RSS

Olli Järviniemi

Karma: 716

A civ­i­liza­tion ran by amateurs

Olli Järviniemi30 May 2024 17:57 UTC
58 points
7 comments6 min readLW link

Test­ing for par­allel rea­son­ing in LLMs

19 May 2024 15:28 UTC
3 points
7 comments9 min readLW link

Un­cov­er­ing De­cep­tive Ten­den­cies in Lan­guage Models: A Si­mu­lated Com­pany AI Assistant

6 May 2024 7:07 UTC
88 points
6 comments1 min readLW link
(arxiv.org)

On pre­cise out-of-con­text steering

Olli Järviniemi3 May 2024 9:41 UTC
7 points
6 comments3 min readLW link