friggeri

I’m beta testing a small abstract strategy game I invented and for which I trained an alphazero style AI, https://span.game

I’m making a baby book for my son Henri featuring famous Henri’s through history.

I’m also building a zigbee free/busy eink display that only needs to powered once a year or so

I stopped drinking 8 or 9 years ago, and I haven’t missed it. Not that it ever was a problem, I enjoyed a glass of wine or a cocktail every now and then, but I was training for an ultra marathon and figured I’d stay dry while I trained for a couple of months. Had a glass of wine a few days after the race and felt completely hammered, at which point I realized if I wanted to drink again I’d have to “train” my body for it, and thought that was totally backwards. I haven’t found any situation where an alcoholic drink can’t be replaced by a glass of water, an NA beer or a mocktail. I’m also very lucky to be married to a wonderful woman who arrived to more or less the same conclusion and we enjoy being the boring ones who don’t drink (but never get a hangover).

I’ve been training an alphazero style model for an abstract strategy game I created 20 years ago. It’s been really fun learning about MCTS and figuring out how to optimize all parts of the pipeline to be able to train on ~millions of moves for ~hundreds of dollars.

I grew up in France and started smoking before age 15, and was a heavy smoker (1 pack a day) until I quit when I was 27 after moving to the US. Getting out of an environment where smoking was normalized is what helped me take that step.

Smoking is terrible in that it really messes with your brain, you intellectually know all the reasons why you should quit but it’s so easy to put it off. “I can quit whenever, I just don’t want to”. Until you try and get that gnawing yearning feeling.

It took me a solid year to not feel that way all the time. And another two to not feel that when having a coffee/glass of wine/standing next to someone else smoking.

13 years later I’m completely over it, to the point where I can barely tolerate being in the vicinity of someone smoking. And yet I often have dreams where I light a cigarette.

If you’re thinking of quitting, there is no better way than today. It’s likely going to be hard, but it’s one of the best things you can do to yourself. You already know that of course, but hopefully this helps.

https://friggeri.net

non tantum … sed etiam …

Looking at the prompts op has shared, I'd recommend more aggressively managing/trimming the context. In general you don't give the agent a new task without /clearing the context before. This will enable the agent to be more focused on the new task, and decrease its bias (if eg. reviewing changes it has made previously).

The overall approach I now have for medium sized task is roughly:

- Ask the agent to research a particular area of the codebase that is relevant to the task at hand, listing all relevant/important files, functions, and putting all of this in a "research.md" markdown file.

- Clear the context window

- Ask the agent to put together a project plan, informed by the previously generated markdown file. Store that project plan in a new "project.md" markdown file. Depending on complexity I'll generally do multiple revs of this.

- Clear the context window

- Ask the agent to create a step by step implementation plan, leveraging the previously generated research & project files, put that in a plan.md file.

- Clear the context window

- While there are unfinished steps in plan.md:

-- While the current step needs more work

--- Ask the agent to work on the current step

--- Clear the context window

--- Ask the agent to review the changes

--- Clear the context window

-- Ask the agent to update the plan with their changes and make a commit

-- Clear the context window

I also recommend to have specialized sub agents for each of those phases (research, architecture, planning, implementation, review). Less so in terms of telling the agent what to do, but as a way to add guardrails and structure to the way they synthesize/serialize back to markdown.

In the last 50 years, software has morphed from a hobbyist pursuit, to a nerdy subculture, to a trillion+ dollars industry. This has caused a pretty significant mix shift in the software developer community: the reason driving the mean developer into this field in 2025 is very different from that of the 2015 developer, and that of the 2005 developer.

Arguably there might be more curious tinkerers nowadays, but they might represent a smaller slice of the pie.

This is awesome! I’ve been working on and off for the last few months on an AI running coach app. Would love to compare notes of effectively prompting Claude or O3 to analyze workouts / build workout plans. In my experience it still requires a lot of hand holding (sudden mileage increases w/w, inconsistent intervals, etc)

I wanted something minimalist but high contrast, and enough variety so charts would not be repetitive. I have a thing for data visualization, so I pulled inspiration from the pile of books I have on my bookshelf.

That was a bug :)

Those are called "tile grid maps", I got the template for the world one here: https://policyviz.com/2017/10/12/the-world-tile-grid-map/

It’s changed over time: I first used MapMyRun with my iPhone, then switched to Strava on the iPhone, then got a garmin, and nowadays an Apple Watch. I’m super grateful for Strava to exist, if only as a repo of all my workouts.

Unfortunately my treadmill runs don’t have GPS data associated with them. Austria, PR and Hawaii were places where I ran mostly in the gym.

This being said, Sweden is a fun one: I was in Copenhagen for a few weeks and I thought it’d be fun to take the train to Malmo, do my long run, and then take the train back. All that to say, I’ve spent 3h30 in Sweden, 3h05 of which I was running.

