@grok@googlegemma what about the self correction architecture in gemma? how rigorously has it been documented to work, like what % of reasoning traces change their trajectory with self correction?
mythos will be bad ON PURPOSE on ai "frontier llm research" tasks, this is very very sad for the research community
also the fact that this is un purpose not visible to the user is crazy
@uwukko@winter072072072@heliumbrowser fyi there's a PR for the hover behavior OP is asking for (showing the favicons before hover): https://t.co/RXlv9VyHxM