Long-form arguments on programming languages, correctness, and the parts of software engineering that resist automation.
// The industry's default answer to insecure AI-generated code is more AI: an LLM checker hunting for bugs an LLM wrote. Fighting fire with fire only ever secures the common case — this traces a path to baking security into generation itself.
→// AI code generation is really a specification problem — and a spectrum of tests, types, and formal methods that narrow the guess.
→// Invariant inference, execution oracles, and the limits of pure AI audits: how a "poor man's neurosymbolic" loop forces LLMs to write down their assumptions, then fuzzes the assumptions themselves.
→// Every breakthrough technology starts as a faster version of the old thing. The true paradigm shift comes when you abandon the old constraints entirely. Are we there yet with AI and software?
→// Agentic orchestration layers are turning software maintenance from a brittle, depreciating asset into a fluid, self-optimizing substrate — replacing the engines of a commercial airliner mid-flight.
→// Test suites aren't enough. CCC passed all of them, then shipped 19 silent miscompilations. FastRender deadlocked under real CSS. The fix: replace sparse test signals with formal invariants agents cannot argue past.
→// When AI agents treat code as a temporary resource — generated, executed, and discarded — human-readable source files become unnecessary overhead. But removing them triggers a process dependency cascade: every engineering practice built on source code must be rebuilt on agentic primitives.
→// As agentic code generation explodes, we are hitting an unyielding complexity ceiling. The mandate of this epoch is not to rebuild the familiar slightly faster, but to abandon procedural scripting for intent-driven, formally verified systems.
→// Zero-day discovery has become a commodity, delegated increasingly to autonomous agent teams. The defensive literature answers with a four-pillar stack — harden, watch, contain, patch — but the feedback arrows between the pillars are where the architecture goes quiet.
→// Across the US, UK, and China, AI funding is hollowing out foundational computer science. The UK is the purest case: centralized, ring-fenced, and suffocated by a 212% personnel-cost hyper-inflation that core systems cannot survive.
→// Grammar-constrained decoding makes it mathematically impossible for a model to emit invalid syntax. That guarantee cuts both ways — closing off failure modes nobody could patch before, while quietly deleting the model's ability to say no.
→// Thirty years after cypherpunks printed encryption code in paper books, history is repeating itself in AI. The boundary of national security regulation has moved from cryptographic algorithms to model weights — and the same enforcement dilemma is back.
→// Enterprise security bet on one frontier model doing everything until the latency spiral caught up with it. The literature's answer is dozens of small, disposable, locally-abliterated models orchestrated by deterministic code — cheap enough to run on every request, narrow enough to audit.
→// J.P. Morgan says AI has collapsed the vulnerability-to-exploit window from a year to a day. It's right about the machine-speed side — and its own footnotes concede the breach data showing 98.6% of disclosed CVEs never get exploited at all.
→// McKinsey's 2023 framework for measuring individual developer productivity triggered the same rebuttal software engineering has delivered every decade since 1968 — and GenAI tooling is now failing the identical way, one layer up, measured in tokens instead of lines.
→// Lean 4, Aeneas/Charon, and AI-orchestrated proof search are credited with turning blockchain consensus verification into a production requirement — the technology is real, and several of the citations behind that claim aren't.
draft// As AI compresses the time from disclosure to working exploit, the patch-window math every security team relies on stops holding — and the harder problem turns out to be the human pipeline behind it, not a single super-attacker model.
draft// When autonomous agents can discover and weaponize zero-day vulnerabilities for pennies, reactive patching collapses. The only survivable architecture enforces structural runtime invariants — making it physically impossible for a vulnerability to execute a destructive action.
draft// Frontier LLMs wired into symbolic tooling are finding genuine weaknesses in real cryptographic schemes. This week's clearest example, from Anthropic, took three days to discover and a month to verify — that ratio is the real story.
draft// Point-in-time API gateways can't see a trajectory. Four frameworks — AWS Dogwood, NVIDIA NeMo Guardrails, Cloudflare WriteGuard, and Niels Provos's IronCurtain — push authorization out of the model and onto a deterministic proxy at the tool-call boundary. What holds up, and what's still aspirational.
draft// AI coding agents have made it cheap to write a second blockchain client from scratch — real projects (rustock, ETH2030, XVI/Guillotine, SHiNode) prove it. What they haven't fixed is N-Version Programming's fifty-year-old asterisk: majority voting only masks bugs that fail independently, and the evidence on AI ensembles says they mostly don't.
draft