Approved Thoughts

Most books should have been blog posts, most blog posts should have been tweets and most tweets should never have been written. - Unknown Tweeter

Another set of AI-heavy links. I can’t help myself right now.

1. Set up a fake cricket league:

   These arrangements might have suggested that the league featured professional-grade cricket that an online audience would find worth watching, but in fact, the players weren’t established cricketers or even skilled amateurs. They were locals that Davda had recruited with the promise of paying 400 rupees (about £3.50) per day — twice what people in the area make in daily wages working on farms and for local businesses.

   Respect.

2. How to choose a religion (NYT Paywall):

   But for the general obligation imposed upon us all, as time-bound creatures in a world shot through with intimations of transcendence, a different Eliot line is apt: “For us, there is only the trying. The rest is not our business.”

   I didn’t know Eliot plagiarized The Gita. The book is called Believe: Why Everyone Should Be Religious. I hope to read this book.

3. I am (not) a Failure: Lessons Learned From Six (and a half) Failed Startup Attempts. I am a sucker for these stories, having a failed startup in my recent past. The conclusion conveniently helps me feel good about the failure.

4. Agency:

5. How to prepare for an AI future: Coincidentally, I ran into a number of pieces on this topic last week. The first one from Tyler Cowen and the second from Nate Silver. Both have the same advice in the first place: use LLMs more than you do and for more things than you do.

6. Using AI to build a nuclear fusor: Combining the wisdom of the previous two links.

7. Using AI to improve learning: I would love to see how the tutor was created. Perhaps I, too, need to take the advice from links 4 & 5 and do this project myself.

1. Why Is Homeowners Insurance Getting So Expensive? by Brian Potter via MR: A great piece objectively exploring a question getting a lot of coverage after the recent LA fires. There’s so much I love about this link. Original, deep analysis of an important question debunking the popular narrative (climate change, see next two links). Also, a great blog on Construction Physics? With 51K subscribers! Isn’t internet the best?

2. Gell-Mann Amnesia: First described by Michael Crichton and apparently nothing to do with Gell-Mann. He just gave it an important sounding name to have it taken seriously.

   Gell -Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray's case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward—reversing cause and effect. I call these the "wet streets cause rain" stories. Paper's full of them.

   In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.

   I should make a spaced repetition card for this.

3. Bjorn Lomborg: A good follow if you want to see less depressing news about climate change, for instance that polar bear population has been increasing since the 1960s or that the Great Barrier Reef is doing just fine. Do note that his work is also subject to Gell-Mann Amnesia.

4. Only reason I am posting this is because I am right now in the land of the great UFO scare of 2025, New Jersey. Trump appointed CIA Director? On Fox News? Former Texas Congressman? There should be an emoji for that. Here’s a palate cleanser (via Alex Tabarrok at MR).

5. Jokic. Watch till the end for the reaction.

6. Is it better to bribe Trump by purchasing his memecoin or his stock? Not financial advice.

No AI in the links at least, although I cannot confirm or deny if an AI was involved in the selection of these links.

Programming note: Since I am traveling for the next few weeks, some of those letters may only contain the links section.

This is the website in question. Bookmark it. Or don’t.

Many people are asking if this can even be called a website. These people are losers. Sad. The finest people I know think its a great website, maybe the best website in the history of the world. Nobody knows websites like I do.

Anyhoo.

It all began when I decided to shift this letter to a website last week. Having purchased a few web domains before, it took me only a few minutes to buy approvedthoughts.com from Cloudflare. Unlike GoDaddy etc. who offer a promotional price bundles and then jack it up on renewals, Cloudflare offers at-cost registration + renewals and I have good experience with some of their other services, so it was an easy choice.

For all my talk about using AI models, I hadn’t really used them for any type of programming project / tech support roles. I figured this was the perfect opportunity for me to try out if I could actually create something useful with the help of one of these models.

For context, while I have an undergraduate degree in Computer Applications, I have never programmed professionally and frankly did barely any programming during the course itself. I am probably a bit better than someone who has never done any programming, but not by a lot.

For context also, I could obviously just spend $20 on a paid service that would be absolutely trivial to set up and manage but where’s the fun in that?

