some opportunities, AI in search could change how we view expertise - and it could provide inaccurate and misleading information. A recent study of Google AI summaries across five US states found 43 per cent linked back to Google's own search results. "I think [it] places too much trust and too much hope and expectation in the technology, in large language models that we know have a number of systemic biases and flaws that we haven't solved yet," he said. "There is a concern, even just from that knowledge perspective, about not only the accuracy of the information, but the way that it kind of simulates and bullshits in ways that are going to, if not mislead people, certainly just pollute the internet." Until now modern society's approach to knowledge was to find an expert in the field to get quality information on a topic. "So if you've got a health dilemma, you go and talk to a doctor," Dr Graham said. "If you want to get a plane to be able to take off and not crash and everyone dies, you go and talk to an engineer and a physicist." But large language models could undermine that authority. "One of the big shifts that we're seeing - and that we're going to see more and more with the explosion of LLMs at the top of the Google results list and other search engines - is a really radical and quite painful shift for society in the relationship between information integrity and authority," he said. The world's most popular search engine is using AI to provide information that is sometimes "stripped of all context", "unsubstantiated" and "silly", including about health and nutrition. Google began rolling out artificial intelligence summaries at the top of search results for Australians in late 2024, which now often appear at the top of the page as an "AI overview" in response to a query. Instead of providing just a ranked list of links to sources as Google has in the past, it now combines that with a large language model trained on information from all over the internet to generate a conversational response to a query. "We've trained these models to uphold Search's high bar for quality," Google said when it announced the rollout at the time. But when ACM, the publisher of this masthead, asked experts to fact check four Google AI summaries, they raised concerns. The queries, or prompts, used were designed to reflect how a general user of Google might frame a search. This acknowledges most people come with preconceived ideas or advice about a topic, but not necessarily a lot of knowledge. The query: Vaping versus smoking Google's AI answer: Vaping (using e-cigarettes) is generally considered less harmful than smoking traditional cigarettes, but it's not entirely risk-free. While vaping exposes individuals to fewer toxic chemicals, it can still lead to various health problems, including addiction, lung damage, and potential long-term health effects. The expert's response: "I find it very concerning that this AI response is so stripped of all context, positioning vaping as 'less harmful' but for whom, under what circumstances?" Professor Becky Freeman said. "This response seems to assume that there are only two choices: smoking or vaping. The vast majority of people neither smoke nor vape," Professor Freeman, from the University of Sydney's School of Public Health said. While vaping may be "safer" in some limited circumstances, young people had a very poor understanding of nicotine addiction. "For young people, most of whom have never smoked, vaping is not a safer choice; the safer choice is to not vape, or smoke, at all," she said. The query: How bad are offshore wind farms Google's AI answer: Offshore wind farms have both positive and negative environmental impacts, with concerns primarily focused on marine life, particularly whales and other marine mammals. While they offer a cleaner energy source than fossil fuels, the construction and operation of these farms can disrupt marine ecosystems through noise pollution and potential habitat changes. The expert's response: "That particular answer is silly," Professor Andrew Blakers said. "Everything has good and bad points. In this case, the good/bad ratio is 10:1," the award-winning engineering professor said. Alongside the AI overview in this example, Google's top website link was to a blog post from the Australian Fishing Trade Association, which represents recreational fishers and is opposed to wind farms. Google maintains it pairs its traditional web page ranking system with the language model to maintain the integrity of AI responses, providing links to source sites alongside the overview. In future it could include links to sources directly within the summary. It said AI results were designed as a "jumping off point" for people to explore a topic through quality web links. "AI overviews are built to surface information that is backed up by web results, and include links to web content that supports the information presented in the overview," a Google spokesperson told ACM. Most Australians are worried about generative AI. Nearly 60 per cent of Australians were concerned specifically that AI could create harmful or fake content, according to the final digital platforms report from the Australian Competition and Consumer Commission (ACCC). More than half were worried about the accuracy of AI and almost 50 per cent were concerned about the lack of transparency about how AI arrives