The Lindahl Letter

Greetings, readers and avid listeners and technology enthusiasts! You're either reading or tuned in to the audio-only podcast of The Lindahl Letter, now in its 154th week. Remember, an extra fresh and original edition lands in your inbox every Friday. Now certified with a three year proven track record. Today, we delve into an intriguing theme: “My 2024 Predictions.” Let's explore the future toget...

Please accept this note of gratitude for being a part of this journey. We made it. Some of you have been a part of the entire journey. Three years ago on January 26, 2021, this very Substack started rocking and rolling along a weekly journey to share research notes. My backlog of weekly items to cover is still pretty darn larger. It contains well over 100 blocks of potential writing content. A few...

Maybe a longer title for this post could be, “Bayesian Models and Elections: A Dive into the Dance of Uncertainty.” This is the 150th transmission of the Lindahl Letter. In the vast and often unpredictable theater of electoral forecasting, the quest for precision is a relentless pursuit. The choreography of voter behavior is a complex ballet, orchestrated by a myriad of factors—societal tremors, e...

Title: The Confluence of Agent Systems and Expert Opinion in Election Simulations In the ever-evolving landscape of political science and technology, curiosity often paves the way for innovative approaches and fresh perspectives. Recently, a wave of curiosity has washed over me, primarily centered around the exploration of diverse agent systems to simulate elections. This intersection of technolog...

Let’s get to work unpacking the Delphi Method & Door-to-Door Canvassing. This is the Substack deep dive you don’t want to miss. Hey there, dear weekly Substack readers! Today, let's embark on a journey through two fascinating potentially election related realms: the Delphi Method and Door-to-Door Canvassing. While these two concepts might seem worlds apart, there is a curious intersection between...

Don’t panic, the Google Scholar searches are coming in fast and furious on this one [ 1 ]. We had a footnote in the first sentence today. Megan Tomlin writing over at neo4j had probably the best one line definition of the difference by noting that knowledge graphs are going to be in the human readable data camp and vector databases are more of a black box [ 2 ]. I actually think that eventually on...

After the adventures of last week, I started this writing adventure wanting to try to figure out what people were doing with LangChain and social media. People are both generating content for social media using LLMs and oddly enough repurposing content as well. We have to zoom out for just a second and consider the broader ecosystem of content. In the before-times, people who wanted to astroturf o...

And now it’s time to pivot toward the “Learning LangChain” topic… The most fun introduction to LangChain seems to be from DeepLearning.ai with Andrew Ng and Harrison Chase [ 1 ]. You can expect to spend a couple of hours to complete the process of watching the videos and absorbing the content. Make sure you use a browser window large enough to support both the jupyter notebook and the video. You a...

You can feel the winds of change blowing and the potential of people building out election expert opinion chatbots. Maybe you want to know what they are probably going to use to underpin that sort of effort. If you were going out to build some generative AI chatbots for you might very well use one of the 5 systems we are going to dig into today. * Voiceflow - This system may very well be the most...

Sometimes a simplified model of something is easier to work with. We dug into econometric models recently during week 136 and they can introduce a high degree of complexity. Even within the world of econometrics you can find information about proxy models. In this case today we are digging into proxy models for elections. My search was rather direct. I was looking for a list of proxy models being...

This might be the year that I finally finish that book about the intersection of technology and modernity. During the course of this post we will look at the intersection of machine learning and election models. That could very well be a thin slice of the intersection of technology and modernity at large, but that is the set of questions that brought us here today. It’s one of things we have been...

We have been going down the door of digging into considering elections for a few weeks now. You knew this topic was going to show up. People love prediction markets. They are really a pooled reflection of sentiment about the likelihood of something occuring. Right now the scuttlebut of the internet is about LK-99, a potential, maybe debunked, maybe possible room temperature superconductor that peo...