This is how I started on Claude 3.5 Sonnet:

I have recently purchased a domain for a website. I used cloudflare for purchasing the domain. I would now like to set up a Wordpress or other website at the domain. Walk me through the steps of doing this.

The Sonnet is the “most intelligent model” by Anthropic. It is the go to model at the moment for a lot of the people I follow and the only model I pay for.

The project went through multiple chats because after a while, in each chat, I would start getting this message:

Here, for the first time, I used a trick I had recently seen (I think) on Twitter.

ok - I have saved and deployed on cloudflare. However I am getting the message that this chat has become too long. Can you provide a status update that I can use with another AI chatbot to continue this work?

And it did! I pasted the update in another chat and the conversation continued there as if it was the same chat!

You can check out the first chat [here. I think / hope it has no confidential information. I won’t be sharing the remaining chats because they do have some of my account credentials. This one should provide enough context for most of what I am discussing here though.

So How’d it Go?

Well you’ve seen the “website”, so clearly not as well as I’d hoped. That said, I am continuing with the project and based on what I have learned so far, I am hopeful I will eventually get it working.

It is still remarkable that I got this far, considering that I have zero experience with the technologies / services involved. Claude successfully walked me through setting up 3 different services (Cloudflare, GitHub and Hugo) and had them work with each other to serve up the site.

All of this happened within a couple of hours and with me blindly following its instructions - copying and pasting code where it asked me to, choosing the options it asked me to and only making high level decisions, like which theme I liked for the blog, which require no technical sophistication.

For the most part, all of this was “one-shot”, meaning it told me to do something, in plain English, I did the thing and it all worked. Where it required a second shot, it was because I hadn’t provided the full context e.g. that I was using a Mac and not a PC. And once I clarified that, it adjusted the directions for all subsequent steps.

In fact, because I use Claude almost exclusively, I had forgotten how much better it is that some of the other models at being almost “human”. This chat is not very different from how I would interact with IT support engineer at work. Just randomly dropping bits of context or asides and having it be incorporated correctly into subsequent interactions as relevant.

In one of the subsequent chats, it seemed to me like Claude was stuck or going around in circles, without fixing the problem, so I decided to switch to the newly launched DeepSeek-R1 reasoning model. While the R1 made immediate progress where Claude was stuck, the experience of working with the R1 was just so much harder.

Unlike Claude, which “understood” that I was not technically sophisticated, and only gave tasks of a manageable size at each stage, the R1 would just throw a laundry list of complex tasks at me.

For e.g. there’s a set of 3 commands I needed to run on the Terminal app on my Mac, after every change to the code. This would “push” the changes to GitHub. Every time there would be only minor changes to these commands. Claude would provide these commands every time, unprompted. R1 would not.

Claude also seemed to just understand better where we were in the overall project at all times. So if it asked me to do three things and if I went back with a question about the first thing, it would help me fix that and then go back to the remaining two items in the list. R1 did not seem to have as good an “understanding” of the overall project and did not seem to “appreciate” that if I was asking a question about step 2 of 5, that steps 3-5 still needed to be done after it answered the question about step 2.

Of course, the answer to step 2 would have 5 steps, so now I have to scroll back and forth to figure out which step of which step I am on. So despite being a “stronger” model, I found it discouraging and just much harder with the R1 to have to keep track of where we were in the project.

What went wrong?

I suspect the website would be looking a lot better if I had just followed Claude’s guidance. In fact, even now, I think it is at a stage where I can post these weekly updates there with some extra effort.

But I knew I was going to be traveling for a few weeks and so after the site was ready for me to start posting content, I asked Claude if we could also set up a CMS, content management system, for the website. That way I could post from anywhere instead of just from my desktop and include links and images in the posts with minimal effort.

Things went off the rails pretty much immediately. Without getting into a lot of detail, we encountered a bug while setting up the authorization setup for the CMS. Claude kept suggesting various tweaks but nothing worked. It felt to me like we were going around in circles, trying the same things over and over again.