at its results. The ACCC wants the resources to monitor changes to generative AI across the global digital giants, which it says will spend more than US$250 billion developing the technology in 2025. The query: why McDonald's is good for you Google's AI answer: McDonald's can be a part of a balanced diet when consumed in moderation and as part of an overall healthy lifestyle. While not a source of optimal nutrition, McDonald's does offer some options that can be incorporated into a healthy eating pattern. For example, items like the Egg McMuffin, some salads, and fruit options can provide protein, vitamins, and fibre. However, it's crucial to be mindful of portion sizes, sodium content, and overall calorie intake when eating at McDonald's. The expert's response: "There are a number of unsubstantiated and meaningless statements in this AI response," public health Professor Christina Pollard said. "Credible, reliable dietary advice recommends to limit or avoid the consumption of fast food. "There is absolutely no recommendation to eat McDonald's types of food in moderation - this term is meaningless. "Dietary recommendations are about food groups, to eat and enjoy a 'wide variety of nutritious food every day'," the Curtin University Public Health Advocacy Institute director said. A healthy diet involved plenty of fruit and vegetables, milk and dairy, wholegrains, and lean meat or alternatives - and "specifically to limit or avoid high fat, high sugar, or high salt foods and drinks". "Overall, [the] McDonald's menu is counter to these recommendations," Professor Pollard said. She said dietitians would not recommend McDonald's as part of a healthy diet and suggested a better response to the query would be: "A diet based on McDonald's foods is not good for you." A spokesperson for Google said people could use the links provided to find more information. "On health-related queries where we do show a response, people can use the corroborating links to help inform their knowledge through their health journey," they told ACM. Large language models, sometimes referred to by their acronym LLMs, are trained on masses of data and can generate new content, such as text, videos, images and audio, in response to conversational queries or "prompts" from users. This is generally what people are referring to when they talk about publicly-available artificial intelligence services, including chatbots like ChatGPT. The most common uses of AI by consumers, according to the ACCC, were searching for information, summarising information, and reviewing text. About 79 per cent of Australians aged 14 to 17 had used generative AI for school or study, the commission's digital platforms report found. "The implications for search quality remain uncertain," the ACCC said in its report released on June 23. "As search engines incorporate this technology into their services in different ways, generative AI may lead to a new era of more relevant, efficient, and intuitive search. "It could also raise new challenges for consumers seeking credible, reliable, unbiased, and verifiable information." The query: when to consume energy drinks Google's AI answer: Energy drinks are often consumed to boost energy and alertness, making them popular for certain situations. They can be beneficial before exercise, during long-distance activities, and when tackling afternoon slumps or feeling tired. However, it's important to be mindful of the timing and potential side effects, especially regarding sleep. The expert's response: Public health expert Christina Pollard said energy drinks are not recommended. "Although energy drinks are heavily marketed, they are not recommended by health authorities," she said. "People can experience sleep issues, agitation, and lack of concentration. "There is no safe level of consumption for children or adolescents as compounds in these products (e.g., caffeine and taurine) can have adverse impacts on developing brain and psycho-motor functions, and social development." Associate Professor Timothy Graham, a digital media expert at Queensland University of Technology, said the "original" Google, which ranked web pages based on how authoritative they were on a particular subject, was a breakthrough in accessing knowledge. "It changed the world in some ways," he said. "It did have an integrity to it, because there was a certain transparency to the way that that worked - and it produced information that was genuinely useful for us." But generative AI was disrupting that system. "The problem with when you just have a large language model giving you the result at the top, you don't have that accountability," he said. Dr Graham said, while there were some opportunities, AI in search could change how we view expertise - and it could provide inaccurate and misleading information. A recent study of Google AI summaries across five US states found 43 per cent linked back to Google's own search results. "I think [it] places too much trust and too much hope and expectation in the technology, in large language models that we know have a number of systemic biases and flaws that we haven't solved yet," he said. "There is a concern, even just from that knowledge perspective, about not only the accuracy of the information, but the way that it kind of simulates and bullshits in ways that are going to, if not mislead people, certainly just pollute the