Supervising the Idea Factory: My Year of 60 Personal Projects
In 2024 I leaned on LLMs to get several personal projects done (around 20). This year I took that to 11 (60 projects).
mostlymaths.net
Recent content on mostlymaths.net
Latest posts
Arguably 3x productive: anecdata on LLMs for personal projects
If you have been following me on BlueSky or have read my recent posts here you will be aware I am a happy LLM user for coding projects.
Poets and Journalists
I use Gemini for coding, a lot. When I tell some colleagues, they look at me like I’m out of my mind. I believe their reaction reveals a fundamental split in how we see our craft: the difference between the Journalist and the Poet .
Test Driven Writing (or Test Driven Documentation)
During the writing (and rewriting) of my last two posts I had this idea: what if we could leverage LLMs for a closed-loop rewriting cycle?
In Practice: Turning an Idea into a Finished Project (A Case Study)
I got some questions about how exactly did I use Gemini when creating a project, after posting my previous post. This is the answer.
Turning 'Someday' Ideas into 'Today' Projects with Gemini
A year ago I didn’t think much of LLMs for coding. Just glorified autocomplete at best, useful but just that. I have partially changed my mind, although I didn’t realise what was the difference until recently.
World's most boring audiobook: German-English text-to-speech
A lot of my projects involve a great deal of I wonder what the result might look like . This one was not unexpected
Concept Maps helper
I am a big fan of Concept maps , but writing them in Graphviz is annoying. So I wrote a helper.
2023#01 Readings
I know, I have been silent for quite a while .
About me
Welcome! I’m Ruben Berenguel, the mind behind the writing here at mostlymaths.net. I have a PhD in Mathematics and work as a Site Reliability Engineer (Software Engineer) in Google Zurich. All the writing here represents (and has always represented unless explicitly stated in the post) my own views. I have a varied set of interests, that range from reliability and data engineering,β¦
2022#26 Readings πΊπ¦π»
There’s as a scarcity of themes for this edition: just (not counting miscellaneous stuff, sure) SRE and how to learn things
2022#25 Readings πΊπ¦π»
Had some stuff going on that ate all my available time.
2022#24 Readings πΊπ¦π»
Trying a cross between the old format and the new format (since there are people who like both)
2022#23 Readings πΊπ¦π»
If you are reading this as a subscriber, you’ll see some difference.
2022#22 Readings πΊπ¦π»
Feeling less tired this weekend.
2022#21 Readings πΊπ¦π»
Playing with stable diffusion on your own machine is great.
2022#20 Readings πΊπ¦π»
The stuff I have pending to read keeps increasing lately. Too much interesting material being written.
Project and task management with Obsidian and Dataview
This post is about how I manage my tasks and projects using Obsidian with the Dataview plugin.
2022#19 Readings πΊπ¦π»
Slowly, very slowly, cleaning up my reading list.
2022#18 Readings πΊπ¦π»
I have been busy . Hence the radio silence.
2022#17 Readings πΊπ¦π»
Slightly shorter because I’ll be on holidays.
The Presto paper
This is the next installment on my quest to read and help understand interesting papers in the data space.
2022#16 Readings πΊπ¦π»
Spent a week in Switzerland⦠and on the flight back caught COVID.
Ray: Another way to distribute work in a cluster
A new entry on the data papers series. Ray is a distributed framework for next generation AI applications . What does this mean? A scam? Blockchain on AI? Nah, it’s actually pretty cool, it has actors .
2022#15 Readings πΊπ¦π»
Shit ain’t gettin' better.
2022#14 Readings πΊπ¦π»
This has been a really tough week.
2022#13 Readings πΊπ¦π»
I was on J on the Beach , so skipped last weekend.
2022#12 Readings πΊπ¦π»
I took some days off for Easter, and I definitely needed them.
2022#11 Readings πΊπ¦π»
A middle-of-the-week one because it’s Easter and I may not write this during days off.
Apache Druid: analytical queries powered by magic
It has been a while since my previous data paper. This time I tackle a less known one.
2022#10 Readings πΊπ¦π»
Lorem ipsum dolor sit amet
2022#09 Readings πΊπ¦π»
This turned out a long one
Winning stakeholders' trust
Trust between business stakeholders and engineering (and data, analytics, operationsβ¦) teams is a tricky matter.
2022#08 Readings πΊπ¦π»
Meetings galore.
2022#07 Readings πΊπ¦π»
Π‘Π»Π°Π²Π° Π£ΠΊΡΠ°ΡΠ½Ρ! ΠΠ΅ΡΠΎΡΠΌ ΡΠ»Π°Π²Π°!
Templates for quotes and recurrent tasks in Obsidian
I have been using templates to add recurrent tasks to my daily journal in Obsidian.
2022#06 Readings
The dbt issue
2022#05 Readings
Next week I’m on holidays!
2022#04 Readings
RIP Michael (originally Marvin) Lee Aday, Meat Loaf π€
2022#03 Readings
Haven’t read much these days, but luckily I have not added much to the list either.
2021#02 Readings
Another week gone by, with a long list of readings seen pass.
2022#01 Readings
Happy new year!
Scriptable widget for Obsidian journal tasks
A bit of Sunday-inspired yak shaving
2021#27 Readings
Christmas edition!
2021#26 Readings
End of year cleanup, so a lot of goodies this time
Data pipelines with Alloy, Take 2
In which I write some easy Alloy code for a data model, with change over time.
2021#25 Readings
Back on track.
Docker replacements (particularly in Mac M1)
An unusual collection of links.
2021#24 Readings
This is a light edition.
2021#23 Readings
As usual, skipping an edition means a longer collection later on.