Hi Reader!

Whoa, it's been a while! After almost six months of not being able to write for the blog or this newsletter (more on that in the next post), you may have forgotten about A Happy PhD. To kickstart my own newsletter habit (and hopefully, your habit of reading it), here is a short one: a little nugget about how you can use AI to "talk to the blog" (or listen to it) about a certain topic... and a flashback to our classic end-of-year post. Do a yearly review, I'm doing one myself and enjoying it! :)

​

New Year's Special Flashback: Forget New Year's resolutions - Do a Yearly Review instead​

(Tweet-length gists of past posts, so that you don't have to read through the whole blog backlog)

The New Year is a great time to look back and reflect. It is also common to leverage the "fresh start effect" to make some improvements in our life. But, how to do this effectively?

​

Tiny Practice / AI Tip (also a new blog post): Create Your Topical “A Happy PhD AI Companion”

If you have been in this planet during the last year, you will have heard of “generative artificial intelligence” (GenAI) tools like ChatGPT. Like everyone, I have been dipping my toe in the ocean of GenAI tools to see how they could help my research and this blog (see an example here). For you trusty newsletter readers, here is an easy way of using AI that is both useful, (relatively) ethical, and blog-related.

The goal of this simple process is to have a little “AI companion” that digests, synthesizes and is able to respond to questions and give advice about “A Happy PhD” topics, in a way that is (hopefully) aligned with what we say in the blog, while citing the original sources in case you want to dig deeper into the blog’s posts. Google’s NotebookLM uses retrieval-augmented generation (RAG), allowing Google’s Gemini model to ground its responses in your provided documents (in this case, our blog posts on a specific topic).

Here is the step-by-step process to build such “A Happy PhD AI Companion”, on a topic of your interest -- say, doctoral dropout:

1. Go to https://notebooklm.google.com/ and log in with your Google/Gmail account.
2. Create a new NotebookLM.
3. Go to the blog’s tag page for your topic of interest, e.g., doctoral dropout (see the blog’s topics page).
4. In the “Sources” tab, add as sources the URLs of the posts that appear in the topic page in step #3 (yes, this is manual and a bit boring).
5. Enjoy asking questions to our blog posts (or getting an AI-generated podcast about them). Be mindful that it may make mistakes!

The tool can generate a quick summary of the whole topic with links to the different posts, and it can even generates a podcast-like audio with some of the posts ideas (which is a bit lame sometimes but not horrible). Sadly, you will not be able to insert there the full blog archive in this way. While NotebookLM’s 50-source limit might seem restrictive, it is known that specialized topic-specific uses of these AI models is often more effective.

Of course, you can also use this with other sources for your thesis, to help you wade through literature and a semi-infinite to-read pile. However, use it with care! Chatting with a paper-AI in this way is not the same as reading the actual paper (in terms of learning and understanding)! I would rather use it to prioritize a reading list, so that sources that appear central to your questions are read first.

Give this one a try, and let me know how that went and whether it helped you, by answering to this email. I’m really curious!

​

May you enter 2025 with renewed energy and attention!

​

Did this content help you? Hit reply and send us feedback (I cannot reply to all the emails we get, but I do read all of them), buy us a coffee, or help us spread the word! Forward this email to a friend you think may find this kind of advice useful. If you are reading this and you have not joined the newsletter yet, you can subscribe and get exclusive access to a worksheet to make the strategic plan towards your next dissertation goal, in the button below:

​