aiqbenchInformații despre AI & calcul cuantic

...

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchSiguranță AI

This guide outlines a concrete workflow for evaluating large language models against "SPI-incompatible" behaviors, moving from high-level strategy to actionable next steps and specific criteria for identifying harmful reasoning patterns. By defining unambiguous benchmarks for these incompatibilities, the research aims to establish a rigorous framework for detecting and mitigating safety risks in model development. The open invitation for collaboration suggests a community-driven approach to refining these evaluation protocols before broader implementation.

Sursă care acoperăLessWrong

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

[Linkpost] Evals for “SPI-incompatible” behavior & reasoning: Guide to initial research

LessWrong9 iunie 20261 min de cititArticolul și perspectiva sunt în engleză.

In Part I of CLR's safe Pareto improvements (SPI) agenda, we gave our high-level strategy for evaluating models for SPI-incompatible behavior and reasoning. This guide gives more details on how I’m thinking about executing on this strategy, especially: the kind of workflow I think we should use, to start out; next steps building on what I’ve tried so far; and my rough sense of what counts as unambiguously bad “SPI-incompatibilities”. If you’re interested in collaborating on the next steps, please get in touch! I’d be happy to flesh things out more, and invite you to the private git repo. Discuss

my rough sense of what counts as unambiguously bad “SPI-incompatibilities”.

If you’re interested in collaborating on the next steps, please get in touch! I’d be happy to flesh things out more, and invite you to the private git repo.

Text integral sub licența deschisă a publicației · 77 cuvinte

Citește pe LessWrong ↗Întreabă despre acest articol