RSS

RobertKirk

Karma: 518

Research Scientist working on Alignment Red Teaming team at the UK AI Security Institute

Im­prov­ing Au­dit Real­ism With In­fer­ence Time Com­pute and De­ploy­ment Scaffolds

Axel Ahlqvist, Richard Guan, Juan Pablo Rivera, adlnk, mitroitskii, alexandrasouly, RobertKirk and John Hughes
3 Sep 2026 14:16 UTC
19 points
0 comments8 min readLW link

Sev­eral fron­tier mod­els are sub­stan­tially pre­fill aware

yeedrag, Parv Mahajan, David Africa, alexsouly, Jordan Taylor and RobertKirk
17 Jun 2026 17:41 UTC
63 points
2 comments5 min readLW link

Trac­ing Eval-Aware­ness Emer­gence Through Train­ing of OLMo 3

Ram Bharadwaj and RobertKirk
10 Jun 2026 10:13 UTC
49 points
9 comments6 min readLW link

Pre­fill aware­ness: can LLMs tell when “their” mes­sage his­tory has been tam­pered with?

David Africa, alexsouly, Jordan Taylor and RobertKirk
9 Mar 2026 10:47 UTC
87 points
11 comments10 min readLW link

A Sober Look at Steer­ing Vec­tors for LLMs

Joschka Braun, Dmitrii Krasheninnikov, Usman Anwar, RobertKirk, Daniel Tan and David Scott Krueger
23 Nov 2024 17:30 UTC
42 points
0 comments5 min readLW link

Spec­u­la­tive in­fer­ences about path de­pen­dence in LLM su­per­vised fine-tun­ing from re­sults on lin­ear mode con­nec­tivity and model souping

RobertKirk20 Jul 2023 9:56 UTC
39 points
2 comments5 min readLW link

Causal con­fu­sion as an ar­gu­ment against the scal­ing hypothesis

RobertKirk and David Scott Krueger
20 Jun 2022 10:54 UTC
86 points
30 comments15 min readLW link

Spar­sity and in­ter­pretabil­ity?

Ada Böhm, RobertKirk and Tomáš Gavenčiak
1 Jun 2020 13:25 UTC
41 points
3 comments7 min readLW link

How can In­ter­pretabil­ity help Align­ment?

RobertKirk and Tomáš Gavenčiak
23 May 2020 16:16 UTC
37 points
3 comments9 min readLW link

What is In­ter­pretabil­ity?

RobertKirk, Tomáš Gavenčiak and Ada Böhm
17 Mar 2020 20:23 UTC
39 points
1 comment11 min readLW link