Building Software for AI Agents: A New Paradigm for the Future
matthew_d_green · x · 2026-07-20
Renowned cryptographer Matthew Green discussed how AI coding agents are upending software development philosophies. He found himself in a peculiar situation: the primary consideration when developing software is no longer making it comfortable and easy for human developers, but making it "comfortable" for AI coding agents.
He added that AI agents are highly vigilant about supply chain risks and "panic" when asked to clone repositories and run servers with extensive permissions. Instead, they prefer straightforward actions like "downloading a random C++ tool from 2015 and running messy experiments in the command line." Green concluded that AI is becoming an entirely new type of software consumer, and this might just be the future of software engineering.
More from coding & agent
- DeepMind paper: LLMs can't sample randomly on their own, only convert given seeds — rohanpaul_ai · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Two engineers rebuilt a FedEx supplier's billing core in 3.5 months vs an estimated 7-8 — alex_verem · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27