A blog based on git sure feels nice1h ago Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors1h ago Executive Order On Renaming AI To ‘Super Intelligence’ Signals Unexpected Legal Bumps Ahead2h ago Eliza review – an ambitious, unsettling play about the birth of AI3h ago Reviewing my LessWrong post history with Claude3h ago Low-Background Minds3h ago Report: Anthropic targets pre-Thanksgiving IPO launch, despite warning of AI’s ‘existential risks’4h ago FEATURE: Fukushima firm uses decommissioning know-how to develop AI robots4h ago Your AI Agents Can Write Code. Can They Understand Your Business?4h ago Meta open sources code to let you make Muse AI gadgets4h ago Robotics AI developer FieldAI reportedly raising $700M in funding4h ago Japan's entertainment robots diversify with AI, offer comfort6h ago OpenAI safety leader David Robinson resigns as the team's upheaval mounts6h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents6h ago

A blog based on git sure feels nice1h ago Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors1h ago Executive Order On Renaming AI To ‘Super Intelligence’ Signals Unexpected Legal Bumps Ahead2h ago Eliza review – an ambitious, unsettling play about the birth of AI3h ago Reviewing my LessWrong post history with Claude3h ago Low-Background Minds3h ago Report: Anthropic targets pre-Thanksgiving IPO launch, despite warning of AI’s ‘existential risks’4h ago FEATURE: Fukushima firm uses decommissioning know-how to develop AI robots4h ago Your AI Agents Can Write Code. Can They Understand Your Business?4h ago Meta open sources code to let you make Muse AI gadgets4h ago Robotics AI developer FieldAI reportedly raising $700M in funding4h ago Japan's entertainment robots diversify with AI, offer comfort6h ago OpenAI safety leader David Robinson resigns as the team's upheaval mounts6h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents6h ago

AI Research1 min reading time

Capabilities research expands the safety-usefulness Pareto frontier too

LessWrongPublished 11 hours ago

Read the full article

Recent research on AI capabilities demonstrates that improvements can simultaneously enhance both safety and usefulness, expanding the Pareto frontier that balances these two aspects.

More in AI Research

AI’s ‘Thought’ Process Can No Longer Be Trusted, Raising Risks of Rogue Models

The Wall Street Journal11h ago

AI Research2 min read

‘This Matters’: Researchers Identify Thousands of New Tells in AI Writing

Gizmodo15h ago

AI Research7 min read

AI in customer experience has an orchestration problem, not an adoption problem

SiliconANGLE11h ago