I even asked Claude to look at the entire conversation and figure out if it was going around in circles. It gave itself a clean chit. Of the 6 or so hours I have spend on this project, my guess is 4-5 have been trying to resolve this issue.

My suspicion is that Claude is trained on an older version of the various services / projects I am using and therefore could not fix these errors.

Eventually I gave up with Claude and took the project over to DeepSeek R1. It made some progress, identifying some errors Claude had made, e.g. key files located in wrong folders, wrong parameters etc. However since neither of the models can really take over and look at the code themselves, they may not be able to fix issues caused by my mistakes in implementing their directions.

Maybe AI agents will fix this issue in future. In any event, the project is on pause as I travel and I am wondering whether I should start from scratch with DeepSeek instead of trying to fix the current version.

What did I learn?

A lot.

Despite the hiccup, I feel comfortable that these models can help me do projects that I just couldn’t have done before. I intend to try more projects, and of course, finish this one.

Different models have very different “skills” and it’s important to figure out which model is the best for a given task.

While Claude is the easiest to talk to, almost like a person, it really helps to understand how to prompt other models to get the best out of them. Providing more context and better instructions can result in much better results.

Larger context windows will change everything. A model that can keep your entire life in context will be multiple orders of magnitude more helpful than the current models.

I am a little more skeptical than before about LLMs becoming generally intelligent or superintelligent. Their ability to deal with problems that are not in their training data seems limited. Maybe agentic models will overcome some of this but breakthroughs in for e.g. fundamental physics seem unlikely. Obviously I am extrapolating from a tiny sample but that’s the direction in which I have updated my priors.

What’s next?

I have a few ideas I want to work on once (not if!) I finish the website. I wonder if I can set up a web server on my old Mac and run a few basic services off it. For e.g. creating a URL shortening service (like Bitly) or a QR code generation service.

This from Simon Willison is my inspiration. 14 projects in 1 week. No rocket science but just small, useful things here and there. Or, if I am more ambitious, that custom Spaced Repetition app built by Andy Matuschak, I mentioned couple of weeks ago.

Is truly customized software possible? I hope it is.

Having done a throat clearing piece the first week and the one writing idea I actually had when starting the newsletter, the second week, this week I was finally forced to think about the direction I want to take with this letter.

I enjoyed heading down the rabbit hole of how to learn better last week. I already knew that there was much I needed to learn about teaching after struggling to homeschool the boys for a year recently. Last week it also became clear that I also had to learn a lot about learning.

As it happens, this is also a space where a lot is changing (yes, AI, duh!) and one that is even otherwise relevant to me given the presence of two (reluctant) learners that I am (even more reluctantly) trying to support.

So it seemed like a natural beat to walk.

I subscribe to a few Substacks and as I trawled through them I realised that the only reason I subscribed to each of them was because they were written by experts who also happen to have an amazing way with the words. Here’s a sample:

1. Money Stuff by Matt Levine - GOAT of newsletters. It’s not even close. And daily? Get outta here…

2. Don't Worry About the Vase by Zvi Mowshowitz - I can’t believe it’s free.

3. Bits about Money by Patrick McKenzie (Patio11) - How is a software engineer teaching me about my job?

In other words, I have a very high bar for who I let into my inbox. I could write about how to learn better but clearly I am not the preeminent expert on the topic, I am barely getting started. It would be hard for me to clear my own bar for quite some time, if ever. And if I am going sustain this, I need to enjoy what I am doing. I need to be able to experiment, make messes and generally figure things out.

It occurred to me that a better medium for that kind of a goal might be a website rather than spamming people in their inboxes. It will give me the freedom to play around with the format, topics, content & timing and make the aforementioned messes without worrying too much.

Now my wife thinks I am trying to wiggle out of my New Year’s resolution with this talk, but frankly, she barely knows me, so we can safely ignore that possibility.

So here’s the plan: I will continue writing here on a weekly basis till the website is setup and then move everything over there.

1. This feels accurate. 😅. He says AGI but looking at the next link I wonder if this is true for plain old AI.

2. Two weeks ago, it was Will Smith eating pizza. Now its this. Click the link to see the video. WhatsApp University is about to go nuts.

