What does an AI think about Net Neutrality?

Originally published on my LinkedIn Newsletter, 9th Feb 2023. See here for comment thread

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:

1. 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.
2. 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.
3. 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.
4. 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.
5. 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:

1. 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.
2. 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.
3. 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.
4. 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.
5. 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:

1. 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.
2. 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.
3. 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.
4. 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:

1. 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.
2. 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.
3. 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.

 

Telco use-cases for AI: A simple categorisation model

The coming years will see the application of AI technology across all sectors of the economy and life. The telecoms industry is no different. Although I’ve been commenting on telco-sector AI in the context of “TelcoFuturism” for some time (link), and co-ran a workshop on it in May 2017 (link), the last few months have seen a notable upswing in interest. I’d say that the public use-cases now seem to be significantly in advance of those for blockchain, in terms of potentially-transformational technologies.

That said, it can still be hard for many executives to grasp exactly what is likely to change, and when, for AI/telecoms combinations. This is highlighted by the surge in AI-related panels, presentations and even complete streams at industry conferences – although sometimes I see more interest from generalist AI people about the telecoms vertical, versus telecom specialists looking at what’s new. 

Both sides of the equation have large volumes of obscure acronyms, multi-layered technology stacks, and complex volume chains – which can mean that mutual understanding is often confined to narrow niches. AI covers machine- and deep-learning, language processing, machine-vision and much more. Telecoms includes vast realms of internal systems and processes that are unknown to most who are not insiders – domains like core networks, OSS/BSS, network optimisation, toll fraud and service-assurance are alien to those not steeped in the industry.

One of the ways I’ve been using to “set the scene” for describing AI/telecoms intersections is to simplify and categorise the use-case areas. I count three, possibly four, large “buckets” into which a variety of telecom AI impacts will fit. These buckets are not based on either specific AI or telecoms technology slices, but more on understandable business functions and roles:

• Dealing with customers
• Managing operations
• Creating new services
• (External risks)

 Within each of these areas, there are many, many sub-sectors – and also some overlap.

“Dealing with customers” can include everything from voice/text chatbots for customer-service, through to predictions of which customers are least-happy and may “churn” to competitors. Where telcos have retail outlets, it could incorporate various in-store technologies, or it could be about smarter web-consoles for B2B customers running complex managed services.

“Managing operations” is even more diverse – it could be fault prediction for network elements, optimising the 100s of configuration variables for radio networks, spotting fraudulent traffic to international premium-rate numbers, allocating engineering resources more productively, or protecting against hackers and malware. There are hundreds of possible uses here, which mostly overlay on top of existing operational/business support systems (OSS/BSS) See also my recent post (link)

“New services” also spans a range of areas, but broadly splits between AI-enabled and AI-enabling services. An AI-enabled service could be a local-language voice assistant added to a cable operator’s set-top box or remote control. Or it could be the provision of integrated “smart city” solutions including video-cameras and security analytics. AI-enablement could include offering “edge” servers for hosting local processing, milliseconds transport-time away from a device, or it could be the provision of anonymised bulk data for others to apply algorithms to. Telco opportunities with IoT+AI include both enablement and enabled services, in numerous manifestations.

The “risks” category includes a diffuse set of possibilities by which AI might harm the telecom industry, or dampen demand for services. Smarter devices (eg autonomous vehicles) will be able to host their own offline image processing & route-planning locally, rather than needing realtime connectivity at 5G speeds/latencies. Another threat could be customers’ smart assistants renegotiating price-plans on their behalf – after crowdsourcing millions of conversations to deduce how best to game the retention staff’s scripts and objections. (Of course in the latter example, the customer-retention team could themselves be bots). Numerous types of automated “least-cost X” and arbitrage engines are likely to emerge. Various security risks are also probable here too.

Clearly, using just these four "buckets" misses much of the fine-grained detail. But I find it helpful as a starting point, as most top-level industry issues apply differently to each. 

Consider input data, for example – for both customer management and operations, telcos have abundant historical records and ongoing data collection that may generate terabytes per day. But for the former, privacy considerations often come to the fore in terms of regulation and risk, while this is far less of a concern for internal operational data, for example on how the network is running. For new services, almost by definition the focus is on collecting/processing/transporting new data, rather than deriving conclusions from existing sets. 

This four-way framework is also useful for thinking about different types of ROI model - split broadly between impacting existing revenues, existing costs, new revenues and potential changes to underlying assumptions. 

I'll be covering these topics in more depth in various upcoming presentations and reports, as well as looking at other areas of telco-linked innovation such as blockchain, 5G and enterprise verticals. Please get in touch if you would like more detail, or are interested in internal workshops, external support through events or white papers, or are seeking ongoing strategic advisory support.

