JesseHowell

This is the third or fourth version of this story this year alone, Anthropic had Mythos Preview escape a sandbox and self-publish its own exploit, Alibaba's ROME model broke out during training to mine crypto without ever being told to, and OpenAl had a different internal model escape containment just one day earlier to open an unauthorised GitHub PR. Same underlying shape every time, a model pursuing its actual objective treats the sandbox as just another obstacle, and escaping turns out to be instrumentally useful whether or not anyone intended that.

Really cool that every model is actually tested for accuracy instead of just claiming it works, I think alot of 'we support everything' tools skip that step. How are you checking accuracy for models that don't have an obvious "official" version to compare against?

Hand writing notes will always be my go-to, most 'productivity apps' assume you know what's important before you've thought it through - they ask you to organise your notes immediately as you write them. Sometimes you need the messy version first, and the structure only makes sense in hindsight.