abliterated
Oh, you say, but that's just terrorists asking for help--what about a rogue LLM coming after my bank account? "In February 2026, we internally estimated that the length of cyber tasks AI models could complete had doubled every 4.7 months since late 2024 โ already an acceleration from our November 2025 estimate of 8 months. Since then, AISI reported on two new models, Claude Mythos Preview and GPT-5.5, which substantially exceeded both doubling rate trends." How fast is autonomous AI cyber capability advancing? But it's not all bad news. Here's someone who dug into a model to surgically extract its slop-maker: Where AI slop comes from, and how to turn it down inside the model.
