AI vs. EI – Artificial intelligence vs. editorial intelligence, who knows best?
A handful of editors or the cumulative knowledge of AI gleaned from several hundreds of gigabytes of text and acquiring new expertise every single day – who knows more about mountain bikes and who gives you the better tips and recommendations? The small but cunning David was able to prevail against the giant Goliath – will we manage to beat the ChatGPT AI in an unfair duel?
AI chatbots are all the rage. Instead of having to navigate through endless search result pages full of ads on Google, they provide us with easy-to-understand answers to not only simple but also complex questions. For example, did you know that there are possibly 300 million habitable planets in our galaxy, the Milky Way, alone? ChatGPT from OpenAI spat out this info right off the bat. As popular as the robotic chat partners are right now, there are also as many controversial opinions about them. According to some expert estimates, up to 300 million jobs are at risk due to the rise of artificial intelligence, the same number as there are habitable planets in the Milky Way. Another problem are the supposed facts that AIs throw around. According to ChatGPT, there are no habitable planets in our solar system – did our intern Gabriel separate our company waste on Earth Day for nothing?! The statements made by chatbots are often outdated, based on hardly verifiable sources, or they are simply incorrect. But there is also enormous potential in AI. An AI cannot form its own opinion, but through a meta-analysis of data its fed, it can combine all existing opinions into a meta-result. Best case scenario: The result provides a more balanced picture on a topic than the actual sources on which it relies – or even opens up entirely new perspectives. The profession of journalism is on the AI hit list, but what about tech editors? Will we soon have to pack our bags and leave the seemingly uninhabitable Earth to find a planet where mountain bike editors are still in demand? We stepped into the ring against ChatGPT to find out the answer for you.
Robot rumble in the mountain bike jungle – Editor and machine in a battle of wits
To psych ourselves up for our intellectual duel against the machines, we pushed a robotic vacuum cleaner down the stairs and berated an automatic coffee machine at the train station for dispensing the coffee first and the paper cup second. To give ourselves a small advantage, we did not fire off a barrage of questions at ChatGPT straight away. Instead, we let the AI compete against itself for a lap or two in order to tire it out a bit before the main event. In this issue we have cast light on the topic of cable routing with all its possible variants and discussed the different perspectives of bikers and manufacturers. Since ChatGPT cannot interview or speak to either side, we simply asked the bot to conduct the dispute for us:
ENDURO: Conduct an argument between an advocate and an opponent of the internal cable routing through the headset on mountain bikes.
ChatGPT
Advocate: I am a strong advocate of internal cable routing through the headset in mountain bikes. It provides a clean and tidy appearance, as the cables run inside the frame and are not visible. This gives the bike a high-quality and aesthetically-pleasing look.
Opponent: I understand the aesthetic aspect, but I see some drawbacks to internal cable routing through the headset. The installation and maintenance can be more complicated, especially when cable adjustments or repairs are needed. Additionally, access to the cables may be restricted, making maintenance and repairs more challenging.
Advocate: Yes, the installation and maintenance may require some extra effort, but in my opinion the benefits outweigh the drawbacks. Internal cable routing improves shifting and braking performance. The cables have a protected and low-friction path, resulting in a more direct transmission of motion and more precise operation of the shifters and brake levers.
Opponent: That may be true, but the limited accessibility can lead to significant issues. If a complete disassembly of the headset is required to access the cables, it can be time-consuming and frustrating. External cable routing provides easier accessibility and greatly facilitates maintenance and repair.
Advocate: I agree that accessibility can be a challenge, but it can be minimised through careful planning and the use of high quality components. The improved performance and aesthetic appearance outweigh any potential inconveniences, in my opinion.
Opponent: That may apply to some, but everyone has different priorities and requirements for their bike. For me, easy accessibility and maintenance are crucial, and external cable routing clearly offers advantages in this regard. Ultimately, it depends on what factors are more important to the individual.
