The Codex "goal" feature will take any silly shortcut possible in order to avoid doing the work (including rewriting your external checks), but if you manage to sufficiently constrain it so that it has absolutely no shortcuts available, it will do very interesting things
@fchollet
-
Limitations of Markovian Models in AI Agent Trajectory Planning
By
–
Most human tasks are not Markovian, the optimal next action cannot be determined solely by looking at the current state. It depends heavily on the past trajectory, the original intent, and context constraints. An agent that cannot compress and track its past trajectory with
-
Mental Models for Guiding AI Coding Agents
By
–
A mental model for working with coding agents is that they're blind squirrels running into a maze and bumping into walls. You must place the walls (verifiable constraints) strategically so that they end up in the general region you want them in.
-
JAX Grows from Niche to Mainstream in Machine Learning
By
–
The JAX package is now around the same level, 20M monthly downloads. Which is incredibly fast growth, because 5 years ago I recall it being below 2M or so. It went from niche to mainstream in the past couple of years. Well deserved success.
-
Keras hits record 21M monthly downloads on PyPI
By
–
The Keras package recently crossed 21M monthly downloads on PyPI, an all-time high (the daily ATH is around 900k). I still remember when it first crossed 10M monthly downloads about 5 years ago and I thought it couldn't possibly go any higher…
-
The impact of AI on developer productivity and code volume
By
–
The quantity of code that devs ship has roughly 10xed. But net developer productivity (value created by unit of time) is only up by a bit, if at all. Part of it is that the additional code is solving more incremental problems. A bigger part is that the new code is creating
-
Symbolic Learning as a Scalable Alternative to Neural Networks
By
–
Symbolic learning is not a replacement for coding agents, it's a replacement for gradient descent & NNs: a low-level, completely general, extremely scalable new learning substrate.
-
Agentic coding vs software engineering
By
–
This means that agentic coding isn't exactly a replacement for software engineering. It is a fundamentally different way of producing software, with different best practices and different use cases. Just like ML.
-
Agentic coding as machine learning
By
–
Agentic coding is a form of machine learning. Generated code is best treated as a blackbox artifact whose behavior and generalization should be managed via empirical evaluation, like with any ML model.
-
Agentic coding use cases by @fchollet
By
–
A few major use cases for agentic coding for me: 1. Adhoc data visualizations. Anytime I have a question that can be answered quantitatively, I generate some code to make a plot. 2. Adhoc data annotation UIs. In ML, "make your own dataset" is often the answer, and that used to