Carlos Guerrero
5 followers · 3 following · 134 views
on the atlas · 25
- Independent Assessment of AI R&D Acceleration at Anthropic in October 2026 - METR13 savers
- A breakdown of AI capability levels focused on AI R&D labor acceleration — AI Alignment Forum1 savers
- An alignment assessment of the UK AISI cybertesting incident \ Anthropic1 savers
- Research Proposal Carlos Guerrero - Documentos de Google1 savers
- Eval Cooperativeness May Be a Scalable Mitigation for Eval Gaming6 savers
- Why I'm scared of RL — AI Alignment Forum1 savers
- An Intuitive Guide to Garrabrant Induction — LessWrong3 savers
- Cyborgism — AI Alignment Forum1 savers
- Deep Deceptiveness — LessWrong6 savers
- What is ambitious value learning? — AI Alignment Forum1 savers
- Fitness-Seekers: Generalizing the Reward-Seeking Threat Model — AI Alignment Forum1 savers
- On Dwarkesh Patel's Podcast With Ryan Greenblatt4 savers
- An Alien Mind | OpenAI28 savers
- The Origin of Consciousness in the Breakdown of the Bicameral Mind1 savers
- [2206.13353] Is Power-Seeking AI an Existential Risk?1 savers
- The behavioral selection model for predicting AI motivations — LessWrong15 savers
- GPT-6 Astra System Card - OpenAI Deployment Safety Hub1 savers
- Cat-Belling Problems — LessWrong2 savers
- Rationality: A-Z9 savers
- An Argument for Analogies — LessWrong1 savers
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident - METR1 savers
- Harsh Bhatt on X: "The Math of RL: From Policy Gradients to PPO and GRPO" / X1 savers
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident - METR20 savers
- Policy Gradient Algorithms | Lil'Log8 savers
- [2608.07514] Open Technical Problems in Open-Weight AI Model Risk Management1 savers