Two very important trends are occurring in tech I’m following at the moment, so I thought it might be fun to combine them:
- The emergence of #GenerativeAI, for answering questions, generating images and sounds, and potentially a whole lot more. OpenAI #ChatGPT
is the current best-known, but there are dozens of others using
language models, transformers & other techniques. Some people are
suggesting it will redefine web search – and potentially an awful lot
more than that. Some even see it as a pivotal shift in technology,
society and “skilled” employment. - The re-emergence of discussions around #NetNeutrality and associated regulation relating to technology platforms, telcos and networks, like the ridiculous (un)#fairshare & #InternetTrafficTax concept being pitched in Europe by lobbyists. In the UK, Ofcom
recently concluded a consultation on whether changes to NN rules should
be made (I sent in a reply myself – I’ll discuss it another time).
So, I asked ChatGPT what it thought about NN, over a series of
questions. I specifically focused on whether it helps or hinders
innovation.
The transcript is below, but some thoughts from me first:
- The text is good. Almost alarmingly good. I found myself
saying “good point” a few times. This is probably because it gives
reasons in fairly long lists, not just “3 bulletpoints for a slide”. - It seems pretty even-handed, with “proponents say this, others say that”
- You
can sense that its training base tends to give it “common” responses
and frequently-cited arguments. That doesn’t mean they’re wrong, but it
can lack nuance, or repeat some common *fallacies* as well. - The long-list approach and comments is quite good at highlighting the need for multiple approaches
& reconciling them. A single statistical approach isn’t enough –
there are also qualitative questions to ask, surveys to undertake and
multiple angles to absorb. ChatGPT understands the issue is complex,
even if it cannot resolve the complexity itself. Simple answers are
wrong. - I was particularly impressed with the response to my question on cross-border effects, and to separating NN vs. funding effects.
- It
struggled with the last question, about Internet and non-Internet
innovation. EDIT: I just realised that it ignored my typo, and
understood that I meant “directly” when I wrote “direct” in my question - I’d
be very worried if I did bog-standard “content generation” for
clickbait blogs, “bucketshop” market research, or corporate social
posts. This is all perfectly-usable general blurb if you need slabs of
text nobody is going to really delve into too deeply.
All that said, I don’t think this is (yet) a gamechanger in terms of
analysis and argument. It’s good for collating a lot of “food for
thought”, but as others have pointed out, it can also be “confidently
wrong”, sometimes in amusing ways.
In a separate chat, I asked it for a contrarian’s view of #5G use-cases. While it was right on some things (“Some argue that the vast majority of #IoT devices do not require the high speed and low latency that 5G provides and that the hype around IoT is overblown.”) others were less convincing: (“Some
argue that 5G may not provide the low latency and high reliability that
is being promised, and that there are other technologies, such as wired
connections, that are better suited for applications such as autonomous
vehicles”). If there’s one thing less relevant to self-driving cars than 5G, it’s fixed broadband!
Anyway – enjoy the debate treanscribed in full, below.
(Note: the image for this article came from Stable
Diffusion, when I asked for a picture showing “An advanced AI debating
Net Neutrality”)
Me: Does net neutrality help innovation?
ChatGPT: Net neutrality has been a topic of much
debate, with proponents arguing that it promotes innovation and others
arguing that it stifles it.
Proponents of net neutrality argue that it helps to level the
playing field for new entrants and small businesses by preventing
Internet Service Providers (ISPs) from discriminating against certain
types of traffic or services. This, in turn, encourages innovation, as
entrepreneurs and startups are free to bring new products and services
to market without fear of being blocked or slowed down by ISPs.
On the other hand, opponents of net neutrality argue that it creates
a regulatory burden that stifles innovation and investment in the
broadband industry. They argue that without the ability to prioritize
different types of traffic, ISPs will be unable to effectively manage
their networks and may be forced to limit investment in new
infrastructure and technologies.
Ultimately, the impact of net neutrality on innovation is a complex
and highly debated issue, and there is no clear consensus on whether it
helps or hurts innovation. However, proponents of net neutrality
generally believe that it promotes a free and open internet that
supports innovation and competition, while opponents believe that it
imposes unnecessary regulation that stifles growth and investment.
Me: What research is necessary to reach a better conclusion?
ChatGPT: To reach a more definitive conclusion on
the impact of net neutrality on innovation, several types of research
would be necessary, including:
- Economic studies: Economic studies could analyze the impact
of net neutrality regulations on investment and innovation in the
broadband industry, as well as the impact on consumer prices and access
to broadband services. - Case studies: Case studies of countries
or regions with and without net neutrality regulations could provide
valuable insights into the real-world effects of these regulations on
innovation and investment in the broadband industry. - Surveys and
interviews: Surveys and interviews with entrepreneurs, startups, and
industry experts could provide insights into the impact of net
neutrality on the ability of new entrants to bring new products and
services to market. - Technical studies: Technical studies could
examine the impact of net neutrality regulations on network management
and traffic prioritization, and assess the potential impact on network
performance, reliability, and security. - Long-term data analysis:
Long-term data analysis could track changes in investment, innovation,
and consumer prices over time in regions with and without net neutrality
regulations, providing valuable insights into the long-term impact of
these regulations.
Overall, a comprehensive and multi-disciplinary approach to
research, combining economic, case study, survey, technical, and data
analysis methods, would be necessary to reach a more definitive
conclusion on the impact of net neutrality on innovation.