Trying to figure out how many republicans, democrats, and independents are registered in each state is actually really hard. It’s not a trivial task. Even with all our modern technology and the extreme power of the internet providing outsized connectedness between things and making content accessible to searches. Even GPT-4 from OpenAI with some decent plugins turned on will struggle to complete t...

It has been a few weeks here since we started by digging into a good Google Scholar search and you know this topic would be just the thing to help open that door [ 1 ]. My searches for academic articles are always about finding accessible literature that sits outside paywalls that is intended to be read and shared beyond strictly academic use. Sometimes that is easier than others when the topics l...

I read and really enjoyed the book by Nate Silver from 2012 about predictions. It’s still on my bookshelf. Strangely enough the cover has faded more than any other book on the shelf.  Silver, N. (2012). The signal and the noise: Why so many predictions fail-but some don't . Penguin. That book from Nate is sitting just a few books over from Armstrong’s principles of forecasting. A book that I have...

Last week we started to mess around with some methods of doing sentiment analysis and setting up some frameworks to work on that type of effort. This week we take a little different approach and are going to look at an election model. I’m actively working on election focused prompt based training for large language models for better predictions. Right now I have access to Bard, ChatGPT, and Llama...

I’m still spending some time digging into notebooks. This time around the topic as you might have guessed for that inquiry is figuring out how to automate a survey or more pointedly some sentiment analysis. People are building automated phone surveys with interactive voice response (IVR) systems. The next wave of this technology will be hard to tell if it is a person or a bot. Seriously, those sys...

Thank you for tuning in to this audio only podcast presentation. This is week 132 of The Lindahl Letter publication. A new edition arrives every Friday. This week the topic under consideration for The Lindahl Letter is, “Synthetic data notebooks.” People are totally working on this one actively which I thought was pretty interesting. I have a general interest in how to create synthetic data using...

We are not to the point where some AI agent is going to be able to do this type of bulk image improvement by a verbal command. I really wanted to be able to just say, “ok computer, edit the photos in this folder to improve them and ping me when you are done.” This use case will probably show up at some point, but now is not that point in the timeline. The future of this type of computer usage is c...

We are getting closer and closer to the world envisioned in Star Trek and countless other science fiction universes where you could just ask the computer to complete some sort of task or build for you. We are starting to see what would be like an AutoGPT or a plugin style version of ChatGPT with agents that work to complete some sort of request. It’s not like they have a full built in chron system...

Working out of notebooks is an easy and lightweight way to just mess around with code. One of my all time favorite ways to go about doing that is in the Colab research space provided by the team over at Google [ 1 ]. They have an offering for a pro subscription, but you can get in and use things without a payment plan. Sure the promise of faster GPUs, more memory, and longer runtimes is enticing....

The topic for this week was a weighty one for sure. It’s one that I think will functionally happen, but I do not believe will be real in terms of actual practice. We are seeing a lot of emphasis on using these new AI systems that are popping up everywhere. People are not able to build these systems from scratch anymore. Using code from somebody else is becoming more and more a part of the process....

Things have been happening with Google DeepMind. A lot of news has been dropping since I started crafting this post. I don’t want to write about the news of the moment on this one. The context and analysis within this post is going to try to be deeper than a base reaction to that recent news. The Verge (and a ton of other people) reported that, “Google’s big AI push will combine Brain and DeepMind...

Something is going to have to give here pretty soon for Hugging Face or they are going to get left behind by the extended model, plugin driven, and now internet connected GPT models that some of the biggest platforms are working to take mainstream. We are seeing the real time development creating extensibility into actions from companies like OpenAI and their partner Microsoft that are going to be...

Security professionals the world over are concerned about what people like some of Samsung’s engineers might be doing with OpenAI’s ChatGPT services [ 1 ]. Let’s back up just a bit from that very real breaking news security reality and make sure to set the stage. Instead of starting with a complete corporate history about OpenAI, you knew that I would go out and search Google Scholar to find some...