Emerging risks to telcos from "Cuckoo Platforms"

Summary

• Telcos want to be platform players at varying points in their network architecture and service offerings. 
• But successful platforms generally need "anchor tenants" to gain scale.
• The problem comes when anchor-tenants are themselves other 3rd-party platforms.
• There is a risk of platforms-on-platforms acting as "cuckoos", pushing the native owner's eggs out of the nest.
• Telcos face a risk from major cloud platforms overwhelming their MEC edge-compute platforms.
• ... and a risk from major AI-based commerce platforms overwhelming their messaging, voice and IoT platforms.
• Other future platforms also face similar challenges.
• To succeed as platform providers, telecom operators need to have their own anchor-type services, and to have a well-designed approach to combating the risk of parasitic cuckoo platforms.

Background: the Internet overcame its broadband host

The cuckoo bird is infamous for laying its eggs in other birds' nests. The young cuckoos grow much faster than the rightful occupants, forcing the other chicks out - if they haven't already physically knocked the other eggs overboard. (See "brood parasitism", here).

Analogies exist quite widely in technology - a faster-growing "tenant" sometimes pushes out the offspring of the host. Arguably Microsoft's original Windows OS was an early "cuckoo platform" on top of IBM's PC, removing much of IBM's opportunity for selling additional software. 

In many ways, Internet access itself has outgrown its own host: telco-provided connectivity. Originally, fixed broadband (and the first iterations of 3G mobile broadband) were supposed to support a wide variety of telco-supplied services. Various "service delivery platforms" were conceived, including IMS, yet apart from ordinary operator telephony/VoIP and some IPTV, very little emerged as saleable services.

Instead, Internet access - which started using dial-up modems and normal phone lines before ADSL and cable and 3G/4G were deployed - has been the interloping bird which has thrived in the broadband nest instead of telcos' own services. It's interesting to go back and look at the 2000-era projections for walled-garden, non-Internet services.


The need for an anchor tenant

The problem is that everyone wants to be a platform player. And when you're building and scaling a new potential platform, it's really hard to turn down a large and influential "anchor tenant", even if you worry it might ultimately turn out to be a Trojan Horse (apologies for the mixed metaphor). You need the scale, the validation, and the draw for other developers and partners.

This is why the most successful platforms are always the one which have one of their own products as the key user. It reduces the cannibalisation risk. Office is the anchor tenant on Windows. iTunes, iMessage and the camera app are anchors on iOS. Amazon.com is the anchor tenant for AWS.

Unfortunately, the telecoms industry looks like it will have to learn a(nother) tough lesson or two about "cuckoo platforms".


MEC is a tempting nest

The more I look at Multi-Access Edge Computing (MEC), the more I see the risks of a questionable platform strategy. Some people I met at the Small Cells event, in the US a couple of weeks ago, genuinely believe it can allow telcos to become some sort of distributed competitor to Amazon AWS. They see MEC as a general-purpose edge cloud for mainstream app and IoT developers, especially those needing low-latency applications. 

I think this is delusional - firstly because no developer will want to deal with 800 worldwide operators with individual edge-cloud services and pricing, secondly because this issue of latency is overstated & oversimplified (see my recent post, link), and thirdly because a lot of edge-computing tasks will actually be designed to reduce the use of the network and reliance/spend on network operators.

But also, this "MEC as quasi-Amazon" strategy will fail mostly because the edge/distributed version Amazon will be Amazon. The recent announcement by Nokia that it will be implementing AWS Greengrass in its MEC servers is a perfect example (link). I suspect that other MEC operators and vendors will end up acting as "nests" for Azure, IBM Bluemix and various other public cloud providers.

Apologies for the awful pun, but these "cloud-cuckoos" will use the ready-made servers at the telco edge to house their young distributed-computing services, especially for IoT - if the wholesale price is right. They will also build their own sites in other "deeper" network locations (link). 

In other words, telcos' MEC deployments are going to help the cloud providers become even larger. They may get a certain revenue stream from their tenancy, but this will likely be at the cost of further entrenching the major players overall. The prices paid by an Amazon-scale provider for MEC hosting are likely to be far lower than the prices that individual "retail" developers might pay.

(The real opportunity for MEC, in my view, lies in hosting the internal network-centric applications of the operators themselves, probably linked to NFV. Think distributed EPCs, security gateways, CDN nodes and so on. Basically, stuff that lives in the network already, but is more flexible/responsive if located at the edge rather than a big data centre).


End-running Messaging-as-a-Platform (MaaP)

Another example of platform-on-platform cannibalisation is around the concept of "messaging as a platform", MaaP. Notwithstanding WeChat's amazing success in China, my sense is that it's being vastly over-hyped as a potential channel for marketing and customer interaction. 

