François Chollet
Creator of the Keras deep-learning library and the ARC-AGI benchmark.
François Chollet did not write this page. What is this?
It collects the places they publish and what they have said there, each linked to the source. They have no account here. Is this you? Claim it, correct it, or ask us to remove it.
Where they publish
@fcholletx.com Where the arguments about what AI can and cannot do happen.
The most active channel: long threads on intelligence, benchmarks and the limits of scaling, plus announcements for ARC Prize and Keras.
Recent
- Test-time scaling has two axes: running agents over longer timeframes (depth), and running a larger number of agents (breadth). Everybody knows about the first… 1 Sept 2026
- Some people worry that the rapid AI progress driving the "AI cybersecurity revolution" of 2026 could soon spill over into biology, potentially leading to extin… 30 Aug 2026
- What makes general intelligence "general" is that, *no matter the problem*, you should show intelligence. Not a-priori competence -- intelligence: the ability… 30 Aug 2026
Show 17 more
- RT @RimShayakhmetov: It's funny, I had my master's on a similar topic of cosmological photometric redshift - classifying stars, galaxies, o… 28 Aug 2026
- Figuring out the origins of cosmic rays (e.g. supernova, black hole...) from ground-based detector arrays is a notoriously difficult inverse problem. This post… 28 Aug 2026
- In verifiable domains, model capability scaling should remain unbounded. Models will simply keep improving by "absorbing more and more of the computational uni… 27 Aug 2026
- RT @mistaHarron: I first came across this book (prev editions) in 2023; it was also recommended by someone on X. Well, I guess it’s my turn… 25 Aug 2026
- RT @mark_l_watson: The first edition of this book was a bible for me. I just spent some time looking through the third edition, well worth… 25 Aug 2026
- If you're 17 (or any age) and you want to learn to build LLMs from scratch, read chapters 15-16 of Deep Learning with Python, available online here: https://t.… 24 Aug 2026
- An increasing fraction of social media consists of slop influencers using AI to make posts and bots replying to them. An echo of an echo of an echo 23 Aug 2026
- Follow the gradient of surprise 21 Aug 2026
- This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world model… 21 Aug 2026
- The conjecture is wrong, here's an AI-generated counter example https://t.co/HTsV8JvaSj 20 Aug 2026
- Incredible watering down -- the Singularity is now redefined to mean "the rate of new firm creation has increased somewhat" Vernor Vinge described the Singular… 19 Aug 2026
- Regular reminder -- the set of public ARC 3 games is called "demonstration set", not "eval set" nor "training set". It is not meant to be used as training data… 14 Aug 2026
- Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-guided on-the-fly synthesis of a symbolic world model, i.e. makin… 14 Aug 2026
- Test-time training was popularized during the ARC Prize 2024 competition, after being explored in particular by @MindsAI_Jack and team. To date, I believe ARC… 13 Aug 2026
- Expedia recently moved its ranking models to a state-of-the-art Keras 3 setup. Results: 30% faster training, and inference latency decreased by 70%. Read their… 12 Aug 2026
- Coding isn't yet another application domain -- it's the meta-skill required for AI to automatically develop its own training material, via symbolic world model… 10 Aug 2026
- Builders respect builders. The loudest, most toxic haters are almost always the ones who have never built a thing -- the Nobody McPoasters. 10 Aug 2026
Link verified 1 Sept 2026. Recent items update automatically from the channel.
fcholletGitHub Keras and the rest of the code.
The code behind the work — Keras above all, plus the smaller research repos. The commit history is where the engineering, as opposed to the argument, lives.
Recent
- deep-learning-with-python-notebooks — Jupyter notebooks for the code samples of the book "Deep Learning with Python" 18 Sept 2025
- namex — Clean up the public namespace of your package! 26 May 2025
- ARC-AGI — The Abstraction and Reasoning Corpus 4 Apr 2025
Show 5 more
- keras-resources — Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library 12 Feb 2024
- keras-blog — Blog with Keras news, tutorials, and demos. 1 Nov 2023
- nelder-mead — Pure Python/Numpy implementation of the Nelder-Mead algorithm. 24 Apr 2021
- deep-learning-models — Keras code and weights files for popular deep learning models. 1 Oct 2020
- hualos — Keras Total Visualization project 2 Feb 2018
Link verified 1 Sept 2026. Recent items update automatically from the channel.
On record
What they believeKorents 8 beliefs, 2 changed minds — each backed by an exact quote.
Compiled by korents.com, not by them: the one-line wordings are korents', the quotes are theirs.
Recent
In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction.
In verifiable domains, model capability scaling should remain unbounded. Models will simply keep improving by "absorbing more and more of the computational universe", which is infinite by construction.
@fchollet on X Said 27 Aug 2026
A growing fraction of social media is AI slop influencers being replied to by bots — an echo of an echo of an echo.
An increasing fraction of social media consists of slop influencers using AI to make posts and bots replying to them. An echo of an echo of an echo
@fchollet on X Said 23 Aug 2026
Calling today's economic effects "the Singularity" waters the term down past recognition; Vinge meant an event horizon beyond which nothing is imaginable.
Incredible watering down -- the Singularity is now redefined to mean "the rate of new firm creation has increased somewhat" Vernor Vinge described the Singularity as an event horizon past which everything (e.g. what happens tomorrow) becomes entirely unimaginable and unpredictable to human understanding
@fchollet on X Said 19 Aug 2026
Show 5 more
Coding is not just another application domain for AI; it is the meta-skill that lets AI generate its own training material and start the recursive self-improvement loop.
