Screencasts could be scalable data + evals for single-user emulation (Guardian Angels)

·LessWrong··

This is a response to Gwern's Guardian Angels post and draws terms from it quite extensively.Epistemic status: draft and to-be-updated once I do more experiments.Suppose you have a Guardian Angel (GA) model and you want to know how well it predicts your knowledge/personality/values/preferences. However, you don't have an extensive list of personal writings to personalize the model (because you're not one of the most prominent internet writers), and you don't want to do a lot of data labeling/sup...

Read full article →

Related Articles

Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
riordan · Hacker News · 18h ago
Mistral Patent for “Code implemented tool calls”
theanonymousone · Hacker News · 14h ago
Kinney Drugs pulls back AI phone assistant after hundreds of customer complaints
kotaKat · Hacker News · 13h ago
Study links GLP-1 drugs to bigger jump in women's employment than a degree
metadat · Hacker News · 12h ago
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
HenryNdubuaku · Hacker News · 10h ago