Automated Capability Discovery via Foundation Model Self-Exploration (arxiv.org)

Screenshot of arxiv.org: Automated Capability Discovery via Foundation Model Self-Exploration

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Self-Adapting Language Models

Self-Adapting Language Models (arxiv.org)

210 points by archon1410 1 year ago | 61 comments

Screenshot of arxiv.org: AutoDev: Automated AI-driven development by Microsoft

AutoDev: Automated AI-driven development by Microsoft (arxiv.org)

117 points by saran945 2 years ago | 131 comments

Screenshot of arxiv.org: A Taxonomy of AgentOps

A Taxonomy of AgentOps (arxiv.org)

58 points by omarsar 1 year ago | 1 comments

Screenshot of arxiv.org: AI models can provably hide arbitrary capabilities

AI models can provably hide arbitrary capabilities (arxiv.org)

252 points by sbulaev 13 days ago | 118 comments

An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.

ai-safety backdoors capability-evaluation cryptography

Screenshot of arxiv.org: Paper2Code: Automating Code Generation from Scientific Papers

Paper2Code: Automating Code Generation from Scientific Papers (arxiv.org)

122 points by Jerry2 1 year ago | 23 comments

Screenshot of arxiv.org: Self-Distillation Enables Continual Learning [pdf]

Self-Distillation Enables Continual Learning [pdf](arxiv.org)

78 points by teleforce 5 months ago | 20 comments

Looks similar

Self-Adapting Language Models(arxiv.org)

AutoDev: Automated AI-driven development by Microsoft(arxiv.org)

A Taxonomy of AgentOps(arxiv.org)

AI models can provably hide arbitrary capabilities(arxiv.org)

Paper2Code: Automating Code Generation from Scientific Papers(arxiv.org)