RSS

Francis Rhys Ward

Karma: 836

An­gles of at­tack for con­tinual learn­ing safety

Rauno Arike, RohanS, Owen Terry, Achu Menon, Zhijing Jin, Francis Rhys Ward and Seth Herd
16 Jun 2026 16:15 UTC
47 points
0 comments13 min readLW link

How might con­tinual learn­ing af­fect safety and al­ign­ment?

Rauno Arike, RohanS, Owen Terry, Achu Menon, Zhijing Jin, Francis Rhys Ward and Seth Herd
13 Jun 2026 17:34 UTC
59 points
2 comments16 min readLW link

What’s Con­tinual Learn­ing, and Why Might We Ex­pect To See It In Ad­vanced LLM Agents?

RohanS, Rauno Arike, Owen Terry, Achu Menon, Zhijing Jin, Francis Rhys Ward and Seth Herd
12 Jun 2026 18:43 UTC
28 points
2 comments17 min readLW link

Im­pli­ca­tions of Con­tinual Learn­ing for LLM Agents: Introduction

RohanS, Rauno Arike, Owen Terry, Achu Menon, Zhijing Jin, Francis Rhys Ward and Seth Herd
12 Jun 2026 18:36 UTC
48 points
0 comments6 min readLW link

Es­ti­mat­ing No-CoT Task-Com­ple­tion Time Hori­zons of Fron­tier AI Models

Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask, Twm Stone, Josh Hills, Ida Caspary and Shubhorup Biswas
10 Jun 2026 17:58 UTC
248 points
20 comments4 min readLW link

Three types of model or­ganism

Francis Rhys Ward10 Jun 2026 8:50 UTC
51 points
7 comments2 min readLW link

[Paper] How does in­for­ma­tion ac­cess af­fect LLM mon­i­tors’ abil­ity to de­tect sab­o­tage?

Rauno Arike, Raja Moreno, RohanS, Shubhorup Biswas and Francis Rhys Ward
11 Feb 2026 21:25 UTC
26 points
0 comments6 min readLW link

The Elic­i­ta­tion Game: Eval­u­at­ing ca­pa­bil­ity elic­i­ta­tion techniques

Teun van der Weij, Felix Hofstätter, JaydenTeoh, HenningB and Francis Rhys Ward
27 Feb 2025 20:33 UTC
15 points
1 comment2 min readLW link

Why care about AI per­son­hood?

Francis Rhys Ward26 Jan 2025 11:24 UTC
43 points
6 comments3 min readLW link

[Paper] AI Sand­bag­ging: Lan­guage Models can Strate­gi­cally Un­der­perform on Evaluations

Teun van der Weij, Felix Hofstätter, Ollie J, Sam F. Brown and Francis Rhys Ward
13 Jun 2024 10:04 UTC
84 points
10 comments2 min readLW link
(arxiv.org)

An In­tro­duc­tion to AI Sandbagging

Teun van der Weij, Felix Hofstätter and Francis Rhys Ward
26 Apr 2024 13:40 UTC
50 points
13 comments8 min readLW link

Sim­ple dis­tri­bu­tion ap­prox­i­ma­tion: When sam­pled 100 times, can lan­guage mod­els yield 80% A and 20% B?

Teun van der Weij, Felix Hofstätter and Francis Rhys Ward
29 Jan 2024 0:24 UTC
39 points
5 comments4 min readLW link

Tall Tales at Differ­ent Scales: Eval­u­at­ing Scal­ing Trends For De­cep­tion In Lan­guage Models

Felix Hofstätter, Francis Rhys Ward, HarrietW, LAThomson, Ollie J, Patrik Bartak and Sam F. Brown
8 Nov 2023 11:37 UTC
49 points
0 comments18 min readLW link

Re­ward Hack­ing from a Causal Perspective

tom4everitt, Francis Rhys Ward, sbenthall, James Fox, mattmacdermott and RyanCarey
21 Jul 2023 18:27 UTC
29 points
6 comments7 min readLW link

Agency from a causal perspective

tom4everitt, mattmacdermott, James Fox, Francis Rhys Ward and Jonathan Richens
30 Jun 2023 17:37 UTC
40 points
5 comments6 min readLW link

Causal­ity: A Brief Introduction

tom4everitt, Lewis Hammond, Jonathan Richens, Francis Rhys Ward, RyanCarey, sbenthall and James Fox
20 Jun 2023 15:01 UTC
49 points
18 comments6 min readLW link

In­tro­duc­tion to Towards Causal Foun­da­tions of Safe AGI

tom4everitt, Lewis Hammond, Francis Rhys Ward, RyanCarey, James Fox, mattmacdermott and sbenthall
12 Jun 2023 17:55 UTC
74 points
6 comments4 min readLW link

For ev­ery choice of AGI difficulty, con­di­tion­ing on grad­ual take-off im­plies shorter timelines.

Francis Rhys Ward21 Apr 2022 7:44 UTC
31 points
13 comments3 min readLW link

On Agent In­cen­tives to Ma­nipu­late Hu­man Feed­back in Multi-Agent Re­ward Learn­ing Scenarios

Francis Rhys Ward3 Apr 2022 18:20 UTC
27 points
10 comments8 min readLW link