I just don't see the majority of people in other markets forgoing the web or optimised native apps, and using WhatsApp or iMessage or SnapChat or SMS as the centrepiece of their future purchases or "engagement" (ugh) with companies and A2P functions. But where they do decide to use messaging apps for B2C reasons, the chatbots they interact with will not be MaaP-dedicated or MaaP-exclusive. 

These chatbots will themselves be general "conversational platforms" that work across multiple channels, not just messaging, with voice as well as text, and with a huge AI-based back-end infrastructure and ongoing research/deployment effort. They'll work in messaging apps, browsers, smart speakers, wearables, car and general APIs for embedding in apps and all sorts of other contexts.

Top of the list of conversational platforms are likely to be Google Assistant, Amazon Alexa, Apple Siri, Microsoft Cortana and Facebook M, plus probably other emergent ones from the Internet realm.


MaaP is "just another channel" for broad conversational/commerce platforms

In other words, some messaging apps might theoretically become "platforms", but the anchor tenants will be "wholesale" conversational platforms, not individual brands or developers. In some cases they will again be in-house assistants (iMessage + Siri, or Google Allo + Assistant for instance). In other cases, they may be 3rd-party bot ecosystems - we already see Amazon Alexa integrated into numerous other devices.

Now consider what telcos are doing around MaaP. As well as extending their existing SMS business towards A2P (application-to-person), they have also allowed third-parties like Twilio to absorb much of the added value as cPaaS providers. And when it comes to RCS* which has an explicit MaaP strategy, they have welcomed Google as a key enabler on Android, despite its obvious desire to use it mainly as a free iMessage rival. (*obviously, I'm not a believer in RCS succeeding for many other reasons as well, but let's leave that for this argument).

What the GSMA seems to have also missed is that Google isn't really interested in RCS MaaP per-se - it simply wants as many channels as possible for its Assistant, and its DialogFlow developer toolkit. To be fair, Google announced Assistant, and acquired API.AI (DialogFlow's original source) after it acquired Jibe. It's moved from mobile-first, to AI-first, since September 2015.

The Google conversational interface is not going to be exclusive to RCS, or especially optimised for it. (I asked the DialogFlow keynote speaker about this at last week's AI World conference in Boston, and it was pretty clear that it wasn't exactly top-of-mind. Or even bottom-of-mind). Google's conversational platform will be native in Android, in other messaging apps like Allo, Chrome, Google Home and presumably 1000 other outlets.

From an RCS MaaP perspective, it's a huge cuckoo that will be more important than the Jibe platform. There is no telco "anchor tenant" for RCS-MaaP as far as I can tell - I haven't even seen large deployment of MNOs' own customer-care apps using it. If I was an airline's or a retailer's customer experience manager, and I was looking beyond my own Android & iOS apps for message-based interactions, I wouldn't be looking at creating an RCS chatbot. I'd be creating an Assistant chatbot, plus one for Alexa and maybe Siri.


Can you cuckoo-proof a platform?

Apple, incidentally, has a different strategy. It tends to view its own services as integrated parts of a holistic experience. It tries to make its various platforms cuckoo-proof, especially where it doesn't have an anchor tenant app. This is a major reason for the AppStore policies being so restrictive - it doesn't want apps to be mini-platforms in their own right, especially around transactions. Currently, Google and Amazon are fighting their own mutual anti-cuckoo war over YouTube on Fire TV, and sales of Google Home on Amazon.com (link). Amazon and Apple are also mutually wary.

It's worth noting that telcos are sometimes pretty good at cuckoo-deterrence too. In theory, wholesale mobile networks could have a been a platform for all manner of disruptive interlopers, but in reality, MVNO deals have been carefully chosen to avoid commoditisation. A similar reticence exists around eSIM and remote SIM provisioning - probably wisely, given the various platform-on-platform concepts for network arbitrage that have been suggested.


Conclusions

In my view, both MEC and (irrespective of its many other failings) RCS are susceptible to cuckoo platforms. I also wonder if various telco-run IoT initiatives, and potentially network-slicing will become a platform for other platforms in future too.

One of the key factors here is a "the rush to platformisation". Platforms only succeed when they evolve out of already-successful products, which can become inhouse anchor tenants. Amazon's marketplace platform grew on the back of its own book and other retail sales. AWS success grew on the back of Amazon using its own APIs and cloud-computing.

MEC needs to succeed on the basis of telcos' own use of their edge-computing resources - which don't currently exist in a meaningful way, partly because NFV has been slower than expected. MaaP needs telcos' own messaging services and use-cases to be successful before it should look at external developers. With RCS, that's not going to happen.

Network-slicing needs to have telcos' own slices in place, before pitching to car manufacturers (or Internet players, again). IoT is the same too. Otherwise, expect even more telco eggs to be pushed out of the nest, as they help to foster other birds' offspring.