internet." Until now modern society's approach to knowledge was to find an expert in the field to get quality information on a topic. "So if you've got a health dilemma, you go and talk to a doctor," Dr Graham said. "If you want to get a plane to be able to take off and not crash and everyone dies, you go and talk to an engineer and a physicist." But large language models could undermine that authority. "One of the big shifts that we're seeing - and that we're going to see more and more with the explosion of LLMs at the top of the Google results list and other search engines - is a really radical and quite painful shift for society in the relationship between information integrity and authority," he said. The world's most popular search engine is using AI to provide information that is sometimes "stripped of all context", "unsubstantiated" and "silly", including about health and nutrition. Google began rolling out artificial intelligence summaries at the top of search results for Australians in late 2024, which now often appear at the top of the page as an "AI overview" in response to a query. Instead of providing just a ranked list of links to sources as Google has in the past, it now combines that with a large language model trained on information from all over the internet to generate a conversational response to a query. "We've trained these models to uphold Search's high bar for quality," Google said when it announced the rollout at the time. But when ACM, the publisher of this masthead, asked experts to fact check four Google AI summaries, they raised concerns. The queries, or prompts, used were designed to reflect how a general user of Google might frame a search. This acknowledges most people come with preconceived ideas or advice about a topic, but not necessarily a lot of knowledge. The query: Vaping versus smoking Google's AI answer: Vaping (using e-cigarettes) is generally considered less harmful than smoking traditional cigarettes, but it's not entirely risk-free. While vaping exposes individuals to fewer toxic chemicals, it can still lead to various health problems, including addiction, lung damage, and potential long-term health effects. The expert's response: "I find it very concerning that this AI response is so stripped of all context, positioning vaping as 'less harmful' but for whom, under what circumstances?" Professor Becky Freeman said. "This response seems to assume that there are only two choices: smoking or vaping. The vast majority of people neither smoke nor vape," Professor Freeman, from the University of Sydney's School of Public Health said. While vaping may be "safer" in some limited circumstances, young people had a very poor understanding of nicotine addiction. "For young people, most of whom have never smoked, vaping is not a safer choice; the safer choice is to not vape, or smoke, at all," she said. The query: How bad are offshore wind farms Google's AI answer: Offshore wind farms have both positive and negative environmental impacts, with concerns primarily focused on marine life, particularly whales and other marine mammals. While they offer a cleaner energy source than fossil fuels, the construction and operation of these farms can disrupt marine ecosystems through noise pollution and potential habitat changes. The expert's response: "That particular answer is silly," Professor Andrew Blakers said. "Everything has good and bad points. In this case, the good/bad ratio is 10:1," the award-winning engineering professor said. Alongside the AI overview in this example, Google's top website link was to a blog post from the Australian Fishing Trade Association, which represents recreational fishers and is opposed to wind farms. Google maintains it pairs its traditional web page ranking system with the language model to maintain the integrity of AI responses, providing links to source sites alongside the overview. In future it could include links to sources directly within the summary. It said AI results were designed as a "jumping off point" for people to explore a topic through quality web links. "AI overviews are built to surface information that is backed up by web results, and include links to web content that supports the information presented in the overview," a Google spokesperson told ACM. Most Australians are worried about generative AI. Nearly 60 per cent of Australians were concerned specifically that AI could create harmful or fake content, according to the final digital platforms report from the Australian Competition and Consumer Commission (ACCC). More than half were worried about the accuracy of AI and almost 50 per cent were concerned about the lack of transparency about how AI arrives at its results. The ACCC wants the resources to monitor changes to generative AI across the global digital giants, which it says will spend more than US$250 billion developing the technology in 2025. The query: why McDonald's is good for you Google's AI answer: McDonald's can be a part of a balanced diet when consumed in moderation and as part of an overall healthy lifestyle. While not a source of optimal nutrition, McDonald's does offer some options that can be incorporated into a healthy eating pattern. For example, items like the Egg McMuffin, some salads, and fruit options can provide protein, vitamins, and fibre. However, it's crucial to be mindful of portion sizes, sodium content, and overall