Everything I publish, in the order I published it: dispatches from Twitter, videos from YouTube and notes from my vault, archived here in full — text, images, video and links — so they outlive the platforms.
I fixed my YouTube feed by (rigorously) using the "Do not recommend videos from this channel" for a month.
Just a heads-up: It felt like strangling a beast. For the first rounds your feed cleans up quickly but then their algorithm fights back with even shittier, top-of-bell-curve slop that you had initially.
You gotta keep blocking channels until suddenly the feed stays clean and tight.
we’re using local apple intelligence models a lot these days in our product for a lot of little things & they work incredibly well, especially for personalization & copy.
you can cache these so you create a pretty lovely little experience in subtle places where the app feels tailored than just one to many (all for free!).
it’ll feel cool as hell when they get even smarter.
@signulll Loved futzing around with Apple's 3B Foundation Model!
Got it to ~ rubric parity with Sonnet 4.6 via autoresearch ->
@karpathy PS: To make this a bit more understandable. Basically we started with all dots red 🔴, created a training set, tried 81 different memorization techniques and landed on all dots green 🟢 t.co/eBWOTNaADd
@karpathy PPS: So thaaaaat... While up in the sky, we can take an in-flight camera frame like zis here and get a location fix like zat back.
YO! I just completed my fourth @karpathy autoresearch-inspired project called "Beeline". It's sort of a prototype for "GPS without GPS" for UAVs.
Claude and I iterated through 81 ideas and found a small neural thingy that can be trained to recall 96% of locations, given satellite images to train on and then a camera frame to remember latitude and longitude for.
Basically:
1. Train: Here are all tiles and their latitude/longitude, remember them
2. Infer: Here's a live frame from my camera. Where am I?
Claude for experiment design and implementation, me for research cybernetics.
My favorite part is that the resulting artifact (the .onnx model that represents the memory of spot and lat/lon) is intentionally custom-built for the defined geo-fence and thus the research harness had to embrace overfitting for this one specific case as a feature, not a bug.
The biggest suprise was that in order to break-through the 75-long experiment plateau, I had to fix the harness, not the loop.
And of course, this is a personal research project, so a bunch of limits apply. Such as training only happened on day-time pictures and the training set is bound to a geo-fence and more.
But hey! It's invented and built completely from scratch, so no dependencies on domain-libraries which means it's all GPL-licensed, too!
@karpathy PS: To make this a bit more understandable. Basically we started with all dots red 🔴, created a training set, tried 81 different memorization techniques and landed on all dots green 🟢
YO! I just completed my fourth @karpathy autoresearch-inspired project called "Beeline". It's sort of a prototype for "GPS without GPS" for UAVs.
Claude and I iterated through 81 ideas and found a small neural thingy that can be trained to recall 96% of locations, given satellite images to train on and then a camera frame to remember latitude and longitude for.
Basically:
1. Train: Here are all tiles and their latitude/longitude, remember them
2. Infer: Here's a live frame from my camera. Where am I?
Claude for experiment design and implementation, me for research cybernetics.
My favorite part is that the resulting artifact (the .onnx model that represents the memory of spot and lat/lon) is intentionally custom-built for the defined geo-fence and thus the research harness had to embrace overfitting for this one specific case as a feature, not a bug.
The biggest suprise was that in order to break-through the 75-long experiment plateau, I had to fix the harness, not the loop.
And of course, this is a personal research project, so a bunch of limits apply. Such as training only happened on day-time pictures and the training set is bound to a geo-fence and more.
But hey! It's invented and built completely from scratch, so no dependencies on domain-libraries which means it's all GPL-licensed, too!
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Infinite Jest has the highest (fiction) prose to highlights ratio in my Kindle library.
Surprise 1: Most of those highlights are single sentences or shorter.
Surprise 2: Most of them really mean I want to capture the feeling more than any presented facts or ideas.
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Oh, interesting. As you probably have noticed, reading Infinite Jest has given me an itch to write a bit more, too. See also: Overweight sports fans, cargo culture, usw.
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Nothing of note actually happens in the first half of the book. But by page 500 I deeply understand how everyone and the world got "here."
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Critic: After reading all of Pratchett's discworld last year, I feel spoiled.
I find Infinite Jest's character names ("Incandenza", "Schritt", "Joelle", "Steeply") the weakest link in the writing.
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Another thought:
If you love reading, you will absolutely adore Infinite Jest.
If you love stories, you will completely hate every page.
