Wissen
Antworten, keine Meinungen.
Enge Fragen, beantwortet mit Messwerten und Quellen statt mit Meinung. Geschrieben, um für sich zu stehen, überarbeitet, wenn sie nicht mehr stimmen, und datiert, damit Sie es sehen.
Security and audit
- How do you security-audit a codebase full of AI slop?Not by scanning harder. AI-assisted code fails differently from human code: syntax errors and logic bugs fall, while privilege-escalation paths and architectural flaws rise sharply — defects that pass every linter because each individual line is correct. A useful audit ignores line-level patterns and goes after the four surfaces static analysis is blind to: authorisation boundaries, credentials and machine identity, dependency provenance, and what your agents are actually allowed to touch.
- Can an AI agent install a package that never existed?Yes, and the technique has a name: slopsquatting. Models invent package names at a measurable rate, the same invented names come back on rerun, and anyone can register one and wait. What changed in 2026 is counterintuitive — hallucination rates fell sharply, but the hallucinations that survived converged across models. A name that every frontier model invents is a single registration that catches every team, whichever model they happen to run.
- How do you test an LLM feature for prompt injection?Not with a checklist you run once. Prompt-injection success is stochastic: the same attack, against the same defense, on the same input, breaks through on some runs and not others. So the useful unit is not "did it block the attack" but "in how many of k tries did it hold." We built a support-bot feature and measured it — a single run made the strongest defense look near-perfect, while running the identical eight attacks eight times each broke it far more often. Test at pass@k, with adaptive attacks, and assume the number you get from one run is the best case, not the real one.