Asking SkyNet Management Questions

The past week there has been a lot of fuss over the release of a language model by OpenAI which was supposed to be the most advanced yet. There is a lot of discussion online too because of the team’s decision to not release the full version of the model, afraid that it will be misused by Russian trolls, Chinese spies or whatever. Nonetheless, the partial model has been available for researchers to tinker with. To make things more convenient, there has also been an online implementation to skip the troubles of having to install the model on my computer.

I played with it to try to find out if it would help me write my doctoral dissertation. Maybe not, but at least give me some inspiration. These are my queries followed by the model’s continuation:

Prompt: Absorptive capacity is important for firms to gain competitive advantage.

A high birth rate reduces labor size relative to that in the United States (approximately 2.5 births per woman per 100 that would be generated in the United States in 2025) by the same method that causes individual WL to lag the rest of the world as a comparable technology (James and Wilcox 2005; Steuber and Turnbull 2006). Moreover, this concept establishes that WL may very well be a competitive advantage in conduct metrics secondary to WL. Thus, in conclusion, an incomplete equilibrium system often poses the problem of generating the next big PBE, ready for limiting these situations…

Prompt: To create disruptive innovations, companies should…

not work in the present day and if they do: “We’re not picking those lines for half-measures. ” Trust Poopmakers, Congress The hard law enforcement obligation imposed by the U. S. government on startups and small businesses should be absolute, followed by the next step. However, the United States should not violate copyright as being without regard to collateral damage and even have some credentials as a custodian of such equivalent works. Counterproductive courts should inquire into the bill from both sides and pass amendments for the immediate reporting of the U. S. to the American people…

The results have been disappointing unfortunately. We are not yet at a point that doctoral students can be replaced by actual robot slaves.

Weekly Reads – Feb 25

This week was a little slow for interesting management articles. I’ll just add fascinating podcast episodes and discussions from the web.

Scientific novelty and technological impact – Tries to find the connection between the novelty of scientific publications and technological impact through resulting patents. Novelty was related to how new the mix of journals referenced in the paper is. Surprise surprise, the highly novel scientific advances result to novel patents.

 The Role of Individual and Organizational Expertise in the Adoption of New Practices – Study at the interface of cognitive psychology and organizational sciences exploring how expertise at the individual and organizational level affect the diffusion of practices within an organization. They find that individuals who have gained expertise through deliberate practice not only adopt new practices faster themselves but also influence their  colleagues to adopt.

Sam Altman’s interview on Conversations with Tyler – As a researcher of entrepreneurship, I find his take that he can judge the potential of a would-be entrepreneur fascinating.  To quote:

These personality traits of determination and communication and the ability to articulate a vision for the world and explain how you’re going to get that done — I used to think that that was so hard to assess in 10 minutes, it was maybe impossible to try, and YC interviews used to be like an hour. I now think that most of the time, we could get it right in five minutes.

Reddit thread on unemployed PhDs – While rants about how difficult the academic market are not new, it seems like this post has gotten more traction than usual. My opinion is that like any other track in life, one should not only consider whether they are passionate about it but also look at the financial viability of such pursuits.

Weekly Reads – Feb 17

These are my interesting reads from this week.

Large teams develop and small teams disrupt science and technology – An extensive study trying to understand what makes disruptive science. It looks at  millions of patents, publications and Github repositories to show that small teams are much more disruptive compared to larger ones.

How do Big Bang Disruptors look like? A Business Model perspective – Management researchers making careers out of new terms. Kidding aside, once you get past this, it is an interesting study exploring the mix of ingredients commonly found in successful unicorns

Patent policy and American innovation after eBay: An empirical examination – Was not aware of this 2006 court case before between eBay and MercExchange. The ruling was supposed to change the dynamics of innovation in the US, by “weakening” IP rights. The authors did not find evidence though that this was the case. Just shows how much unpredictable systems can be.

Analysing the theoretical roots of technology emergence: an evolutionary perspective – Emergence has always been a fascinating topic in technology management. In this paper, they look at how this concept diffused from the disciplines of philosophy of science, complexity theory, and evolutionary economics and has evolved since then in the technology studies paradigm.


Public Speaking

As an aspiring academic, I know that it is important to be able to communicate my research not only to colleagues but also to the society at large. To improve my public speaking, I have signed up in a Toastmaster club. A few months ago, I challenged myself to describe my PhD topic in such a way that the general public would understand.



Weekly Reads – Feb 10

Interesting management reads from the previous week

Beyond the matrix: Visual methods for qualitative network research – collecting network data for qualitative studies

Foundations of entrepreneurial strategy – how do entrepreneurs decide which strategy to pursue

Strategic choice in universities: Managerial agency and effective technology transfer – why technology transfer is not as simple as investing in the support infrastructure

The emergence of the maker movement: Implications for entrepreneurship research – the maker movement as an interesting laboratory to study various aspects of entrepreneurship

Low Risk High Reward Career Advice

From time to time, I get messages from students asking for career advice. In the academia community in Reddit, there are daily posts also asking for how to search for jobs or find mentors. If I had one advice for highly motivated students who might not have the best network or guidance to help them in their path, it is this: Don’t be afraid to send cold emails to successful people.