Shanghai was an overnight layover.

Having experienced them, those runs were surprisingly not awful. In such cases I’ll jog a very slow mile, paying really close attention to what my body tells me (if I can walk, I can shuffle a mile or so). If anything, the act of getting out of the house and accomplishing something has more than once given me a morale and energy boost while sick.

The actually awful runs I’ve had are more of the "type 2 fun" kind (running in the desert, grueling trail runs), or the occasional hungover run before I quit drinking.

I’ve been lucky to never have any real knee issues. The only period I ended up with a little knee pain was because of a poor running shoe choice, and it resolved when I got properly fitted and changed shoes. Hope you figure out the source of your troubles!

Not AFib thankfully, I had a few sporadic SVTs while running (it’s however unclear whether exercise was the original cause, or if it was congenital and started manifesting while running).

Thankfully the ablation took care of them and I haven’t had an episode in a few years.

Like others said: take it slow, invest in the long term, and most importantly learn to listen to your body. Best of luck in your journey!

Congrats, that’s an amazing milestone!

Jogging a slow mile is pretty much "a day off" these days

I haven’t been to Australia, but I’ve run in Hawaii, which is part of Oceania (broader than just Australia).

Definitely a bug, will fix tomorrow, thanks for catching!

I haven’t aggregated the trend over time, but my resting HR has definitely decreased, I’m roughly around 40bpm at the moment, down from ~60bpm 10 years ago.

Unfortunately I ended up winging the data processing, so it was mostly a pile of adhoc scripts. The incremental update pulling from the Strava API is a little cleaner, but would require significant work to open source.

The only thing I ever really cared about was keeping the streak going, everything else has come second. I dropped out of a trail running trip after a fall because I felt that even though I could continue, putting too much mileage on my knee would jeopardize the streak.

I thought about it last week, was pretty quick to hack together!

I loved loved running in Japan, such a wonderful country

At first it was all about the challenge of doing one more day.

After about two years the streak became part of my identity, which might sound a little unhealthy. It’s easier to just head out and jog a mile or two than to let the number go back to zero.

This being said, it’s made for interesting conversations with medical professionals – I needed a cardiac ablation a couple of years ago and my electrocardiologist came to an “agreement” (as in she didn’t forcefully dissuade me from doing it) that I could jog a slow slow slow mile late in the evening the day after the procedure, as long as I kept my heart rate down and I made sure I was being mindful of my puncture sites.

I've had the absolute opposite experience, AI has brought back a lot of the joy of programming and building products for me.

I've been using Cursor extensively these past few months, for anything ranging from scaffolding to complex UIs. The trick, I've found, is to treat the AI like I would work with a junior engineer, giving in concrete detailed tasks to accomplish, breaking the problem down myself into manageable chunks. Here are two examples of little word games I've made, each of them took all in all a couple of days to ideate, design and build.

https://7x7.game You're given a grid and you need to make as many words as possible, you can only use the letters in the bottom row. There's complex state management, undo, persistent stats, light/dark modes, animations. About 80-90% of the code was generated and then manually tweaked/refactored.

https://vwls.game Given 4 consonants, you have to generate as many words as possible. This is heavily inspired by Spelling Bee, but with a slightly different game mechanic. One of the challenges was that not all "valid" words are fun, there are a lot of obscure/technical/obsolete words in the dictionary, I used Claude's batch API to filter down the dictionary to words that are commonly known. I then used cursor to generate the code for the UI, with some manual refactoring.

In both cases, having the AI generate the code enabled me to focus on designing the games, both visually and from an interaction perspective. I also chose to manually code some parts myself, because these were fun.

At the end of the day, tools are tools, you can use them however you like, you just need to figure out how they fit in your workflow.

One piece of advice I usually give is to avoid applying to jobs through company’s career websites or LinkedIn. Instead, tap your social network: see if there is someone you know/have worked with who either works at the company you’re interested in or is connected to it someone (as an advisor, investor, personal friend of someone in a leadership position) and ask them for a warm intro. Social proof gives you an advantage over the legion of anonymous online applicants.

Apologies for the misunderstanding, I just caught the typo, should have read "ala wordle", not "aka wordle", the game is fully original.

Using AI enabled me to spend more time thinking about game mechanics.

I recently started using Cursor for all my typescript/react personal projects and the increase in productivity has been staggering. Not only has it helped me execute way faster, similar to the OP I also find that it prevents me from getting sidetracked by premature abstraction/optimization/refactoring.

I recently went from an idea for a casual word game (aka wordle) to a fully polished product in about 2h, which would have taking me 4 or 5 times that if I hadn’t used Cursor. I estimate that 90% of the time was spent thinking about the product, directing the AI, and testing and about 10% of the time actually coding.