Agents
If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic lea…
If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic learning. In fact what you're doing is specifically a form of D
If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic learning. In fact what you're doing is specifically a form of DL-guided program synthesis (that's what LLM codegen is). However there are far more efficient (data-wise and compute wise) ways to do symbolic learning. By many orders of magnitude.
Related
- Agentic coding is a form of machine learning. Generated code is best treated as a blackbox artifact whose behavior and generalization should…
- Agentic coding forces you to design clean interfaces and document them well. An agent cannot read the implicit mental model shared by your e…
- This means that agentic coding isn't exactly a replacement for software engineering. It is a fundamentally different way of producing softwa…
Source: Francois Chollet (X) | 2026-09-10