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
Continued thoughts/impressions and the like:
I've re-read R.A.W. & R.S.'s "Illumiatus!" trilogy five or six times over the years.
So reading IJ feels like finding a distant cousin in spirit. They're similarly encyclopedic (I've collected the full list of band names from the Lake Totenkopf festival of anyone is interested!), they both switch between POVs (present/past, inner/outer monologues, etc.), they both contain full vaguely related storylines where some cross paths only on the final pages, they both take place in imagined, remembered, hallucinated and "real" situations, they both revolve around odd public and secret organizations, they both contain oddly gratuitous "Mord und Totschlag" and more...
In my opinion, one of the biggest differences I found was that the trilogy goes into action right away while I feel like I've spent 500 pages in IJ carefully observing the status quo and getting a deep, deep, DEEP brief into "But and this is how we got here..." (BTW I love DFW's sentences starting with "But so/and...")
I'm at 65%, discounting the appendix, and I would say, the first actual action started exactly at the 50% mark. The unfolding of the Eschaton game chaos felt like a "OMG finally something is actually happening!".
And, well, if manifesting the "Eschaton" on a tennis court is not a nod to the trilogy, I don't know what is.
Now, one of the ways, that IJ is gaining a very special place in my heart is that I've never read an author with DFW's level of "Aufnahmevermögen", meaning his ability to observe and verbalize all kinds of inner thoughts that, once he's written them down, made me think "Oh, shit. I've had that exact thought or feeling dozens of times but didn't even notice them!"
Currently it's those incredibly microscopic bylines that have kept me coming back most. I'll find and share some examples later.
Proud to announce: I'm 65% through Infinite Jest. And still reading. And enjoying it a lot.
What impresses me the most is that reading Infinite Jest has created an urge in me to read a bunch of other books in parallel. This has not happened to me before. I'm confused.
So that means I'm also actively reading DFW's bio by D.T. Max, "The Emperor of Gladness" by Ocean Vuong and "Wahrheit ist die Erfindung des Lügners" by H.v. Foerster.
Much to say, maybe in a series of tweets in the coming week. I'll post those below as they roll in.
New Anthropic research: Discovering cryptographic weaknesses with Claude.
Claude Mythos Preview has helped our researchers find weaknesses in cryptographic algorithms—the mathematical methods that are used to keep data private.
As senior engineering consultant, I designed and shipped the infrastructure for a truly randomized, multi-month, large-scale field experiment for Prof. Steve Levitt of Freakonomics — the engine behind his 2020 “Heads or Tails” study on how a coin toss shapes big life decisions and happiness.
My technical co-founder run: I designed and wrote a best-selling “programming for non-programmers” video course that got complete beginners shipping real code in a month — earning us a spot at Y Combinator and profitability since 2016.
Working as senior technology consultant, I coached client teams to ship better products faster through lean experiments, pair-programming and test-driven development. One team used live data from 250,000 trucks to preempt supply-chain failures — averting losses in the millions.
Hey @runpod! Love my little pod running my autoresearch loop. Migration from overclocking my laptop to your cloud took about an hour, completely easy.
Benefits: 1. I can touch my computer again 2. my experiments are running smoother and faster 3. pricing is great, comes in at ~two-fiddy/experiment. Nice.
Currently at experiment 17/100 and I put the loop live if you wanna check it out ->
Yes! We found a special-purpose neural memory architecture that ‘remembers’ an exact geo-location, given an in-flight daytime picture of Berlin. The typical miss is 27 m — no GPS, no internet, no map on board, just a 3.1 MB file of weights. It works on 96.5% of camera frames, and it took 81 experiments and $364 to find.
alexisrondeau.me"Which city in Paris are you staying in?" - A post-training study on small-model specialization with an autoresearch loopAcross 77 experiments — every lever from prompting and retrieval to fine-tuning and 2025's rubric-grounded RL — an on-device 3B model landed within about one rubric point of a frontier cloud model on every quality dimension: close, but consistently a notch below. None of the post-training playbook closed the last notch, and the controlled tests show why — the gap is a broad capability limit, not a…↗ alexisrondeau.me
“Not all who wander are lost”Ballpark — “Not all who wander are lost”: Can a UAV learn a city by heart — no GPS, no map on board, just a $4 flight computer?Yes: a from-scratch neural memory that knows Berlin by heart. One downward photo in, (lat, lon, confidence) out — the map is the weights, one city in 3.1 MB. Found by an autonomous loop of coding agents in 81 experiments for $364.↗ alexisrondeau.me
