Are we entering a world where chatbots will replace devs?
Probably not. Prompting an LLM with natural language is inherently lossy and ambiguous. Up to this point, programming has always been deterministic: Your code does what you say it should do otherwise, it’s a bug. Coding agents break that contract.

Our blog:
https://blog.trailofbits.com/2025/12/19/can-chatbots-craft-correct-code/

Can chatbots craft correct code?

LLMs fundamentally differ from compilers because they lack determinism and semantic guarantees, making them useful coding assistants but unreliable for autonomous code generation without human review and formal verification.

The Trail of Bits Blog
@trailofbits you really think that the world would know how hard it is to get the correct code from experienced coders based on natural language specifications, why would a poorly trained Markov chain be any better.