3. She Is in Love With ChatGPT (NSFW. NYT Paywall.) And you thought K-Dramas were stealing your spouse.

4. The Serendipity Machine or how to use Twitter better. A few years ago I implemented a simple algorithm on my twitter feed:

   a. Block everyone who talks about politics and

   b. Block everyone who is is dissing / attacking anyone / anything.

   In less than a month my feed stopped being the anxiety inducing, doomscrolling nightmare that it was and transformed into the best source of learning & inspiration on internet. This piece takes you to the next level.

   Committing to writing this newsletter has also been great. Now instead of mindlessly flicking my finger and consuming, I have a purpose every time I open Twitter. Its almost energising to engage actively with each tweet, thoughtfully considering whether its fit to be served to my exceptionally smart and good-looking audience.

5. E(X)>0: An Open Letter to Elon:

   “Your top engineers and programmers are only able to work 80-hour weeks because they can hire nannies and maids, ride in Ubers, and order food delivery. High-skill productivity depends on an abundance of complementary low-skill productivity.”

   As a repeat immigrant, I have many thoughts on this debate going on in US right now. There’s a lot that is wrong with a policy of focusing exclusively on so called Skill or Merit based immigration. This piece from Bryan Caplan makes some good points.

6. The War for India: I am enjoying this talk by Prof. Sarah Paine of the Naval War College. She talks about the history of international conflict and politics in South Asia and the role to US & Russia. I did not know that India supported China’s bid for a permanent seat on the UN Security Council. 🤯 😱

7. Better ways to wear a Polo: Always a pleasure to see a master in action.

“…networking conferences where there’s plated cantaloupe.” chef’s kiss.

Here’s another one from Derek:

8. Fix Your Glutes. (NYT Paywall) Strongly endorse. Really helps when trying to hold a fart but many other benefits too.

   My frail-as-porcelain glutes — the cluster of tissue from hip to thigh tasked with keeping the body upright and on occasion propelling it forward — were causing a domino chain of damage, and had most likely been doing so for some time. To compensate for the glutes’ infirmity, my ankles, knees, hips and even my shoulders and arms had to thrash madly, taking on vast and uneven amounts of pressure, often far more than they were structurally fit to bear

   and

   Only after I started remedying my “gluteal amnesia” (real medical term) did it become clear how little I knew about basic affairs like walking, standing and sitting (or living, for that matter). Within a week of the mandated twisting and shimmying and clam-shelling, my spine was noticeably straighter, smoother. Four weeks later and I could finally walk without pain again. It took three months more to fully rebalance my loopy musculature and break into a manageable jog — but when I did, I noticed a wondrous new power to each step and spring. My reawakened haunch muscles were doing their job.

   For the last two months, I have been doing a core workout formulated personally for me by (who else?) ChatGPT, with a special focus on glutes and I can feel the difference, not just in my ability, but my willingness to do things. Core strength is underrated and it isn’t just about the abs. You can have a six-pack and a weak core. I happen to have one of those.

That’s it for this week. It seems like my writing and links are all AI all the time but that isn’t the intention. However it is a space where a lot of fun stuff is happening right now and so that’s the path of least resistant.

I will be on the road for the next few weeks so programming may be light. Hopefully the website will be ready soon.

What is Spaced Repetition (SR)?

Claude says:

Spaced repetition is a learning technique that involves reviewing information at gradually increasing intervals. Here's how it works:

When you first learn something new, you review it fairly soon (like the next day). If you remember it well, you wait a bit longer before the next review (maybe 3 days). If you still remember it well, you extend the interval further (perhaps a week, then two weeks, then a month).

The key principles behind spaced repetition are:

1. The spacing effect: Information is better remembered when studying is spread out over time rather than crammed into a single session.
2. The testing effect: Actively recalling information strengthens memory more effectively than passive review.

This may not sound revolutionary. After all, some version of this is how we prepared for our exams. But the important thing is that unlike the 90s, there’s an app for that (Anki, Mochi & others). The app handles the spacing and repetition, making it more practical, reliable and scalable.

When I first learned about and used SR apps years ago, I thought, “Wow! It would have been great to have this in school. This will be great for the boys in a few years.”

