couple reading a book together

Reading with bots

It seems obvious that anyone who is not using generative AI in their day job is missing out. There is a wealth of interesting opportunities, and new ways of working that need to be explored and analysed. What I have been playing around with lately is what it means to read with the help of bots.

I try to read a lot. I like pure human reading on paper, but am also aware that I need to develop different reading skills to consume information at the rate and depth that I want to. So, I have since long also used skimming in some cases – reading the first line in each paragraph in a book, and if not surprised continue until I do not understand the argument, then slow down. I do this when I am not sure a book is worth deep reading, and sometimes I am right, sometimes I am wrong and have to shift reading modes.

Bot reading allows for a new kind of reading, that can be very effective – depending on how you prompt the reading. Here is my current favourite prompting structure:

  • Ask for a summary in 5-10 points depending on how interesting the thing is — and specifically ask for summary of argument and analysis separately.
  • Ask for a criticism in 3-5 points to understand the weaknesses of the paper or article.
  • Ask for any novel or surprising items – again 3-5.

Doing this in different variations allows you to approach texts in a multistep evaluation: first, if the result from the reading prompt is enough you can stop there (occasionally verifying that the bot did its job well – of course, but one in 20 papers perhaps), second – if the summary is intriguing enough continue interrogating the paper.

  • Ask for clarification of the criticisms and how the author could meet them.
  • Ask for X’s perspective (“What would a virtue ethicist say about this?”)
  • Ask for related ideas or papers.

Overall this then gives you a sense of if the paper should be the subject of deep reading.

Now, I am the first to admit that this feels like cheating. But the alternative is not having the time to read these articles or papers at all, since there is finite time in the week — so this at least gives a deeper situational awareness and opens the mind to detect trends and patterns in the discourse you are interested in.

The trick, I find, is to think about this as really interrogating or talking with the paper in different ways; building it into a conversation.

Here an example of the first stage with Brooking’s recent article on cities and AI (I used Claude 2 for this — another trick is to do this with different bots):

Here is a 10 point summary of the article “Building AI cities: How to spread the benefits of an emerging technology across more of America”, along with 5 criticisms and 3 novel/surprising points:

Summary (10 points):

  1. AI activity is heavily concentrated in a few “superstar” tech hubs like SF and Seattle.
  2. Generative AI job postings also appear highly concentrated so far in early adopter cities.
  3. This concentration risks limiting innovation, economic opportunity, and accessible AI applications.
  4. Market forces alone are unlikely to decentralize AI geography. Intentional policy is needed.
  5. The federal government should expand R&D funding with geographic distribution mandates.
  6. Access to computing power and data needs to be democratized.
  7. Workforce development programs should aim to build AI talent pipelines in new regions.
  8. Federal grants can catalyze new regional AI clusters and ecosystems.
  9. States can complement federal efforts through targeted R&D, data access, skills programs.
  10. Bottom-up strategies tapping federal support can grow viable new AI hubs.

Criticisms (5 points):

  1. It lacks data on the concentration of generative AI specifically. Claims remain speculative.
  2. Proposed policies may spread AI thinly rather than build critical mass hubs.
  3. It underestimates costs of decentralization and duplication of resources.
  4. The roles of academia, industry, government are not clearly delineated.
  5. Implementation challenges of coordinated multi-level governance are overlooked.

Novel/Surprising Points (3 points):

  1. Nearly half of all generative AI job postings in 2022 were in just 6 metros.
  2. AI job concentration increased over the past decade despite assumed diffusion.
  3. Specific policy tools like the BBBRC and NAIRR are presented as decentralization vehicles.

Leave a Reply