Ever since I came across this idea, I have been applying it in my own career. Whenever I read articles or listen to podcasts that are fascinating, I reach out to the authors just to say thank you. Sometimes, if I feel it’s relevant, I might even ask for career advice. Believe it or not, most of them actually respond. So, far I have around 85% success rate. People are generally gracious and they always want to help others if what you ask is not too inconvenient for them. The worst thing that would happen is that they would not reply and your email goes to spam. The best case however is that they see your interest and motivation, and you become under their radar. If they sense some opportunity, they might remember you and reach out to you.

If you want to go further and really impress them, you can even create the so-called pre-interview project . It’s a small project that one could do in  a short amount of time that can impress a possible collaborator, future employer, etc.  Especially in this noise-filled world, if you really want to be recognized, you have to find a way to differentiate yourself from the rest.

Conforming vs. Differentiating in Everything

In the first month of my PhD, I came across the article by Hambrick and Chen on how academic fields develop. Briefly, they described three processes that fields how to go through to receive acceptance: differentiation, legitimation and mobilization. The first differentiation means that a field should try to set itself apart from other existing fields. At the same time however, it should not stray too far away as it still have to build legitimacy and gain recognition from the wider scientific community. Mobilization refers to the field’s ability to mobilize resources. As I see it, this last process basically serve as the fuel to advance the two other processes. During those days, I found this study to be interesting but set it aside for the next two years not knowing how to incorporate it in my work.

Differentiation, legitimacy building and mobilization

How new fields gain acceptance

In the past few months, I’ve been thinking of a way to unify the different studies that I’ve been conducting for my PhD. One day, I randomly came across the article again. I then realized that the dynamic of conforming and differentiation occur everywhere. It does not only occur at the field level but also in other levels; not only in scientific development but also in many other facets of life. At the individual level, all of us, in one way or another, conform to the communities we belong to while at the same time, try to make ourselves stand out. To contribute, we try to bring something new or unique to the groups that we are in. Upon looking further, this has been referred to as the theory of optimal distinctiveness in psychology circles, which has been described even as early as 1991.

Recently, this concept has also been gaining more interest at the organizational level, such as this review by Zhao et al. Firms cannot compete by only conforming with other firms in their market, they also have to differentiate themselves from other players in their area. As there can be different dimensions of comparison across firms, the balancing act between conforming and differentiating can be complex. Research then is of value to explore how to orchestrate such dynamics effectively.

Studying in the past two years how new scientific fields develop, I notice the recurring theme of conformation vs. differentiation. Fields have to manage these forces if they want to be established. Big firms have to be aware of these forces if they want to stay relevant. New entrepreneurial firms also have to balance the two to gain resources and find customers. Teams within  firms, to stay innovative, have to be in touch with what their colleagues are doing while at the same time, bring new things to the table. Researchers and managers also have to practice optimal distinctiveness.

The Science of Science

Last week, I was having lunch with a colleague and she asked me, “what is your research niche?” The answer did not come as easily because it was something I was struggling with before. Ever since I started my PhD, I was exploring various perspectives, not trying to settle with a specific scientific field. Working at the interface of many fields including pharmaceutical sciences, innovation studies, scientometrics, sociology of science and management, I did not want to settle with a field afraid that it would lock me in. After all, it is an important decision as it would affect the future career opportunities I could pursue in academia. The answer should be something that I am greatly interested in, something that I can stand exploring in for the rest of my academic career. At the same time, it should be something that would have an exciting future ahead of it.

Finding the field I identify with was a journey, picking up nuggets along the way. One is collaborating with a supervisor whose expertise is bibliometrics. This exposed me to journals like Scientometrics that always interested me whenever new issues would be released as various studies get creative in analyzing various texts.  I was also very interested in data science, curious about the new techniques people apply to analyze and present data. At the same time, I was  fascinated with how new academic fields started. This article by Hambrick and Chen, “New academic fields as admittance-seeking social movements: The case of strategic management” was one of the first that I read on the topic. With my interest forming in such direction, I had to read Kuhn’s The Structure of Scientific Revolutions which confirmed my interest in this field whatever it is called.

All of these nuggets seem unrelated at first but they were pointing towards something. The problem was I did not know what to call the field I was interested in. Fortunately, a review published recently in Science by Fortuno et al.  helped me. In their review, they were able to put into words what I was really excited studying in my future academic career. It is  called the “Science of Science.”  They viewed the science of science as “a transdisciplinary approach that uses large data sets to study the mechanisms underlying the doing of science.”