I never used the technique until last year when I used Anki for homeschooling the kids in Hindi. You can get many ready-made decks (free & paid) on the Anki website, but creating your own (necessary for specific requirements) was a chore, and I stopped after a few months.

I thought SR was for students until I saw a Dwarkesh Patel podcast with Dan Shipper using it to learn more broadly. It wasn’t limited to coursework or vocabulary but included concepts. He claims it allows for better understanding of linkages and patterns over time.

But what had my jaw drop was that he used Claude / ChatGPT to create the cards! Of course. Just throw in the material you are learning into Claude, ask it to create SR cards for the material and you’re done.

It may need some editing or creating additional cards, but it’s generally good enough. It can even output in Anki file format. Rope in an AI and the amount of knowledge you can include in your SR system just explodes.

While researching this piece, I revisited Alexey Guzey’s original post that introduced me to the concept. I didn’t remember this, but the first thing he talks about is to use SR for instilling novel thought patterns.

Front card: saying no

Back card: If I want to say no, I will stop and make sure this is not just status quo bias (coz it probably is)

Status quo bias sucks. Does this one solve it? Beautifully so. Although several months had passed before it finally kicked in, the number of times I noticed saying “no” out of status quo bias, then having this thought come up and make me retroactively reverse the initial “no” is in the tens already.

Will this work? I am not sure, but between how Dwarkesh is using SR and this, I feel the case for having my own SR system is growing stronger. Hopefully, I’ll have an update in a few weeks.

How do you train?

Tyler Cowen’s post inspired by David Perell planted another bug in my brain.

“Athletes train. Musicians train. Performers train. But knowledge workers don’t.”

Recently, one of my favorite questions to bug people with has been “What is it you do to train that is comparable to a pianist practicing scales?”

If you don’t know the answer to that one, maybe you are doing something wrong or not doing enough. Or maybe you are (optimally?) not very ambitious?

Here’s his answer. Of course, I didn’t know the answer to that one.

Watching Andy Matuschak study Quantum Mechanics with Dwarkesh Patel (who else?) led to a few realisations.

Having the right tools and workflows and being good at them is a huge productivity unlock. In the video, Andy uses custom software that allows him to do much more, faster. He reads, creates SR cards, and reviews material on the fly.

He also knows how to put mathematical symbols in his notes, making useful cards so much more quickly.

What is the difference in learning between someone manually revising from a textbook before an exam (as I used to do) and someone using a custom SR system, AI-generated SR cards, and a workflow to push those cards daily? Huge.

This year, I plan to practice getting better with the keyboard. How long can I work on my desktop without touching the mouse? To switch between windows and apps, and use functions within apps?

Sure, I can do Ctrl + C and Ctrl + V. But can I effortlessly do Alt + E + S + V + F (Paste Special > Formulas in Excel)? Can I do 50 other menu actions across multiple programs? Can I set up workflows for routine processes and use AI to automate?

The second thing that struck me was the depth of his learning approach. Sure, it’s a tough topic, but he spent 20+ min on the first page, asking questions, drawing connections, testing himself, and revising. I don’t recall engaging with my coursework so diligently.

The last thing that occurred to me is how important and hard it is to learn these hacks/tricks/workflows. Some people just know and others never do.

Here’s a great resource for this “tacit knowledge.” I’m glad someone recognised the importance of the concept, named it, and created a knowledge base.

1. Reflections - Sam Altman:

   We are now confident we know how to build AGI as we have traditionally understood it. We believe that, in 2025, we may see the first AI agents “join the workforce” and materially change the output of companies. We continue to believe that iteratively putting great tools in the hands of people leads to great, broadly-distributed outcomes.

   We are beginning to turn our aim beyond that, to superintelligence in the true sense of the word. We love our current products, but we are here for the glorious future. With superintelligence, we can do anything else. Superintelligent tools could massively accelerate scientific discovery and innovation well beyond what we are capable of doing on our own, and in turn massively increase abundance and prosperity.