Me: How would you measure innovation in this context?
ChatGPT: Measuring the impact of net neutrality on
innovation is a complex task, as innovation can take many forms and can
be difficult to quantify. However, several metrics could be used to
measure innovation in this context, including:
- Investment in research and development (R&D): This could
be measured by tracking the amount of investment in R&D by
broadband companies and startups, as well as the number of patents filed
in relevant areas. - New product and service launches: This could
be measured by tracking the number of new products and services
introduced by broadband companies and startups, as well as the market
adoption and success of these offerings. - Entrepreneurial
activity: This could be measured by tracking the number of new startups
founded in the broadband industry, as well as the success of these
startups in attracting investment and bringing new products and services
to market. - Consumer benefits: This could be measured by
tracking changes in consumer prices, access to broadband services, and
the availability of new and innovative online services and applications. - Network
performance and reliability: This could be measured by tracking changes
in network speed, latency, and uptime, as well as the ability of
networks to handle new and innovative applications and services.
While these metrics are not exhaustive, they provide a good starting
point for measuring the impact of net neutrality on innovation in the
broadband industry. By tracking changes in these metrics over time in
regions with and without net neutrality regulations, researchers could
gain valuable insights into the impact of these regulations on
innovation.
Me: A lot of those metrics are international. More regions
with net neutrality might increase innovation globally, not locally. How
do you account for that?
ChatGPT: You are correct, some of the metrics
mentioned could be influenced by factors beyond the borders of a single
region. To account for this, it would be important to consider both the
local and global impact of net neutrality on innovation.
For example, to measure the local impact of net neutrality,
researchers could compare the metrics mentioned in regions with and
without net neutrality regulations, taking into account factors such as
the local economy, cultural and regulatory environment, and the state of
the broadband industry in each region. This would provide valuable
insights into the specific impact of net neutrality on innovation within
those regions.
To measure the global impact of net neutrality, researchers could
compare these metrics on a global scale, taking into account factors
such as the state of the global economy, the state of the broadband
industry globally, and the regulatory environment in different regions.
This would provide a broader perspective on the impact of net neutrality
on innovation globally, and could help to identify any trends or
patterns that may not be apparent from a regional analysis alone.
Overall, it is important to consider both the local and global
impact of net neutrality on innovation to gain a complete and accurate
understanding of the impact of these regulations on the broadband
industry and innovation more broadly.
Me: How would we know if net neutrality had a larger effect on innovation than availability of financing for startups?
ChatGPT: Determining the relative impact of net
neutrality versus the availability of financing on innovation can be
challenging, as these factors are often interrelated and can have
complex and interconnected effects. However, several approaches could be
used to isolate the impact of each factor, including:
- Comparative studies: Researchers could compare regions with
and without net neutrality regulations, but with similar levels of
financing available for startups. By controlling for the availability of
financing, researchers could isolate the impact of net neutrality on
innovation. - Historical analysis: Researchers could analyze data
from periods of time when net neutrality regulations were in place or
not in place, and compare this data with changes in the availability of
financing for startups. This would help to identify any correlations
between net neutrality and innovation, independent of changes in
financing. - Causal inference methods: Researchers could use
causal inference methods, such as regression analysis, to model the
relationship between net neutrality, financing, and innovation, while
controlling for other factors that could influence these relationships. - Survey
and interview-based research: Researchers could survey and interview
startups, entrepreneurs, and industry experts to gain insights into the
relative importance of net neutrality and financing for innovation. This
would provide valuable qualitative data to complement the quantitative
data obtained from other research methods.
Overall, a multi-disciplinary and multi-method approach,
incorporating comparative studies, historical analysis, causal inference
methods, and survey and interview-based research, would be necessary to
determine the relative impact of net neutrality and financing on
innovation in a robust and comprehensive manner.
Me: How do you distinguish innovations that direct relate to
Internet access, compared to those which involve non-Internet
applications and technologies?
ChatGPT: Distinguishing innovations that directly
relate to Internet access versus those that involve non-Internet
applications and technologies can be challenging, as many innovations
are influenced by both Internet access and non-Internet technologies.
However, several approaches could be used to differentiate these types
of innovations, including:
- Technical classification: Innovations could be classified
based on their underlying technologies, with innovations that rely
primarily on Internet access being classified as Internet-related
innovations and innovations that rely primarily on non-Internet
technologies being classified as non-Internet-related innovations. - Market
classification: Innovations could be classified based on the markets
they serve, with innovations that serve primarily Internet-based
markets, such as online commerce or online communication, being
classified as Internet-related innovations and innovations that serve
primarily non-Internet-based markets, such as manufacturing or
agriculture, being classified as non-Internet-related innovations. - End-user
classification: Innovations could be classified based on their
end-users, with innovations that are primarily designed for use by
individuals accessing the Internet being classified as Internet-related
innovations and innovations that are primarily designed for use by
individuals not accessing the Internet being classified as
non-Internet-related innovations.
It is important to note that these classifications are not mutually
exclusive, and that many innovations may have elements of both
Internet-related and non-Internet-related technologies, markets, and
end-users. Nevertheless, using these classifications can provide
valuable insights into the extent to which innovations are influenced by
Internet access, and can help to distinguish Internet-related
innovations from non-Internet-related innovations.