With what I am doing now, studying how fragment-based drug discovery emerged as a scientific field, I felt that this review deeply resonated with me. I encourage everyone else, even those not from my field to read it, as it is very fascinating.

Getting Featured in Nature Biotech

There has been more push for scientists to interact with the greater public. As a young scientist hoping to break into the field, it is important to take every opportunity to get exposure. Last year, I had a great opportunity to be featured in Nature Biotechnology. Although it ended up to be just one line in the end, the experience I had of being interviewed was a nice opportunity to understand how science journalism works and more importantly, to share the research I am doing to my target audience of drug discovery practitioners. In this brief blog post, I will share how it happened.

Last year, there was a drug that got approved from the firm Astex. Coincidentally, although the drug was not derived from the approach I am studying for my PhD, the firm Astex is one of the pioneers of in the approach called fragment-based drug discovery (FBDD). With this news, the person writing the article, Mark Peplow, was looking around for more information about Astex and FBDD. With some luck, he came across our consortium website (Fragnet.EU) and found the research that I was carrying out which was just about that – the development of the approach. He first reached out to my supervisor Peter. However, realizing how great of an opportunity it would be for me, my supervisor who was very supportive decided to direct him to me.

With that, a time was set for our interview. Before the actual interview, I prepared a little bit by reviewing the numbers I had with regards to collaboration in FBDD. At first I was a little nervous, since I had not experienced an interview before. However, with time, I eased up and just talked about all the things I knew about FBDD. It probably ended up to be a 30 minute call as I talked about various facets of collaborations. It was a really pleasant experience overall. At the end, he informed me when it would get published and said that he would inform me once again when it happens.

After a month of waiting, the article was live and I had my 1 minute of fame.

Bibliometrics Assisted Literature Review

Starting a PhD program or any research project for that matter, one of the first things that you have to do is the literature review. When I first started carrying out the review, I found searching literature and organizing the readings to be excruciating. Where do you begin? In what order should you read your articles? Where do you stop reading? After delving into bibliometrics, I found that using the tools are really helpful to make the literature review less painstaking and more efficient. In this post, I will just list my ideas on how various bibliometric techniques can aid in this task.

Literature Search

One of the first things one has to do is to download the literature. Many researchers would carry this out by using Google scholar and search the keywords that they are familiar with. The problem however with this process is that especially for beginning researchers, they would not know all the relevant keywords in the first place and thus, exclude a lot of important papers. For more advanced researchers, they can resort to the Web of Science or Scopus and apply various Boolean operators to narrow or widen their search. But still, the problem persists, how can you ensure that you have not excluded valuable articles that are not using the keywords in their title, abstract or author-identified keywords.

Bibliometrics has an approach that can be helpful. To ensure that your collection of articles will be comprehensive, you can grow that collection from a seed of articles. To do so, you first download a set of articles through keywords that you are sure are related to your topic of interest. After downloading data from these set of articles, you can grow this set by downloading their frequently cited articles. One can set a minimum threshold of citations an article should have before it is downloaded. This can easily be done through software like CitNetExplorer, which exports the DOI.

Extending this further, another step one can do is download the citing articles. This is especially helpful for fields where advances are constantly occurring, making it difficult to track the keywords being used. This also allows one to identify the adjacent fields that the original field is extending to. This step can easily be done through the citation report feature of the Web of Science. As a caveat though, one should set a threshold on how many citations a paper should have in the original dataset before it is added to ensure that all the papers are still relevant. This can be done in the absolute or relative. For instance, one should consider that a paper cites 5 papers from the original dataset or at least 30% of its citations are from this. One should also consider the journal and category the article belongs to.

Organizing your Papers

Having downloaded the papers, it is now important to organize them by topics. To help with identifying the subtopics within your main topic, you can create a rough cooccurrence map of the keywords. This can be carried out through software like VosViewer. This shows you the different keywords used in your literature and how related they are with each other.

A more direct way of organizing the papers is by plotting the bibliographic coupling network of the publications. This plot shows paper according to how they are related to each other based on the references they share.

Reading Order

Now that you have to organized your papers, there are many ways to read them according to your preference. I propose to subdivide them by core papers and current papers. You can then read the core papers first to contextualize the foundations of the field. These core papers are identified by high citation count within your set of papers. On the other hand, the current papers show the current trends in the field. These are identified by looking at the latest publications in the top journals in your field. This journals can be identified by combining measures of citations, number of relevant articles and relatedness of keywords.

Literature Review

To carry out the actual literature review, everyone has their own system. I fortunately have found something that works for me. It involves combining Microsoft Access with a qualitative data analysis software like Atlas.Ti. I plan to share my system in the coming weeks.

NOTE: This is draft#1 and is still under revision.