   This sounds like science fiction right now, and somewhat crazy to even talk about it. That’s alright—we’ve been there before and we’re OK with being there again. We’re pretty confident that in the next few years, everyone will see what we see, and that the need to act with great care, while still maximizing broad benefit and empowerment, is so important. Given the possibilities of our work, OpenAI cannot be a normal company.

   Emphasis mine. Those are tall claims. More from Zvi here.

2. How to grow a $3tn market cap? - John Gruber. When You Search for ‘Google’ on Bing, Bing Attempts to Trick You Into Thinking the Results Page Is Google. Don’t know if I should laugh or cry.

3. Having spent more time on LinkedIn last year than anyone should ever have to, I fully endorse this advice. via Shaan Puri.

3. It’s the Most Indispensable Machine in the World—and It Depends on This Woman - WSJ (Paywall). One can never get enough of ASML:

   Brienna Hall has the most valuable role that you’ll never see at the most vital company that you’ve never heard of.

   Until she began working at ASML last year, she didn’t know the first thing about the company. She also didn’t know what she would be doing as a customer-support engineer—a “fancy mechanic,” as she calls herself.

   It’s the machine that produces the most advanced microchips on the planet. It was built with scientific technologies that sound more like science fiction—breakthroughs so improbable that they were once dismissed as impossible. And it has transformed wafers of silicon into the engines of modern life.

   Even today, there are only a few hundred of these EUV machines in existence—and they are ludicrously expensive. The one that Hall maintains cost $170 million, while the latest models sell for roughly $370 million.

   But maybe the most remarkable thing about these invaluable machines is that they’re all made by the same company: ASML.

   ASML is the glue holding the chip business together. That’s because this one Dutch company is responsible for all of the EUV lithography systems that help make the chips in so many of your devices. Like your phone. And your computer. And your tablet. And your TV. Maybe even your car, too.

   These machines have become indispensable. And they depend on the invisible work of Brienna Hall.

   Truly a case of following the previous tweet’s advice. Brienna Hall still has a LinkedIn profile, but I give it another 18 months at most.

4. Meta announcements. If you’ve been hiding under a rock and missed this on the airwaves. Not much to add but Zuck knows how to nail a pivot.

1. How to be More Agentic by Cate Hall - Staying with the new year resolution theme… as the twitter meme goes, you can just do things.

2. Life Without Stars: Stanets and Ploons by Julian Gough - Could most life in the Universe exist without stars, in the deep oceans on icy moons of large planets?

3. How to do the jhanas by Nadia Asparouhova

4. Will Smith eating spaghetti - the pace of progress in AI is mind boggling.

5. How Dwarkesh Patel uses AI a podcast by Dan Shipper - Also subscribe to Dwarkesh’s podcast if you don’t already.

6. A Tutorial on Teaching Data Analytics with Generative AI by Robert L. Bray

The last two are a great if you are thinking about how to incorporate Generative AI in your work or life.

A hack I learned recently is anytime I have a question I am too embarrassed / worried / lazy to ask the right person or even google for, I just ask Claude or ChatGPT. Here are some examples of questions that would have gone unanswered but for the chatbots.

A piece I was reading mentioned that Starlink’s low earth orbit satellites have a useful life of 5 years. I wondered what happens to them afterwards. Sure I could have googled that1 and probably found the answer somewhere in the top 3 links2. But having the bot answer your exact question has a lot less friction than doing that and I find I am asking a lot more of these questions.

I recently started reading Cloud Atlas by David Mitchell, apparently a modern classic. After the first 10 pages I was really struggling to understand what was going on and ordinarily I would have just dropped the book.

Instead, I asked Claude “I am reading the book Cloud Atlas. I am struggling to understand the theme through the first few pages.” I got this response: “The book is structured in a unique way, with six nested stories that span different time periods and genres. Each story is interrupted halfway through, only to be concluded in reverse order in the second half of the book.”

No risk of spoilers and I suddenly felt more comfortable navigating the book.

Claude has already changed my mind on multiple questions and I am sure will keep doing so. I hereby declare 2025 the year of asking more questions.

Did you know that (in iOS at least) this button allows you to dictate text? I used to think it was to send a voice message (don’t do that) but no, this types it out and does a pretty good job of it too. This deserves to be used a lot more.