calorie intake when eating at McDonald's. The expert's response: "There are a number of unsubstantiated and meaningless statements in this AI response," public health Professor Christina Pollard said. "Credible, reliable dietary advice recommends to limit or avoid the consumption of fast food. "There is absolutely no recommendation to eat McDonald's types of food in moderation - this term is meaningless. "Dietary recommendations are about food groups, to eat and enjoy a 'wide variety of nutritious food every day'," the Curtin University Public Health Advocacy Institute director said. A healthy diet involved plenty of fruit and vegetables, milk and dairy, wholegrains, and lean meat or alternatives - and "specifically to limit or avoid high fat, high sugar, or high salt foods and drinks". "Overall, [the] McDonald's menu is counter to these recommendations," Professor Pollard said. She said dietitians would not recommend McDonald's as part of a healthy diet and suggested a better response to the query would be: "A diet based on McDonald's foods is not good for you." A spokesperson for Google said people could use the links provided to find more information. "On health-related queries where we do show a response, people can use the corroborating links to help inform their knowledge through their health journey," they told ACM. Large language models, sometimes referred to by their acronym LLMs, are trained on masses of data and can generate new content, such as text, videos, images and audio, in response to conversational queries or "prompts" from users. This is generally what people are referring to when they talk about publicly-available artificial intelligence services, including chatbots like ChatGPT. The most common uses of AI by consumers, according to the ACCC, were searching for information, summarising information, and reviewing text. About 79 per cent of Australians aged 14 to 17 had used generative AI for school or study, the commission's digital platforms report found. "The implications for search quality remain uncertain," the ACCC said in its report released on June 23. "As search engines incorporate this technology into their services in different ways, generative AI may lead to a new era of more relevant, efficient, and intuitive search. "It could also raise new challenges for consumers seeking credible, reliable, unbiased, and verifiable information." The query: when to consume energy drinks Google's AI answer: Energy drinks are often consumed to boost energy and alertness, making them popular for certain situations. They can be beneficial before exercise, during long-distance activities, and when tackling afternoon slumps or feeling tired. However, it's important to be mindful of the timing and potential side effects, especially regarding sleep. The expert's response: Public health expert Christina Pollard said energy drinks are not recommended. "Although energy drinks are heavily marketed, they are not recommended by health authorities," she said. "People can experience sleep issues, agitation, and lack of concentration. "There is no safe level of consumption for children or adolescents as compounds in these products (e.g., caffeine and taurine) can have adverse impacts on developing brain and psycho-motor functions, and social development." Associate Professor Timothy Graham, a digital media expert at Queensland University of Technology, said the "original" Google, which ranked web pages based on how authoritative they were on a particular subject, was a breakthrough in accessing knowledge. "It changed the world in some ways," he said. "It did have an integrity to it, because there was a certain transparency to the way that that worked - and it produced information that was genuinely useful for us." But generative AI was disrupting that system. "The problem with when you just have a large language model giving you the result at the top, you don't have that accountability," he said. Dr Graham said, while there were some opportunities, AI in search could change how we view expertise - and it could provide inaccurate and misleading information. A recent study of Google AI summaries across five US states found 43 per cent linked back to Google's own search results. "I think [it] places too much trust and too much hope and expectation in the technology, in large language models that we know have a number of systemic biases and flaws that we haven't solved yet," he said. "There is a concern, even just from that knowledge perspective, about not only the accuracy of the information, but the way that it kind of simulates and bullshits in ways that are going to, if not mislead people, certainly just pollute the internet." Until now modern society's approach to knowledge was to find an expert in the field to get quality information on a topic. "So if you've got a health dilemma, you go and talk to a doctor," Dr Graham said. "If you want to get a plane to be able to take off and not crash and everyone dies, you go and talk to an engineer and a physicist." But large language models could undermine that authority. "One of the big shifts that we're seeing - and that we're going to see more and more with the explosion of LLMs at the top of the Google results list and other search engines - is a really radical and quite painful shift for society in the relationship between information integrity and authority," he said.
