🎯 AI Alignment - buckman · Scour

Sixteen schemes for AI safety

🛡️AI Safety

lesswrong.com·

Reasoning RL in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond

🎮Reinforcement Learning

turingpost.com·

Controversial smut as an AI alignment issue

⚖️Ethics News Blog

thingofthings.substack.com··Substack

One AI Vendor Is a Single Point of Failure. Treat It Like One.

🔧MCP Blog

AI Paper Review: Training Language Models to Follow Instructions with Human Feedback (InstructGPT)

freecodecamp.org·

Neglected Basics of AI Alignment

🛡️LLM Security

lesswrong.com·

Who is Chris Olah? The atheist Anthropic cofounder the Pope chose to sit beside him at the Vatican and tell the tech industry it can’t govern itself

·

Who Elected Anthropic?

🎭Anthropic Claude Blog

vizierprime.substack.com··Substack

Iliad is Hiring

🛡️AI Safety Evals

lesswrong.com·

Governing AI Agents in Codebases Like a Linter

🔧Developer Tooling Blog

Learnings from starting an AI safety research team

🛡️AI Safety

lesswrong.com·

Solstice Sync: A Dynamic Gemini AI Alignment Puzzle

⚖️Ethics Blog

Linkpost for June

🌍Civilizational Risk Blog

thingofthings.substack.com

One Year of PauseAI UK

🛡️AI Safety

lesswrong.com·

Human-Aligned Decision Transformers for satellite anomaly response operations with inverse simulation verification

🤖Large Language Models Blog

Book of Cron Job

🐚Shell Scripting

lesswrong.com·

Thoughts on 'Learning Mechanics'

🧠Machine Learning

lesswrong.com·

My research agenda and work

lesswrong.com·

[Paper] Dictionary Learning Identifiability for Understanding SAEs

lesswrong.com·

Aligning Superintelligent Humans

lesswrong.com·

No more posts from buckman's subscribed feeds.

Scour all 25255 feeds Learn more about Feeds

Log in to enable infinite scrolling