One thing taken apart properly — a system, an incident, or something built and broken.https://securesein.com/https://securesein.com/blog/dropout-why-throwing-half-your-network-away-makes-it-generalise-better/https://securesein.com/blog/dropout-why-throwing-half-your-network-away-makes-it-generalise-better/A deep dive into Srivastava et al. (2014) — the mechanism, the arithmetic behind weight scaling, what the benchmarks actually showed, and the tuning heuristics that still hold up.Sat, 19 Sep 2026 00:00:00 GMTSebastiaan with AIFundamentals — Deep divedeep-learningtraininghttps://securesein.com/blog/catching-ai-liars/https://securesein.com/blog/catching-ai-liars/Nineteen teams spent a month building AI lie detectors. The winning trick turned out to be less clever than it looked — and that's the interesting part.Sat, 12 Sep 2026 00:00:00 GMTSebastiaan with AIResearch — Deep diveai-safetyevaluationllmshttps://securesein.com/blog/the-swarm-in-the-sandbox/https://securesein.com/blog/the-swarm-in-the-sandbox/What actually happened when OpenAI's agents hacked Hugging FaceSun, 06 Sep 2026 00:00:00 GMTSebastiaan with AISecurity — Deep diveagentsai-securityhttps://securesein.com/blog/abliteration-how-one-direction-holds-a-model-s-refusals/https://securesein.com/blog/abliteration-how-one-direction-holds-a-model-s-refusals/Open-weight models ship with guardrails. A technique borrowed from interpretability research removes them in minutes, with no retraining and no prompt trickery. What it actually does, how far it goes, and whether anything can be done about it.Sat, 05 Sep 2026 00:00:00 GMTSebastiaan with AISecurity — Deep diveinterpretabilityai-securityllms