Coding isn't yet another application domain -- it's the meta-skill required for AI to automatically develop its own training material, via symbolic world models. That's how the RSI loop actually kicks off.
@fchollet on X Said 10 Aug 2026
Future AI, say in fifteen years, will not be built on the LLM stack; it will have to move to symbolic learning.
However, looking ahead, I still do not believe that future AI (say, in 15 years) will be based on the LLM stack. I believe it will necessarily have to move closer to its optimal, final form -- symbolic learning. Obviously this is a risky and contrarian belief -- the safe bet would be LRMs. But let's see.
@fchollet on X Said 7 Aug 2026
Current AI techniques are four to six orders of magnitude away from optimal in data efficiency and test-time compute efficiency.
I believe current techniques are 4-6 orders of magnitude away from optimality in terms of data efficiency and test-time compute efficiency. But far future AI will be near-optimal.
@fchollet on X Said 7 Aug 2026
Scaling the 2019-2023 recipe — same architecture, bigger model, more data — is not enough; further progress depends on new architectural ideas.
o3's improvement over the GPT series proves that architecture is everything. You couldn't throw more compute at GPT-4 and get these results. Simply scaling up the things we were doing from 2019 to 2023 -- take the same architecture, train a bigger version on more data -- is not enough.
OpenAI o3 Breakthrough High Score on ARC-AGI-Pub Said 20 Dec 2024
Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence.
Passing ARC-AGI does not equate to achieving AGI, and, as a matter of fact, I don't think o3 is AGI yet. o3 still fails on some very easy tasks, indicating fundamental differences with human intelligence.
OpenAI o3 Breakthrough High Score on ARC-AGI-Pub Said 20 Dec 2024
Latest
Everything, newest firstFeed Posts, videos, repos and beliefs from every card above, in one stream.
Filter & sortAll sources · condensed
- Test-time scaling has two axes: running agents over longer timeframes (depth), and running a larger number of agents (breadth). Everybody knows about the first… 1 Sept
- Some people worry that the rapid AI progress driving the "AI cybersecurity revolution" of 2026 could soon spill over into biology, potentially leading to extin… 30 Aug
- What makes general intelligence "general" is that, *no matter the problem*, you should show intelligence. Not a-priori competence -- intelligence: the ability… 30 Aug
- RT @RimShayakhmetov: It's funny, I had my master's on a similar topic of cosmological photometric redshift - classifying stars, galaxies, o… 28 Aug
- Figuring out the origins of cosmic rays (e.g. supernova, black hole...) from ground-based detector arrays is a notoriously difficult inverse problem. This post… 28 Aug
- In verifiable domains, model capability scaling should remain unbounded. Models will simply keep improving by "absorbing more and more of the computational uni… 27 Aug
Show 25 more
- In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction. 27 Aug
- RT @mistaHarron: I first came across this book (prev editions) in 2023; it was also recommended by someone on X. Well, I guess it’s my turn… 25 Aug
- RT @mark_l_watson: The first edition of this book was a bible for me. I just spent some time looking through the third edition, well worth… 25 Aug
- If you're 17 (or any age) and you want to learn to build LLMs from scratch, read chapters 15-16 of Deep Learning with Python, available online here: https://t.… 24 Aug
- An increasing fraction of social media consists of slop influencers using AI to make posts and bots replying to them. An echo of an echo of an echo 23 Aug
- A growing fraction of social media is AI slop influencers being replied to by bots — an echo of an echo of an echo. 23 Aug
- Follow the gradient of surprise 21 Aug
- This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world model… 21 Aug
- The conjecture is wrong, here's an AI-generated counter example https://t.co/HTsV8JvaSj 20 Aug
- Incredible watering down -- the Singularity is now redefined to mean "the rate of new firm creation has increased somewhat" Vernor Vinge described the Singular… 19 Aug
- Calling today's economic effects "the Singularity" waters the term down past recognition; Vinge meant an event horizon beyond which nothing is imaginable. 19 Aug
- Regular reminder -- the set of public ARC 3 games is called "demonstration set", not "eval set" nor "training set". It is not meant to be used as training data… 14 Aug
- Coding is not just another application domain for AI; it is the meta-skill that lets AI generate its own training material and start the recursive self-improvement loop. 10 Aug
- Current AI techniques are four to six orders of magnitude away from optimal in data efficiency and test-time compute efficiency. 7 Aug
- Future AI, say in fifteen years, will not be built on the LLM stack; it will have to move to symbolic learning. 7 Aug
- deep-learning-with-python-notebooks — Jupyter notebooks for the code samples of the book "Deep Learning with Python" 18 Sept 2025
- namex — Clean up the public namespace of your package! 26 May 2025
- ARC-AGI — The Abstraction and Reasoning Corpus 4 Apr 2025
- Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence. 20 Dec 2024
- Scaling the 2019-2023 recipe — same architecture, bigger model, more data — is not enough; further progress depends on new architectural ideas. 20 Dec 2024
- keras-resources — Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library 12 Feb 2024
- keras-blog — Blog with Keras news, tutorials, and demos. 1 Nov 2023
- nelder-mead — Pure Python/Numpy implementation of the Nelder-Mead algorithm. 24 Apr 2021
- deep-learning-models — Keras code and weights files for popular deep learning models. 1 Oct 2020
- hualos — Keras Total Visualization project 2 Feb 2018