Pinned Tweet
My first article using Deep Learning is now out with the title "A deep learning approach for mapping and dating burned areas using temporal sequences of satellite images"
Article: sciencedirect.com/science/ar…
Code and data: github.com/mnpinto/banet
Miguel Pinto retweeted
I asked fable 5.2 to invent a new musical form.
Fable 5.2 wrote a symphony that’s shaped like a training run.
The orchestra starts as random noise, learns the key, pulse, harmony and the melody, then plays music it was never shown.
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
Miguel Pinto retweeted
On August 12th, 2026, the Moon totally eclipsed the Sun and cast its shadow across Siberia, Greenland, Iceland, Spain, and Portugal. Today’s image features two total solar eclipses viewed from Zaragoza, Spain, one over the Cathedral-Basilica of Our Lady of the Pillar and the other reflecting in the Ebro River. For a few moments, Spain saw its first major total solar eclipse since 1905. Those witnessing totality may experience a chill in the air, the quieting of birds, the confused chirps of insects, and the shared awe of many. It’s the corona’s time to shine as the Sun’s bright disk is blocked by the Moon. Among other reasons to study eclipses, they help scientists understand why the corona is millions of degrees hotter than the Sun’s surface. Enthusiastic citizens can contribute to these studies by recording how wildlife responds, imaging the corona, and monitoring air temperature and clouds.
Image Credit & Copyright: Ruiyu Zhang Text: Keighley Rockcliffe (NASA GSFC, UMBC CSST, CRESST II)
Miguel Pinto retweeted
New art project.
Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further.
gist.github.com/karpathy/862…
Miguel Pinto retweeted
I am proud to announce that I have successfully completed the world’s first USA coast to coast fully autonomous drive!
I left the Tesla Diner in Los Angeles 2 days & 20 hours ago, and now have ended in Myrtle Beach, SC (2,732.4 miles)
This was accomplished with Tesla FSD V14.2 with absolutely 0 disengagements of any kind even for all parking including at Tesla Superchargers.
Miguel Pinto retweeted
Excited to release new repo: nanochat!
(it's among the most unhinged I've written).
Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single, dependency-minimal codebase. You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web UI.
It weighs ~8,000 lines of imo quite clean code to:
- Train the tokenizer using a new Rust implementation
- Pretrain a Transformer LLM on FineWeb, evaluate CORE score across a number of metrics
- Midtrain on user-assistant conversations from SmolTalk, multiple choice questions, tool use.
- SFT, evaluate the chat model on world knowledge multiple choice (ARC-E/C, MMLU), math (GSM8K), code (HumanEval)
- RL the model optionally on GSM8K with "GRPO"
- Efficient inference the model in an Engine with KV cache, simple prefill/decode, tool use (Python interpreter in a lightweight sandbox), talk to it over CLI or ChatGPT-like WebUI.
- Write a single markdown report card, summarizing and gamifying the whole thing.
Even for as low as ~$100 in cost (~4 hours on an 8XH100 node), you can train a little ChatGPT clone that you can kind of talk to, and which can write stories/poems, answer simple questions. About ~12 hours surpasses GPT-2 CORE metric. As you further scale up towards ~$1000 (~41.6 hours of training), it quickly becomes a lot more coherent and can solve simple math/code problems and take multiple choice tests. E.g. a depth 30 model trained for 24 hours (this is about equal to FLOPs of GPT-3 Small 125M and 1/1000th of GPT-3) gets into 40s on MMLU and 70s on ARC-Easy, 20s on GSM8K, etc.
My goal is to get the full "strong baseline" stack into one cohesive, minimal, readable, hackable, maximally forkable repo. nanochat will be the capstone project of LLM101n (which is still being developed). I think it also has potential to grow into a research harness, or a benchmark, similar to nanoGPT before it. It is by no means finished, tuned or optimized (actually I think there's likely quite a bit of low-hanging fruit), but I think it's at a place where the overall skeleton is ok enough that it can go up on GitHub where all the parts of it can be improved.
Link to repo and a detailed walkthrough of the nanochat speedrun is in the reply.
Miguel Pinto retweeted
The USGS created a geonarrative about the M7.7 #earthquake that occurred near Mandalay, Burma (Myanmar) on March 28, 2025. Read more below!
storymaps.arcgis.com/stories…
Miguel Pinto retweeted
Just 10 days after o1's public debut, we’re thrilled to unveil the open-source version of the groundbreaking technique behind its success: scaling test-time compute 🧠💡
By giving models more "time to think," LLaMA 1B outperforms LLaMA 8B in math—beating a model 8x its size. The full recipe is open-source🤯
This is the power of open science and open-source AI! 🌍✨
Miguel Pinto retweeted
FSD 13.2 enters a parking garage. I then park it on the second floor and it escapes the parking garage. I then park it on the snow covered roof and...
Miguel Pinto retweeted
tried my best to get FSD 13 stuck
it beat me, Austin Powers style
I am speechless...
Miguel Pinto retweeted
Major X9.05 flare from sunspot region 3842
Follow live on spaceweather.live/l/flare
Miguel Pinto retweeted
NotebookLM is quite powerful and worth playing with
notebooklm.google/
It is a bit of a re-imagination of the UIUX of working with LLMs organized around a collection of sources you upload and then refer to with queries, seeing results alongside and with citations.
But the current most new/impressive feature (that is surprisingly hidden almost as an afterthought) is the ability to generate a 2-person podcast episode based on any content you upload. For example someone took my "bitcoin from scratch" post from a long time ago:
karpathy.github.io/2021/06/2…
and converted it to podcast, quite impressive:
notebooklm.google.com/notebo…
You can podcastify *anything*. I give it train_gpt2.c (C code that trains GPT-2):
github.com/karpathy/llm.c/bl…
and made a podcast about that:
notebooklm.google.com/notebo…
I don't know if I'd exactly agree with the framing of the conversation and the emphasis or the descriptions of layernorm and matmul etc but there's hints of greatness here and in any case it's highly entertaining.
Imo LLM capability (IQ, but also memory (context length), multimodal, etc.) is getting way ahead of the UIUX of packaging it into products. Think Code Interpreter, Claude Artifacts, Cursor/Replit, NotebookLM, etc. I expect (and look forward to) a lot more and different paradigms of interaction than just chat.
That's what I think is ultimately so compelling about the 2-person podcast format as a UIUX exploration. It lifts two major "barriers to enjoyment" of LLMs. 1 Chat is hard. You don't know what to say or ask. In the 2-person podcast format, the question asking is also delegated to an AI so you get a lot more chill experience instead of being a synchronous constraint in the generating process. 2 Reading is hard and it's much easier to just lean back and listen.
Miguel Pinto retweeted
We are excited to introduce Stable Fast 3D, Stability AI’s latest breakthrough in 3D asset generation technology. This innovative model transforms a single input image into a detailed 3D asset in just 0.5 seconds, setting a new standard for speed and quality in the field of 3D reconstruction!
Alongside this release, we’ve also published a technical report that highlights how we achieve fast inference speeds with reduced baked illumination and material parameters.
👾You can learn more and access the report here: stability.ai/news/introducin…
































