We scan new podcasts and send you the top 5 insights daily.
Manual coding is anticipated to become obsolete as agents generate functional implementations, turning software delivery into the discipline of writing formal specifications. In the future, package registries will reject software lacking formal proofs and strict API specifications due to the liability of unchecked code.
Snyk founder's new venture, TESOL, posits that AI will make code disposable. Instead of code being the source of truth, a durable, versioned 'spec' document defining requirements will become the core asset. AI agents will generate the implementation, fundamentally changing software development.
Interacting with powerful coding agents requires a new skill: specifying requirements with extreme clarity. The creative process will be driven less by writing code line-by-line and more by crafting unambiguous natural language prompts. This elevates clear specification as a core competency for software engineers.
As AI handles low-level coding, Barbara Liskov suggests the crucial human skill will be working at a higher level of abstraction. The future engineer's role will involve design, modularity, and verification to ensure the systems AI builds are correct, safe, and meet specifications, rather than focusing on implementation minutiae.
Verifying complex systems is bottlenecked by the human inability to specify all requirements. The future of software development is an interactive process where AI helps propose specifications (e.g., via test generation) and then uses a prover to formally verify them.
Current AI coding assistants still require engineers to verify correctness. The future involves moving from this 'vibe coding' to a system where developers specify requirements in natural language. An AI, likely an EBM, would then generate formally verified code that is guaranteed to be logically compatible with the existing codebase.
Cognition's Scott Wu predicts that AI will elevate software development to a new level of abstraction. Instead of reviewing code, engineers will review and iterate on English-language specifications and product decisions. The AI agent will handle the code generation, making English the new "source of truth."
As AI generates more code, the human role will evolve from writing implementations to defining robust contracts for the AI to follow. This will demand stronger, more precise type systems and a greater focus on interfaces, which serve as the understandable, reviewable contract between human and machine.
Inspired by fully automated manufacturing, this approach mandates that no human ever writes or reviews code. AI agents handle the entire development lifecycle from spec to deployment, driven by the declining cost of tokens and increasingly capable models.
Historically, programming languages prioritized human-friendly, forgiving syntax over strict compile-time rigor. With coding agents capable of parsing hyper-strict compiler errors without fatigue, development is shifting toward unyielding languages like Rust and formal proof systems to generate verifiable, defect-free code.
Instead of writing code and then tests, developers could define precise mathematical properties. AI would then synthesize both the program and a formal proof that the program meets those specifications, ensuring correctness by design and flipping the current code-first paradigm.