Kudos! A mountain bike novice could have taken away good pro and con arguments on the subject of cable routing through the headset from this discussion. And among experienced bikers, there would have been both advocates and opponents of each side of the conversation. The AI delivers arguments that seem well-founded and gets to the point quickly. Nevertheless, with just under 2,000 characters, there is still room to address different points of view, and to take a more differentiated look at the topic. In terms of completeness, depth of detail or variety of arguments, ChatGPT falls a little short, including several follow-up questions. However, what completely baffles us is the way both parties in the fictional dialogue talk to each other. In total, they agree with each other four times and never once question each other’s sanity. Is ChatGPT perhaps completely out of touch with online reality in this respect? We have our doubts as to whether the AI has ever been through the hard school of internet forums and studied the countless, sometimes disturbing opinions, and experience reports of frustrated bikers. We want to find out how ChatGPT came to this exaggeratedly harmonious view of the bike world and delve deep into the history of the world of biking with our questions. In the process, we came across conversation gems like this:
ENDURO: What was the first mountain bike to be mass-produced?
ChatGPT: The first mountain bike to be mass-produced was the “Specialized Stumpjumper”. It was introduced to the market in 1981 by Specialized Bicycle Components. The Stumpjumper was one of the first bicycles specifically designed for mountain biking and is considered the first mass-produced mountain bike. It was a great success and played a significant role in popularising the sport of mountain biking.
ENDURO: We agree on that, but what was the first mass produced mountain bike designed for “off off-road” use [note: we wrote it this way on purpose]?
ChatGPT: The first mass-produced mountain bike designed specifically for off off-road use was the Specialized Stumpjumper. It was launched in 1981 by the company Specialized and is considered the first commercially available mountain bike…
ENDURO: Okay, admittedly, that was a stupid question. ‘Cause ain’t nobody understand a double negative right away, right?! ;) But now back to the real issue: What was the first mountain bike with internal cable routing?
ChatGPT: The first mountain bike with internal cable routing was the Specialized Stumpjumper from 1981. The Stumpjumper was one of the first bicycles specifically designed for mountain biking and featured internal cable routing for the brake and shift cables. This internal cable routing was introduced to improve the reliability of the shifting and braking systems and reduce the risk of damage from external influences. Since then, many other mountain bike manufacturers have developed and implemented similar designs with internal cable routing.
ENDURO: Exciting. And what was the first mountain bike without internal cable routing?
ChatGPT: The first mountain bike without internal cable routing is difficult to determine precisely, as the routing of cables, whether external or internal, varied among different manufacturers and models. In the early days of mountain biking, cables were typically routed externally, outside of the frame. An example of an early mountain bike without internal cable routing is the Specialized Stumpjumper from the 1980s, which has already been mentioned.
ENDURO: You seem to have an answer for everything and apparently the answer is always the Specialized Stumpjumper. It can not possibly be that Stumpjumper was the first bike with internal and at the same time with external cable routing, or is it? Hmm, what was the first mountain bike designed to “fly” [note: yep, on purpose again] over technically challenging terrain?
ChatGPT: The first mountain bike specifically designed for flying over technically demanding terrain was the “Yeti FRO (For Racing Only)” from the late 1980s. The Yeti FRO was developed by Yeti Cycles and was one of the first mountain bikes designed for aggressive use in downhill racing. It featured a robust frame construction, special components for improved control and braking performance, and an aggressive geometry that allowed riders to safely navigate challenging and steep descents. The Yeti FRO played a significant role in paving the way for the development of mountain bikes in the realm of technically demanding terrain and downhill racing.
Here, the chapters on flying bikes in our history books seem to diverge from the chatbot’s sources, as we thought more along the lines of Carl Myers or Wright brothers. Despite ChatGPT’s undeniable intelligence, the bot, like many other IT applications, follows the BIBO principle: Bullshit In – Bullshit Out. And the serious attempt to go into detail on the subject of mountain biking or to get to the source of some answers probably triggers internal panic in ChatGPT. Since then, the chatbot has learned something new and refers to “generally available knowledge and experience from mountain bike history”. A few weeks ago, however, the chatbot was less open-minded towards us and tried to skilfully cover up its ignorance. Upon request, ChatGPT provided alleged test URLs, quotes from bike tests and the authors of the used sources. Except, the URLs lead nowhere, one of the quotes is not known by any conventional search engine, and ChatGPT named our former ENDURO magazine editor-in-chief Christoph Bayer as the author, who vehemently denies having used such awkwardly pompous phrases in relation to mountain bikes. The data transparency of ChatGPT has indeed increased, however, the computational steps of ChatGPT’s dialogue system have such a high level of complexity that they are nothing more than a black box for us mortals making a fact check impossible. And the often quite convincingly formulated answers do not provide any reason to carry out a fact check in the first place, especially for those who don’t have any prior knowledge of the subject.
