verification

An example-based test checks the cases you thought of, which is exactly the set that excludes your bugs. Property-based testing inverts it: state a law the code must obey for all inputs, let the machine hunt for a counterexample, and let it shrink that counterexample to something you can read. This lesson covers the property patterns, generators, shrinking, and where the technique stops fitting.

Verification is now the expensive step, which changes what a sensible checking strategy looks like. This lesson covers the asymmetry between producing and refuting, deciding what to check before you read it, the questions that actually discriminate, and what a citation is worth.

If recognition no longer establishes identity, verification has to move to the channel. This lesson builds the practice: out-of-band confirmation, which requests need it, designing protocols people will actually follow under pressure, the household version, and what to do in the first hour after something goes wrong.

Assistants sit where authority, access and urgency meet, which is exactly what impersonation fraud exploits. This lesson covers why the role is targeted, what changed when voice and video became cheap to fake, and the verification habits that hold up when a convincing executive is asking you to move quickly.

Generated media makes fabrication cheap in both directions: false material is easy to produce, and real material is easy to dismiss as fake. This lesson covers how verification actually works, why detection tools are the weakest link in it, provenance standards, and the liar's dividend.

Since a model cannot judge its own output, detection has to compare it against something external. This lesson covers grounding through retrieval and why it reduces rather than eliminates the problem, then the detection methods that work: self-consistency sampling, entailment checking against sources, claim decomposition, and chain-of-verification.

Make loops trustworthy. Adversarial verification panels, sub-agent orchestration, loop-until-dry for unbounded discovery, loop-until-budget for paid depth, multi-modal sweeps with diverse prompts, eval-driven cap selection, and the five anti-patterns — silent caps, infinite plans, drift, premature termination, thrashing — that ship to prod more than they should.