Why Spec-Driven Development Breaks at Scale (and How to Fix It) – Arcturus Labsarcturus-labs.com·2 pts·JnBrymn·0
Karpathy on DeepSeek-OCR paper: Are pixels better inputs to LLMs than text?twitter.com·410 pts·JnBrymn·173
An alignment auditing agent capable of quickly exploring alignment hypothesisgithub.com·2 pts·JnBrymn·0
Agentic Context Engineering: Evolving Contexts for SelfImproving Language Modelsarxiv.org·2 pts·JnBrymn·0
Agentic Context Engineering: Evolving Contexts for SelfImproving Language Modelsarxiv.org·2 pts·JnBrymn·0
Petri: An open-source auditing tool to accelerate AI safety research \ Anthropicanthropic.com·2 pts·JnBrymn·0
Levels of AI agent autonomy: learning from self-driving cars – AI Native Devainativedev.io·2 pts·JnBrymn·0
Julia Neagu: Why evals haven't landed (yet) + lessons from evals at Copilottwitter.com·4 pts·JnBrymn·0
Yuck. Anthropic welcomes dystopia by hinting that AI should have moral statustwitter.com·21 pts·JnBrymn·24