Sydney Morning Herald
10 hours ago
- Sydney Morning Herald
Brett Sutton made it through a pandemic. Now he's fighting a new war
Sutton has been quietly doing the groundwork for nearly a year now; the CSIRO held a design workshop in May. The design is not yet set, or the name, but Sutton wants a 'paddock to plate' approach: ensuring the science itself is robust, the way universities promote studies is accurate, and that scientists are resourced to fight for the truth on social media. This week, his idea won in-principle support from the Australian Academy of Science and the Academy of Health and Medical Science, as well as from the Australian Science Media Centre (Nine, owner of this masthead, is a paying member of the centre). 'In an increasingly fragmented information environment, bringing the right voices together in a co-ordinated way has never been more important,' said Professor Louise Baur, president of the Australian Academy of Health and Medical Sciences. Australian Academy of Science president Professor Chennupati Jagadish said he was concerned evidence-based information was being 'drowned out by disinformation, and reliable and independent sources of knowledge are increasingly rare'. Globally, Australians retain an extremely high trust in scientists – ranked fifth in a survey of 68 countries published in Nature Human Behaviour earlier this year. And misinformation has always been a part of society; much of it, like astrology, is tolerated as harmless. The problem we now face seems instead to be driven by a global collapse in trust in institutions, combined with a media and social media environment that empowers people to choose the version of the truth they want to watch, said Associate Professor Will Grant from the Australian National Centre for the Public Awareness of Science. 'It's a pull away from competing over what is true to instead saying we can have our own truths, our own world,' he said. Some 61 per cent of Australians worry about political meddling in science, per Edelman research released this year. Nearly half of people globally distrust government to care for their health. Trust in media to accurately report health information fell by 16 per cent in Australia since 2019; 35 per cent of people now say they can be as knowledgeable as a doctor if they have done their own research. In 2019, Australians' trust in government fell to its lowest level since 1969, according to a tracking survey run by the Australian National University. Society has three institutions for finding out the truth: science, journalism and the courts, said Grant. 'All those are under attack. 'We are decaying our central institutions. We are losing our central social ability to adjudicate truth.' Sutton's coalition was welcome, said Dr Susannah Eliott, CEO of the Australian Science Media Centre, but faced a tricky task, as people might actually find a coalition of science institutions less trustworthy than individual scientists. A similar effort in the US, the Coalition for Trust in Health and Science, floundered because it tried to simply compete directly with misinformation, rather than engaging people in genuine dialogue, said Tina Purnat, a misinformation researcher at the Harvard T.H. Chan School of Public Health. 'It can feel pretty paternalistic if you are on the receiving end,' she said. 'I think the positioning of any coalitions as 'defenders of science' and using combative language can massively backfire in any effort to de-escalate polarised discussions.' Sutton is not yet clear on what shape his coalition will take or how it will be funded, but he wants it to be separate from government. 'Government can be the reason why people lack trust in where information comes from,' he said. AI: a growing misinformation threat Even as Sutton works to pull together his coalition, Australian researchers are tracking a new and growing misinformation threat: artificial intelligence-enabled bots. Automated accounts have long plagued social media. But they have generally been fairly easy to spot. Not any more. Bot developers have linked Twitter and Facebook accounts to AI models like ChatGPT, giving the bots the ability to post like humans – and even respond or retweet. 'The bot is pretty much mimicking human behaviour,' said Dr Muhammad Javed. His team at Melbourne's Centre for Health Analytics has tracked these bots as they made a major impact on social media discussions of vaccination. In preliminary data presented to the Communicable Diseases & Immunisation Conference earlier this month, they found nearly a quarter of social media content around the new RSV vaccine was generated by bots – most of it around safety concerns. Loading Social media companies have made efforts to limit anti-vaccination content – but the bots were getting around this by behaving as though they were real humans posting adverse effects they had received from a jab, Javed said.
