pith. sign in

arxiv: 2412.05282 · v2 · pith:GNK3H7ZHnew · submitted 2024-11-05 · 💻 cs.CY · cs.AI

International Scientific Report on the Safety of Advanced AI (Interim Report)

classification 💻 cs.CY cs.AI
keywords reportinternationalscientificadvancedexpertsinterimsafetyunderstanding
0
0 comments X
read the original abstract

This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI -- AI that can perform a wide variety of tasks -- with a focus on understanding and managing its risks. A diverse group of 75 AI experts contributed to this report, including an international Expert Advisory Panel nominated by 30 countries, the EU, and the UN. Led by the Chair, these independent experts collectively had full discretion over the report's content. The final report is available at arXiv:2501.17805

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Forecasting Scientific Progress with Artificial Intelligence

    cs.AI 2026-05 unverdicted novelty 7.0

    Introduces the CUSP benchmark across 4760 events and finds frontier AI models can pick plausible directions but fail to predict whether or when scientific advances will occur, with performance varying by domain and in...

  2. Proof-of-Learning with Incentive Security

    cs.CR 2024-04 unverdicted novelty 6.0

    The paper introduces an incentive-secure Proof-of-Learning protocol for blockchain consensus that claims provable security against two attacks, reduced computational overhead, and guarantees even with untrusted proble...

  3. Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance

    cs.LG 2026-06 unverdicted novelty 5.0

    GCD uses diffusion model priors to guide suffix search, achieving higher attack success rates with better semantic adherence and lower detection than GCG-style methods.

  4. From monoliths to modules: Decomposing transducers for efficient world modelling

    cs.AI 2025-12 unverdicted novelty 5.0

    A framework for decomposing transducers into sub-transducers on distinct subspaces to enable parallel and interpretable world models.