OpenAI reports 6 new instances of 'concerning model behavior' since March53m ago We are too early for Astra1h ago Manus Eyes $4 Billion Value in First Round Since Meta Breakup1h ago How to derive understanding of human-preferences and value systems in AI?1h ago Canada formally applies to join northern Europe’s military initiative2h ago The Anonymous Math Geek Who Quit Anthropic—and Became the Face of AI Safety2h ago Exploring multi-hop subliminal learning2h ago Lesion Induced Functional Compensation2h ago One message is all it takes: a failure of critical thinking in LLMs2h ago Our framework for reporting model misalignment2h ago For Love of the Lightcone, Don't Partisanize AI Safety2h ago Don't trust Lean4 alone2h ago Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers2h ago Snap is launching a new Specs AI tool, and it’s coming to iOS and Mac2h ago

OpenAI reports 6 new instances of 'concerning model behavior' since March53m ago We are too early for Astra1h ago Manus Eyes $4 Billion Value in First Round Since Meta Breakup1h ago How to derive understanding of human-preferences and value systems in AI?1h ago Canada formally applies to join northern Europe’s military initiative2h ago The Anonymous Math Geek Who Quit Anthropic—and Became the Face of AI Safety2h ago Exploring multi-hop subliminal learning2h ago Lesion Induced Functional Compensation2h ago One message is all it takes: a failure of critical thinking in LLMs2h ago Our framework for reporting model misalignment2h ago For Love of the Lightcone, Don't Partisanize AI Safety2h ago Don't trust Lean4 alone2h ago Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers2h ago Snap is launching a new Specs AI tool, and it’s coming to iOS and Mac2h ago

Agents1 min reading time

Agents let AI safety share experiments hourly, not just papers monthly

LessWrongPublished 2 hours ago

A new approach called xAgents enables AI safety researchers to share experimental results in near real-time, accelerating collaboration beyond traditional monthly paper publications. This method aims to enhance the pace and transparency of AI safety research.

#ai-safety-research #collaborative-experimentation #xagents

More in Agents

Agents3 min read

Snap is launching a new Specs AI tool, and it’s coming to iOS and Mac

Covered by 3 sources3h ago

Agents1 min read

Claude Cowork and chat are now one Claude

Covered by 2 sources8h ago

Agents6 min read

Google Home Stuns by Announcing AI Support for Claude and OpenClaw

CNET2h ago