Mihai's page

Six months (and a few days) ago, a day after leaving Google, I was entering the OpenAI office for my orientation as a new hire.

This will be the last article about \(\pi\) for this year, but I could not miss today, given that \(\pi \approx 22/7\) and in most countries of the world today’s date is 22/7, the pi approximation day.

A week or so after publishing the previous article I observed an unexpected traffic pattern on my blog.

In the US and countries with a similar date format, today is the \(\tau\) day (\(\tau = 2 \pi\)).

At the start of the year I introduced my AI benchmark for 2026, or at least the first one I was planning to run.

It is the last hour of Pi Day (March 14th in the US is written as 3/141) and I can finally post the article about \(\pi\) that I was planning since the article about the 3 possible regular 2D tilings and getting these tiles into my math AI benchmark for 2…

Recently, I started using LLMs to answer some of my questions.

In the last article I introduced two different problems that I was curious how LLMs would answer.

Exactly a year ago, I started an AI competition where I tested multiple LLMs on several math problems, with various prompting guides.

Happy New Year!

At the start of December, I wanted to publish an article every day until Christmas, following the other “Advent of X” events.

LLMs can now write code 100x faster (or more).

One of the downsides of the LLMs right now is the amount of AI slop that is generated by them.

Because the way LLMs function, it is very hard for them to correct once they start going a wrong path (more recent models can look at the prompt multiple times and fix some of these, but in general the model can still hallucinate).

One of the things that took place in yesterday’s social media for me was the discussion around a 10,000$ bet between two DeepMind engineers, Marcus Hutter and David Budden (who left DeepMind to work on proving math stuff with LLMs).

Doing what’s best for the user, respecting their wishes, used to be the best approach to deliver software.

Software engineers don’t just crank out code, are not just machines to convert coffee into executables / web-apps.

More and more websites are pushing you to use their apps.

I already posted two separate articles on how to use math to do a better decision regarding conserving the in-game currency in Silksong, given that many players need a lot of attempts before they git gud.

The last linear algebra article ended just right after we introduced the concept of a matrix and justified why the matrix vector multiplication has the form it has.

No matter what will happen in the future, AI is here to stay.

In the first article of the “blog daily until XMass” series we got to a very simple expression linking the probability of dying on a runback to a boss and the best choice on whether to convert the rosaries (in-game currency) to necklaces (losing some valu…

In one of his latest videos, Matt Parker says Any sufficiently well explained mathematics is indistinguishable from being obvious.

A year or so ago I got shown a geometry problem involving 3 circles.

When releasing software, we need to also assign unique identifiers to each state that gets promoted to an artifact that others can use.

A stock grows by 20% in the first year and drops by 4% in the second year?

After introducing grids and linear algebra, it is time to merge both subjects into a single one: what can we say about linear algebra when we look at regular grids?

For this short article, as a stop gap before another one, I thought I would look at how the movement of a single particle (its kinematics) look like in a plot of speed versus position.

Think of any board game or a 2D computer game and most likely it involves a square grid somewhere.

This is going to be a financial analysis of a special investing instrument created by Romania.

If Leo Tolstoy were a mathematician, he might have written All zero vectors are alike; each non-zero vector is a vector in its own way What does this mean?

A few months ago, on one of the Discord servers I am in, someone mentioned that Rust might be asking for too much memory at runtime, compared to the equivalent C program.

Another short post for today: this time, we look at two geometry problems and how AI can solve them.

Today we also do a short post.

I am not doing Advent of Code this year.

Slightly more than half a year ago, I launched the AI puzzle competition: I selected 3 math problems and a common sense one and then looked at how OpenAI models, Gemini models, Claude models, Mistral models, Llama models, QwQ, and Deepseek perform on these

For the AI puzzle competition we have seen how OpenAI models, Gemini models, Claude models, Mistral models, Llama models, QwQ, and Deepseek perform on 3 problems, when using various prompt hints.

We are almost done with analyzing the results of the AI puzzle competition where we asked models to solve 3 problems with several prompt engineering strategies.

We are almost done with analyzing the results of the AI puzzle competition.

Let’s continue the AI puzzle competition.

In the past article from the AI puzzle competition series we looked at how Google models perform of the 3 problems, while two articles back we looked at the OpenAI ones.

In the past article from the AI puzzle competition series we looked at how OpenAI models perform of the 3 problems, comparing against different prompt engineering hints.

In the AI puzzle competition series, after talking about the problems and the prompts, it is time to look at the performance of some of the contenders.

Two days ago I introduced the AI puzzle competition, and yesterday we talked about the problems we will use to gauge the performance of the competing LLMs.

In the previous post I introduced the scaffolding for running a test on various LLMs where I give them several puzzles and prompt engineering hints to look at what helps them in reaching a solution, if ever.

At the end of last year I had a significant amount of OpenAI API credits which were set to expire by the end of the month.

One of the main components of GUAC is a graph database to store all the metadata pertaining to the software supply chain.

One question that I had for a long time was do the power profiles on a laptop have any real impact?.

After solving the limit from the first part of Visual Differential Geometry and Forms: A Mathematical Drama in Five Acts by Tristan Needham, we can now move on to the next part.

In the last section of a previous article I presented a limit that was given as an exercise in Visual Differential Geometry and Forms: A Mathematical Drama in Five Acts by Tristan Needham.