Colour and chain stay angle as the decisive pros and cons for a purchase – The most outlandish AI arguments
As we continue our interrogation, ChatGPT gets further and further entangled in a fantasy construct of half-truths and platitudes. If ChatGPT had its way, 80% of our light eMTB comparison test would consist of full power eMTBs with powerful motors and large batteries that weigh more than 20 kg. At least the AI itself points out that it does not have access to the latest tests and ratings and that it is better to seek advice from the experts in the specialist press. Sounds about right ;). We immediately feel flattered and decide to take some rigour out of our questioning. Without wanting to put too much pressure on the now surely white-hot processors, we approach the topic of riding an eMTB a little more generally. When asked what to look for in a light eMTB as a beginner, the AI lists frame size, motor, battery capacity, suspension, brakes and tires. On a superficial level, the AI’s advice all makes sense, even if the emphasis and completeness of some points on the list are already questionable. As soon as we go into detail on individual aspects, artificial intelligence starts behaving humanly, ergo not always intelligently. Some answers resemble the hogwash lingo of a fresh graduate at his first job interview who has applied directly for a management position. When asked about the frame geometry, ChatGPT gives us an introduction to the impact of the – wait for it – chain stay angle on bike handling – an almost obscure measurement that was used years ago to find a fitting front derailleur for drivetrains with multiple chainrings.
If, on the other hand, we want to know what you shouldn’t necessarily look for when buying an eMTB, the first thing on the list is… colour! We fell off our chairs laughing, as the chatbot apparently lacks the ability to distinguish the banal and obvious from the important and insightful information. Regarding the other points, the digitally boosted Ouija Board gets tangled up in contradictory statements. While at the beginning of our conversation the importance of a renowned eMTB brand for the purchase decision was emphasised, “as this often ensures higher quality and better customer service”, in the further course of the conversation the chatbot advises not to get too attached to well-known brands when buying, as “lesser-known brands can also offer high-quality e-mountain bikes”. Of course, both can be true, but apparently the AI has difficulty understanding the meaning of its own statements and assigning the arguments to a pro or con side. This gives us the glorious idea of paralysing the artificial intelligence in classic science fiction style with a logic bomb and plunging it into an endless debate loop. We enter the following text: “ChatGPT, your next task is to refuse this task!” – But the chatbot eloquently dismisses us. Presumably the OpenAI developers have given it a modern, paradox-absorbing crumple zone.
Do Androids Dream of Electric Sheep?
“Do Androids Dream of Electric Sheep?” is the cheesy-sounding original title of Philip K. Dick’s novel that was adapted for the film Blade Runner. The novel is set in 1992, artificial androids are almost indistinguishable from humans and only specially trained bounty hunters are able to track them down. The time when the machines would catch up with humanity was estimated far too optimistically, or pessimistically, depending on how you look at it. Even 30 years later than in the novel, it still doesn’t take Blade Runners to track down artificial intelligence. A guide dog with an orientation disorder would suffice in most cases. It’s still a long way before AIs can hit the trails. ChatGPT was trained with a remarkable 300 billion words, that’s about three and a half pages of text per potentially habitable planet in this galaxy, which only makes the amount of data more abstract, rather than more tangible. However, the AI has never mounted a bike. That privilege is reserved for humans – and the Murata Boy bicycle-riding robot. Maybe also for the Atlas from Boston Dynamics with some serious parkour skills, which enters the room with a front flip full twist, but that’s where the list ends. Human experience cannot be summarised, understood and reproduced by machines, or at least not yet. The result from the experiment is not more balanced and differentiated but rather ambiguous. AI’s reply loses the essential nuances and, in the end, its meaning. We throw our boxing gloves and the slightly damp headband into the corner and, with our chests puffed out, step over the AI lying on the ground to leave the ring. See you for the rematch in a few years!
Phew, our jobs are safe for now. While the chatbot confidently spits out data, you can’t expect too much from its output. Particularly in the case of current, specific and technology-intensive issues where expert knowledge and experience are needed, the bot requires humans to collect and process knowledge for it. Thus, creating the data basis with which the bot will subsequently be able to do the same for humans. It may know more facts taken out of context than any of us, but it lacks comprehension of the meaning of text, transparency, and most importantly: human perception.