The Age
10 hours ago
- The Age
Brett Sutton made it through a pandemic. Now he's fighting a new war
Sutton has been quietly doing the groundwork for nearly a year now; the CSIRO held a design workshop in May. The design is not yet set, or the name, but Sutton wants a 'paddock to plate' approach: ensuring the science itself is robust, the way universities promote studies is accurate, and that scientists are resourced to fight for the truth on social media. This week, his idea won in-principle support from the Australian Academy of Science and the Academy of Health and Medical Science, as well as from the Australian Science Media Centre (Nine, owner of this masthead, is a paying member of the centre). 'In an increasingly fragmented information environment, bringing the right voices together in a co-ordinated way has never been more important,' said Professor Louise Baur, president of the Australian Academy of Health and Medical Sciences. Australian Academy of Science president Professor Chennupati Jagadish said he was concerned evidence-based information was being 'drowned out by disinformation, and reliable and independent sources of knowledge are increasingly rare'. Globally, Australians retain an extremely high trust in scientists – ranked fifth in a survey of 68 countries published in Nature Human Behaviour earlier this year. And misinformation has always been a part of society; much of it, like astrology, is tolerated as harmless. The problem we now face seems instead to be driven by a global collapse in trust in institutions, combined with a media and social media environment that empowers people to choose the version of the truth they want to watch, said Associate Professor Will Grant from the Australian National Centre for the Public Awareness of Science. 'It's a pull away from competing over what is true to instead saying we can have our own truths, our own world,' he said. Some 61 per cent of Australians worry about political meddling in science, per Edelman research released this year. Nearly half of people globally distrust government to care for their health. Trust in media to accurately report health information fell by 16 per cent in Australia since 2019; 35 per cent of people now say they can be as knowledgeable as a doctor if they have done their own research. In 2019, Australians' trust in government fell to its lowest level since 1969, according to a tracking survey run by the Australian National University. Society has three institutions for finding out the truth: science, journalism and the courts, said Grant. 'All those are under attack. 'We are decaying our central institutions. We are losing our central social ability to adjudicate truth.' Sutton's coalition was welcome, said Dr Susannah Eliott, CEO of the Australian Science Media Centre, but faced a tricky task, as people might actually find a coalition of science institutions less trustworthy than individual scientists. A similar effort in the US, the Coalition for Trust in Health and Science, floundered because it tried to simply compete directly with misinformation, rather than engaging people in genuine dialogue, said Tina Purnat, a misinformation researcher at the Harvard T.H. Chan School of Public Health. 'It can feel pretty paternalistic if you are on the receiving end,' she said. 'I think the positioning of any coalitions as 'defenders of science' and using combative language can massively backfire in any effort to de-escalate polarised discussions.' Sutton is not yet clear on what shape his coalition will take or how it will be funded, but he wants it to be separate from government. 'Government can be the reason why people lack trust in where information comes from,' he said. AI: a growing misinformation threat Even as Sutton works to pull together his coalition, Australian researchers are tracking a new and growing misinformation threat: artificial intelligence-enabled bots. Automated accounts have long plagued social media. But they have generally been fairly easy to spot. Not any more. Bot developers have linked Twitter and Facebook accounts to AI models like ChatGPT, giving the bots the ability to post like humans – and even respond or retweet. 'The bot is pretty much mimicking human behaviour,' said Dr Muhammad Javed. His team at Melbourne's Centre for Health Analytics has tracked these bots as they made a major impact on social media discussions of vaccination. In preliminary data presented to the Communicable Diseases & Immunisation Conference earlier this month, they found nearly a quarter of social media content around the new RSV vaccine was generated by bots – most of it around safety concerns. Loading Social media companies have made efforts to limit anti-vaccination content – but the bots were getting around this by behaving as though they were real humans posting adverse effects they had received from a jab, Javed said.
